Technical Paper Table of Contents

ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | 978-1-7281-6327-7/23/$31.00 ©2023 IEEE | DOI: 10.1109/ICASSP49357.2023.10096024

Grand Challenges

6829: Multi-Speaker End-to-end Multi-modal Speaker Diarization System for the MISP 2022
CHALLENGE
Tao Liu (Shanghai Jiao Tong University)*; Zhengyang Chen (Shanghai Jiao Tong University); Yanmin
Qian (Shanghai Jiao Tong University); Kai Yu (Shanghai Jiao Tong University)

6832: HappyQuokka system for ICASSP 2023 Auditory EEG challenge

Zhenyu Piao (Yonsei University)*; Miseul Kim (Yonsei University); Hyungchan Yoon (Yonsei University);
Hong-Goo Kang (Yonsei University)

6834: HIGH-SPEED DRONE DETECTION BASED ON YOLO-V8

JUN-HWA KIM (Dongguk University)*; Namho KIM (Dongguk University); Chee Sun Won (Dongguk
University)

6848: The NPU-ASLP System for Audio-Visual Speech Recognition in MISP 2022 Challenge
Pengcheng Guo (Northwestern Polytechnical University)*; He Wang (NWPU); Bingshen Mu
(Northwestern Polytechnical University); Ao Zhang (Northwestern Polytechnical University); Peikun Chen
(Northwestern Polytechnical University)

6850: Personalized speech enhancement combining band-split RNN and speaker attentive module
Xiaohuai Le (Nanjing University；ByteDance)*; Li Chen (ByteDance); Yiqing Guo (ByteDance); Chao He
(ByteDance); Cheng Chen (ByteDance); Xianjun Xia (NA); Jing Lu (Nanjing University)

6852: MULTI-TASK SUB-BAND NETWORK FOR DEEP RESIDUAL ECHO SUPPRESSION

Jiayao Sun (Northwestern Polytechnical University)*; Dawei Luo (Li Auto); Zhaoxia LI (Li Auto); Jingdong
Li (Tencent ); Yukai Jv (Shaanxi Provincial Key Laboratory of Speech and Image Information Processing,
School of Computer Science, Northwestern Polytechnical University); Yang Li (Li Auto)

6853: Dialogue Context Modelling for Action Item Detection: Solution for ICASSP 2023 MUG
Challenge Track 5
Jie Huang (Harbin Institute of Technology); Xiachong Feng (Harbin Institute of Technology)*; Ye Yangfan
(HIT); Liang Zhao (HIT); Xiaocheng Feng (Harbin Institute of Technology); Bing Qin (Harbin Institute of
Technology); Ting Liu (哈尔滨工业大学)

6854: A Multi-stage Low-latency Enhancement System for Hearing Aids

Chengwei Ouyang (Orka Inc.)*; Kexin Fei (Orka Inc.); Haoshuai Zhou (Orka Inc.); Congxi Lu (Orka Inc.);
Linkai Li (Orka Inc.)

6855: Relate Auditory Speech to EEG by Shallow-Deep Attention-based Network

Fan Cui (Mi)*; Liyong Guo (Xiaomi Corp.); Lang He (XUPT); Jiyao Liu (NWPU); Ercheng Pei (XUPT);
Yujun Wang (Mi); Dongmei Jiang (Northwestern Polytechnical University \ Peng Cheng Laboratory)

6856: A Progressive Neural Network for Acoustic Echo Cancellation

Zhuangqi Chen (South China University of Technology); Xianjun Xia (RTC Lab, ByteDance)*; Siyu Sun
(Wuhan University); Ziqian Wang (Northwestern Polytechnical University); Cheng Chen (ByteDance);
Guoliang Xie (ByteDance); Pingjiang Zhang (South China University of Technology); Yijian Xiao
(ByteDance)

6857: INPLACE CEPSTRAL SPEECH ENHANCEMENT SYSTEM FOR THE ICASSP 2023 CLARITY
CHALLENGE
Jinjiang Liu (College of Computer Science, Inner Mongolia University)*; Xueliang zhang (Inner Mongolia
University)

12
6858: A_TAYLOR_STYLE_NEURAL_NETWORK_IN_FULLBAND_ECHO_CANCELLATION
Xu Weiming (Northwest Polytechnic University)*; Guo Zhihao (elevoc)

6859: Multi-Head Attention and GRU for Improved Match-Mismatch Classification of Speech
Stimulus and EEG Response
Marvin Borsdorf (University of Bremen)*; Saurav Pahuja (University of Bremen); Gabriel Ivucic (University
of Bremen); Siqi Cai (National University of Singapore); Haizhou Li (The Chinese University of Hong
Kong, Shenzhen); Tanja Schultz (University of Bremen)

6860: Multi-speaker Multi-lingual VQTTS System for LIMMITS 2023 Challenge

Chenpeng Du (Shanghai Jiao Tong University)*; Yiwei Guo (Shanghai Jiao Tong University); Feiyu Shen
(Shanghai Jiao Tong University); Kai Yu (Shanghai Jiao Tong University)

6861: RELATING EEG RECORDINGS TO SPEECH USING ENVELOPE TRACKING AND THE
SPEECH-FFR
Michael D Thornton (Imperial College London)*; Danilo Mandic (Imperial College London); Tobias
Reichenbach (FAU)

6863: S-FEATURE PYRAMID NETWORK AND ATTENTION MODEL FOR DRONE DETECTION
Pengcheng Dong (Shandong Normal University)*; Chuntao Wang (Shandong Normal University);
Zhenyong Lu (Shandong Normal University); Kai Zhang (Shandong Normal University); Wenbo Wan
(Shandong Normal University); Jiande Sun (Shandong Normal University)

6864: E-BRANCHFORMER-BASED E2E SLU TOWARD STOP ON-DEVICE CHALLENGE

Yosuke Kashiwagi (Sony)*; Siddhant Arora (Carnegie Mellon University); Hayato Futami (Sony Group
Corporation); Jessica Huynh (Carnegie Mellon University); Shih-Lun Wu (Carnegie Mellon University);
Yifan Peng (Carnegie Mellon University); Brian Yan (Carnegie Mellon University); Emiru Tsunoo (Sony
Group Corporation); Shinji Watanabe (Carnegie Mellon University)

6865: W2KPE: Keyphrase Extraction with Word-Word Relation

Wen Cheng (Nanjing University)*; Shichen Dong (Nanjing University); Wei Wang (Nanjing University)

6866: CONSEN: Complementary and Simultaneous Ensemble for Alzheimer's Disease Detection
and MMSE Score Prediction
LONGBIN JIN (Konkuk University)*; Yealim Oh (Konkuk University); Hyunseo Kim (Konkuk University);
Hyuntaek Jung (Konkuk University); Hyo Jin Jon (Konkuk University); Jung Eun Shin (Voinosis Inc.); Eun
Yi Kim (Konkuk University)

6867: The WHU-Alibaba Audio-Visual Speaker Diarization System for the MISP 2022 Challenge
Ming Cheng (Duke Kunshan University)*; Haoxu Wang (Wuhan University); Ziteng Wang (Alibaba
Group); Qiang Fu (Alibaba Group); Ming Li (Duke Kunshan University)

6868: A TWO-STAGE SYSTEM for SPOKEN LANGUAGE UNDERSTANDING

zhang gaosheng (transsion.com)*; shilei miao (传音控股); tang linghui (Transsion); qian peijia (Transsion)

6869: A Low-Latency Deep Hierarchical Fusion Network for Fullband Acoustic Echo Cancellation
Haoran Zhao (Kuaishou Technology)*; Nan Li (北京达佳互联信息技术有限公司); Runqiang Han
(kuaishou); Xiguang Zheng (北京达佳互联信息技术有限公司); Chen Zhang (北京达佳互联信息技术有限公
司)

13
6875: DEEP LEARNING-BASED PATH LOSS PREDICTION FOR OUTDOOR WIRELESS
COMMUNICATION SYSTEMS
Kehai Qiu (University of Cambridge)*; Stefanos Bakirtzis (University of Cambridge); Hui Song (Ranplan
Wireless Network Design Ltd); Ian J Wassell (University of Cambridge); Jie Zhang (University of
Sheffield)

6877: Ensemble and personalized Transformer models for subject identification and relapse
detection in e-Prevention Challenge
Salvatore Calcagno (University of Catania)*; Raffaele Mineo (University of Catania); Daniela Giordano
(University of Catania); Concetto Spampinato (University of Catania)

6878: Speech Signal Improvement Using Causal Generative Diffusion Models

Julius Richter (Universität Hamburg)*; Simon Welker (Universität Hamburg); Jean-Marie Lemercier
(Universität Hamburg); Bunlong Lay (Universität Hamburg); Tal Peer (Universität Hamburg); Timo
Gerkmann (Universität Hamburg)

6879: A Transformer-Based E2E SLU model for Improved Semantic Parsing

Othman Istaiteh (Samsung Research Jordan)*; Yasmeen Kussad (Samsung Research Jordan); Yahya
Daqour (Samsung Research Jordan); Maria Habib (Samsung); Mohammad Habash (Samsung Research
Jordan); Dhananjaya Gowda (Samsung Electronics)

6880: Half-temporal and half-frequency attention U2Net for speech signal improvement
Zehua Zhang (Harbin Institute of Technology(Shenzhen))*; Shiyun Xu (Harbin Institute of
Technology(Shenzhen)); Xuyi Zhuang (Harbin Institute of Technology(Shenzhen)); Yukun Qian (Harbin
Institute of Technology (Shenzhen)); Lianyu Zhou (Harbin Institute of Technology(Shenzhen)); Mingjiang
Wang (Harbin Institute of Technology Shenzhen)

6881: DRONE-VS-BIRD: DRONE DETECTION USING YOLOV7 WITH CSRT TRACKER

Sahaj K Mistry (Indian Institute of Technology Jammu)*; Shreyas Chatterjee (Indian Institute of
Technology Jammu); Ajeet Kumar Verma (Indian Institute of Technology Jammu); Vinit Jakhetiya (IIT
JAMMU); Badri Subudhi (Indian Institute of Technology, Jammu); Sunil Jaiswal (K|Lens GmbH)

6882: Decoding Auditory EEG Responses using an Adapted WaveNet

Bob M.S.L. Van Dyck (KU Leuven)*; Liuyin Yang (KU Leuven); Marc Van Hulle (KU Leuven)

6883: Agile Radio Map Prediction Using Deep Learning

Enes Krijestorac (University of California, Los Angeles); Hazem Sallouha (KU Leuven)*; Shamik Sarkar
(University of California, Los Angeles); Danijela Cabric (University of California, Los Angeles)

6885: A Study on the Integration of Pipeline and E2E SLU systems for Spoken Semantic Parsing
toward STOP Quality Challenge
Siddhant Arora (Carnegie Mellon University)*; Hayato Futami (Sony Group Corporation); Shih-Lun Wu
(Carnegie Mellon University); Jessica Huynh (Carnegie Mellon University); Yifan Peng (Carnegie Mellon
University); Yosuke Kashiwagi (Sony); Emiru Tsunoo (Sony Group Corporation); Brian Yan (Carnegie
Mellon University); Shinji Watanabe (Carnegie Mellon University)

6887: Multi-Channel Speaker Extraction with Adversarial Training: the Wavlab submission to the
Clarity ICASSP 2023 Grand Challenge
Samuele Cornell (Università Politecnica delle Marche)*; Zhong-Qiu Wang (Carnegie Mellon University);
Yoshiki Masuyama (Tokyo Metropolitan University); Shinji Watanabe (Carnegie Mellon University);
Manuel Pariente (Pulse Audition); Nobutaka Ono (Tokyo Metropolitan University); Stefano Squartini
(Università Politecnica delle Marche)

14
6891: PMNet: Large-Scale Channel Prediction System for ICASSP 2023 First Pathloss Radio Map
Prediction Challenge
Ju-Hyung Lee (University of Southern California)*; Joohan Lee (University of Southern California); Seon-
Ho Lee (MCL, Korea University); Andreas Molisch (University of Southern California)

6892: The pipeline system of ASR and NLU with MLM-based data augmentation toward STOP low-
resource challenge
Hayato Futami (Sony Group Corporation)*; Jessica Huynh (Carnegie Mellon University); Siddhant Arora
(Carnegie Mellon University); Shih-Lun Wu (Carnegie Mellon University); Yosuke Kashiwagi (Sony); Yifan
Peng (Carnegie Mellon University); Brian Yan (Carnegie Mellon University); Emiru Tsunoo (Sony Group
Corporation); Shinji Watanabe (Carnegie Mellon University)

6893: Exploring Language-Agnostic Speech Representations using Domain Knowledge for

Detecting Alzheimer's Dementia
Zehra Shah (University of Alberta)*; Shi-ang Qi (University of Alberta); Fei Wang (University of Alberta);
Mahtab Farrokh (University of Alberta); Mashrura Tasnim (University of Alberta); Eleni Stroulia (University
of Alberta); Russell Greiner (U Alberta); Manos Plitsis (Athena Research Center); Athanasios Katsamanis
("ATHENA R.C., Behavioral Signal Technologies")

6896: The USTC System for ADReSS-M Challenge

Kangdi Mei (University of Science and Technology of China); Xinyun Ding (iFlytek Research); yinlong liu
(USTC); Zhiqiang Guo (University of Science and Technology of China); Feiyang Xu (iFlytek Co.Ltd); Xin
Li (University of Science and Technology of China); Tuya Naren (University of Science and Technology of
China); Jiahong Yuan (University of Science and Technology of China)*; Zhen-Hua Ling (University of
Science and Technology of China)

6897: VANI: Very-lightweight Accent-controllable TTS for Native and Non-native speakers with
Identity Preservation
Rohan Badlani (NVIDIA)*; Akshit Arora (NVIDIA); Subhankar Ghosh (NVIDIA); Rafael Valle (NVIDIA);
Kevin Shih (NVIDIA); João Felipe Santos (NVIDIA); Boris Ginsburg (NVIDIA); Bryan Catanzaro (NVIDIA)

6898: Cross-lingual Alzheimer's disease detection based on paralinguistic and pre-trained

features
Chen Xuchu (Tsinghua University); Yu Pu (Tsinghua University); Jinpeng Li (Tsinghua University); Wei-
Qiang Zhang (Tsinghua University)*

6899: TWO-STEP BAND-SPLIT NEURAL NETWORK APPROACH FOR FULL-BAND RESIDUAL

ECHO SUPPRESSION
Zihan Zhang (Northwestern Polytechnical University)*; Shimin Zhang (Northwestern Polytechnical
University); Mingshuai Liu (NWPU); Yanhong Leng (Bytedance Inc); Zhe Han (ByteDance); Li Chen
(ByteDance ); Lei Xie (NWPU)

6900: A person identification system for the ICASSP 2023 e-Prevention challenge
Jinting Wu (Samsung Research China-Beijing (SRC-B))*; Mei Tu (Samsung)

6902: HITsz TMG at ICASSP 2023 SPGC: Leveraging pre-training and distillation method for title
generation with limited resource
Tianxiao Xu (Harbin Institute of Technology, shenzhen)*; Zihao Zheng ( Harbin Institute of Technology,
shenzhen ); Xinshuo Hu (Harbin Institute of Technology, Shenzhen); Zetian Sun (Harbin Institute of
Technology, shenzhen); Yu Zhao (Harbin Institute of Technology, Shenzhen); Baotian Hu (Harbin Institute
of Technology, Shenzhen)

15
6903: LeanSpeech: The Microsoft Lightweight Speech Synthesis System for LIMMITS Challenge
2023
Chen Zhang (Microsoft)*; SHUBHAM BANSAL (Microsoft); Aakash Lakhera (Microsoft); Jinzhu Li
(Microsoft); Gag Wang (Microsoft); Sandeep kumar Satpal (Microsoft,India); sheng zhao (microsoft); Lei
He (Microsoft Cloud and AI)

6904: The NPU-Elevoc Personalized Speech Enhancement System for ICASSP2023 DNS Challenge
Xiaopeng Yan (Northwestern Polytechnical University)*; Yindi Yang (Elevoc); Zhihao Guo (Elevoc);
Liangliang Peng (Elevoc); Lei Xie (NWPU)

6905: The XMU system for audio-visual diarization and recognition in MISP challenge 2022
Tao Li (Xiamen University)*; Haodong Zhou (Xiamen University); Jie Wang (Xiamen University); Qingyang
Hong (Xiamen University); Lin Li (Xiamen University)

6906: Gesper: A Unified Framework for General Speech Restoration

Jun Chen (Tsinghua University); yupeng shi (tencent); wenzhe liu (Tencent); Wei Rao (Tencent)*; shulin
何 (Tencent); Andong Li (Institute of Acoustics, Chinese Academy of Sciences); Yannan Wang (Tencent);
Zhiyong Wu (Tsinghua University); Shi-dong Shang (tencent); Chengshi Zheng (Chinese Academy of
Science)

6908: A LOW-LATENCY HYBRID MULTI-CHANNEL SPEECH ENHANCEMENT SYSTEM FOR

HEARING AIDS
Tong Lei (Nanjing University)*; Zhongshu Hou (Nanjing University); Yuxiang Hu (Horizon Robotics);
Wanyu Yang (Horizon Robotics); Tianchi Sun (Nanjing University); Xiaobin Rong (Nanjing University);
Dahan Wang (Nanjing University); Kai Chen (Nanjing University); Jing Lu (Nanjing University)

6909: TEA-PSE 3.0: TENCENT-ETHEREAL-AUDIO-LAB PERSONALIZED SPEECH ENHANCEMENT

SYSTEM FOR ICASSP 2023 DNS-CHALLENGE
Yukai Jv (Shaanxi Provincial Key Laboratory of Speech and Image Information Processing, School of
Computer Science, Northwestern Polytechnical University)*; Jun Chen (Tencent); Shimin Zhang
(Northwestern Polytechnical University); Shulin He (College of Computer Science, Inner Mongolia
University); Wei Rao (Tencent); weixin zhu (tencent); Yannan Wang (Tencent); Tao Yu (Tencent); Shi-
dong Shang (tencent)

6910: Tspeech-AI System Description to the 5th Deep Noise Suppression (DNS) Challenge
Jianwei Yu (Tencent AI lab)*; Hangting Chen (Tencent ASSP OTeam); Yi Luo (Tencent AI Lab); Rongzhi
Gu (Tencent); Chao Weng (Tencent AI Lab)

6911: SSI-Net: A MULTI-STAGE SPEECH SIGNAL IMPROVEMENT SYSTEM FOR ICASSP 2023 SSI
CHALLENGE
weixin zhu (tencent)*; Zilin Wang (Tsinghua University); Jiuxin Lin (Tsinghua University); Chang Zeng
(National Institute of Informatics); Tao Yu (Tencent)

6912: POST-TRAINED LANGUAGE MODEL ADAPTIVE TO EXTRACTIVE SUMMARIZATION OF

LONG SPOKEN DOCUMENTS
Hyunjong Ok (Kyung Hee University); Seong-Bae Park (Kyung Hee University)*

6914: CONVOLUTIONAL RECURRENT METRICGAN WITH SPECTRAL DIMENSION COMPRESSION

FOR FULL-BAND SPEECH ENHANCEMENT
Zhongshu Hou (Nanjing University); Qinwen Hu (Nanjing University)*; Tianchi Sun (Nanjing University);
Yuxiang Hu (Horizon Robotics); Changbao Zhu (Horizon Robotics); Kai Chen (Nanjing University)

6915: THE AJMIDE TOPIC SEGMENTATION SYSTEM FOR THE ICASSP 2023 GENERAL MEETING
UNDERSTANDING AND GENERATION CHALLENGE
Beibei Hu (Ajmide Media)*; Qiang Li (Ajmide Media); Xianjun Xia (Ajmide Media)

16
6916: Signal Processing Grand Challenge 2023 - e-Prevention: Sleep Behavior as an Indicator of
Relapses in Psychotic Patients
Kleanthis Avramidis (University of Southern California)*; Kranti Adsul (University of Southern California);
Digbalay Bose (University of Southern California); Shrikanth Narayanan (USC)

6917: Dual-Path Dilated Convolutional Recurrent Network with Group Attention for Multi-Channel
Speech Enhancement
Jiaming Cheng (Southeast University)*; Cong Pang (Southeast University); Ruiyu Liang (Southeast
University); Jingjie Fan (Southeast University); Li Zhao (Southeast University)

6918: Lightweight Prosody-TTS for multi-lingual multi-speaker scenario

Giridhar Pamisetty (IIT Hyderabad)*; Chaitanya Varun Sahukari (IIT Hyderabad); Sri Rama Murty
Kodukula (IIT Hyderabad)

6919: TWO-STAGE NEURAL NETWORK FOR ICASSP 2023 SPEECH SIGNAL IMPROVEMENT
CHALLENGE
Mingshuai Liu (NWPU)*; Shubo Lv (Shaanxi Provincial Key Laboratory of Speech and Image Information
Processing, School of Computer Science, Northwestern Polytechnical University); Zihan Zhang
(Northwestern Polytechnical University); Runduo Han (Northwestern Polytechnical University); Xiang Hao
(NWPU); Xianjun Xia (ByteDance); Li Chen (ByteDance ); Yijian Xiao (ByteDance); Lei Xie (NWPU)

6921: REPLAPSE DETECTION IN PATIENTS WITH PSYCHOTIC DISORDERS USING

UNSUPERVISED LEARNING ON SMARTWATCH SIGNALS
Salam Hamieh (CEA)*; Christelle Godin (CEA); vincent heiries (CEA); Hussein Al Osman (University of
Ottawa)

6923: THE NIO SYSTEM FOR AUDIO-VISUAL DIARIZATION AND RECOGNITION IN MISP
CHALLENGE 2022
Gaopeng Xu (nio)*; Xianliang Wang (nio); Sang Wang (nio); junfeng yuan (nio); Wei Guo (nio); Wei Li
(nio); Jie Gao (nio)

6925: STREAM ATTENTION BASED U-NET FOR L3DAS23 CHALLENGE

Honglong Wang ( Tianjin University)*; Yanjie Fu (Tianjin University); Junjie Li (Tianjin University); Meng
Ge (Tianjin University); Longbiao Wang (Tianjin University); xinyuan qian (National University of
Singapore)

6926: 3D audio signal processing systems for speech enhancement and sound localization and
detection
Jisheng Bai (School of Marine Science and Technology, Northwestern Polytechnical University)*; Siwei
Huang (JLESS); Han Yin (JLESS); Mou Wang (Northwestern Polytechnical University); Yafei Jia (School
of Marine Science and Technology, Northwestern Polytechnical University); Jianfeng Chen (School of
Marine Science and Technology, Northwestern Polytechnical University)

6929: THE NERCSLIP-USTC SYSTEM FOR THE L3DAS23 CHALLENGE TASK2: 3D SOUND EVENT
LOCALIZATION AND DETECTION (SELD)
Haoyin Yan (University of Science and Technology of China)*; Haitao Xu ( University of Science and
Technology of China); Jie Zhang (University of Science and Technology of China); Qing Wang (University
of Science and Technology of China)

6930: Cross-Lingual Transfer Learning for Alzheimer’s Detection From Spontaneous Speech
Bastiaan Tamm (KU Leuven)*; Rik Vandenberghe (University of Leuven); Hugo Van hamme (KU Leuven)

6965: PERSON IDENTIFICATION WITH WEARABLE SENSING USING MISSING FEATURE

ENCODING AND MULTI-STAGE MODALITY FUSION
Payal Mohapatra (Northwestern University)*; Akash Pandey (Northwestern University ); Sinan Keten
(Northwestern University); Wei Chen (" Northwestern University, UK"); Zhu Qi (Northwestern University)

17
7015: Lightweight Machine Learning for Seizure Detection on Wearable Devices
Baichuan Huang (Lund University)*; Azra Abtahi (Lund University); Amir Aminifar (Lund University)

7021: Pretrained Transformers for Seizure Detection

Saarang Panchavati (UCLA)*; Samuel Vander Dussen (UCLA); Hemal Semwal (UCLA); Ahmed Ali
(UCLA); Justin Chen (UCLA); Haoran Li (UCLA); Corey Arnold (UCLA); William Speier (UCLA)

7022: Towards Interpretable Seizure Detection Using Wearables

Irfan Al-Hussaini (Georgia Institute of Technology)*; Cassie S Mitchell (Georgia Institute of Technology)

7033: OPTIMIZATION OF THE DEEP NEURAL NETWORKS FOR SEIZURE DETECTION

Andrey Kiryasov (Brainify.AI); Aleksei Shovkun (Brainify.AI); Ilya Zakharov (Brainify.AI)*

18
 Applied Signal Processing Systems

246: An Evaluation Platform to Scope Performance of Synthetic Environments in Autonomous

Ground Vehicles Simulation
Xiangyu Bai (Northeastern University); Jiang Le (Northeastern University ); Yedi Luo (Northeastern
University); Aniket Gupta (Northeastern University); Pushyami Kaveti (Northeastern University);
Hanumant Singh (Northeastern University); Sarah Ostadabbas (Northeastern University)*

256: NL-DSE: Non-Local Neural Network with Decoder-Squeeze-and-Excitation for Monocular

Depth Estimation
Tsung-Han Tsai (National Central University)*; Wei-Chung Wan (NCU)

286: mmSense: Detecting Concealed Weapons with a Miniature Radar Sensor

Kevin Mitchell (University of Glasgow); Khaled Kassem (University of Glasgow); Chaitanya Kaul
(University of Glasgow)*; Valentin Kapitany (University of Glasgow); Philip Binner (University of Glasgow);
Andrew Ramsay (University of Glasgow); Daniele Faccio (University of Glasgow); Roderick Murray-Smith
(University of Glasgow)

328: Hardware-limited Non-uniform Task-based Quantizers

Neil Irwin M Bernardo (University of Melbourne)*; Jingge Zhu (University of Melbourne); Yonina Eldar ();
Jamie S Evans (University of Melbourne)

394: Robust Dominant Periodicity Detection for Time Series with Missing Data
Qingsong Wen (Alibaba DAMO Academy)*; Linxiao Yang (Machine Intelligence Technology, Alibaba
Group, Hangzhou, China); Liang Sun (Alibaba Group)

454: Knowledge-graph Augmented Music Representation for Genre Classification

Han Ding (Xi'an Jiaotong University)*; Wenjing Song (Xi'an Jiaotong University); Cui Zhao (Xi'an Jiaotong
University); Fei Wang (Xi'an Jiaotong University); Ge Wang (Xi'an Jiaotong University); Wei Xi (Xi'an
Jiaotong University); Jizhong Zhao (Xi'an Jiaotong University)

1034: UNOBTRUSIVE RESPIRATORY MONITORING SYSTEM FOR INTENSIVE CARE

Xudong Tan (East China Normal University); Menghan Hu (East China Normal University)*; Guangtao
Zhai (Shanghai Jiao Tong University); Yan Zhu (Shanghai Changzheng Hospital); Wenfang Li (Shanghai
Changzheng Hospital); Xiao-Ping Zhang (Ryerson University)

1054: An Adaptive DFE Using Light-Pattern-Protection Algorithm in 12 nm CMOS Technology

Shiyuan Xing (Institute of Computing Technology, Chinese Academy of Sciences ；University of Chinese
Academy of Sciences)*; Changlong Lin (Loongson Technology Corporation); Yuchen Li (Loongson
Technology Corporation); Huandong Wang (Loongson Technology Corporation)

1069: Residual Squeeze-and-Excitation U-shaped Network for Minutia Extraction in Contactless

Fingerprint Images
Anderson Cotrim (Institute of Computing - UNICAMP); Helio Pedrini (Institute of Computing - UNICAMP)*

1115: Code-Enhanced Fine-Grained Semantic Matching for Tag Recommendation in Software

Information Sites
Lin Li (Wuhan University of Technology)*; Peipei Wang (Wuhan University of Technology); Xinhao Zheng
(Wuhan University of Technology); Qing Xie (Wuhan University of Technology)

1171: Improved Indoor Localization With NLOS Signal Propagations

Wei Huang (Southwest University); Yixin Zhao (Southwest University); Xuechao Wu (Southwest
University); Le Yin (Southwest University)*

19
1603: TSPTQ-ViT: TWO-SCALED POST-TRAINING QUANTIZATION FOR VISION TRANSFORMER
Yu Shan Tai (National Taiwan University GIEE)*; Ming Guang Lin (National Taiwan University GIEE); An-
Yeu (Andy) Wu (National Taiwan University)

1724: Adaptive Noise Canceller Algorithm with SNR-Based Stepsize and Data-Dependent
Averaging
Akihiko K. Sugiyama (Yahoo Japan Corporation)*

1752: HIERARCHICAL MULTI-AGENT REINFORCEMENT LEARNING WITH INTRINSIC REWARD

RECTIFICATION
Zhihao Liu (Institute of Automation, Chinese Academy of Sciences)*; Zhiwei Xu (Institute of Automation,
Chinese Academy of Sciences); Guoliang Fan (Institute of Automation, Chinese Academy of Sciences)

2043: DailyTalk: Spoken Dialogue Dataset for Conversational Text-to-Speech

Keon Lee (KRAFTON, Inc.)*; Kyumin Park (KAIST); Daeyoung Kim (KAIST)

2355: Parallel 2D Seismic Ray Tracing using CUDA on a Jetson Nano

Ban-Sok Shin (German Aerospace Center)*; Luis Wientgens (German Aerospace Center); Dmitriy Shutin
(DLR)

2421: RGB-D BASED POSE-INVARIANT FACE RECOGNITION VIA ATTENTION DECOMPOSITION

MODULE
Wei-Chen Lin (Department of Computer Science, National Tsing Hua University); Ching-Te Chiu (National
Tsing Hua University); Kuan-Chang Shih (Department of Computer Science, National Tsing Hua
University)*

2458: DESIGN AND PERFORMANCE OF THE LOW-POWER NOISE REDUCTION ALGORITHM OF

THE MED-EL SONNET 2 COCHLEAR IMPLANT AUDIO PROCESSOR
Ernst Aschbacher (MED-EL)*; Florian Fruehauf (MED-EL); Anja Kurz (University Hospital of Würzburg);
Peter Nopp (MED-EL)

3000: PREFALLKD: PRE-IMPACT FALL DETECTION VIA CNN-VIT KNOWLEDGE DISTILLATION

Tin-Han Chi (Department of Biomedical Engineering, National Yang Ming Chiao Tung University); Kai-
Chun Liu (Academia Sinica); Chia-Yeh Hsieh (Bachelor’s Program in Medical Informatics and Innovative
Applications, Fu Jen Catholic University); Yu Tsao (Academia Sinica)*; Chia-Tai Chan (Department of
Biomedical Engineering, National Yang Ming Chiao Tung University)

3040: COOPERATIVE FIVE DEGREES OF FREEDOM MOTION ESTIMATION FOR A SWARM OF

AUTONOMOUS VEHICLES
Nikos Piperigkos (University of Patras/ATHENA Research Center)*; Aris Lalos (Industrial Systems
Institute, Athena Research Center); Kostas Berberidis (University of Patras); Christos Anagnostopoulos
(Industrial Systems Institute, Athena Research and Innovation Center)

3109: CUTTING THROUGH THE NOISE: AN EMPIRICAL COMPARISON OF PSYCHOACOUSTIC

AND ENVELOPE-BASED FEATURES FOR MACHINERY FAULT DETECTION
Peter Wißbrock (Lenze SE)*; Yvonne Richter (FH Bielefeld); David Pelkmann (Fachhochschule Bielefeld);
Zhao Ren (L3S Research Center); Gregory Palmer (L3S Research Center)

3136: Tracking Targets in Hyper-scale Cameras using Movement Predication

Jiaping Yu (National University of Defense Technology)*; Tongqing Zhou (National University of Defense
Technology); Zhiping Cai (NUDT); Wenyuan Kuang (360 Digital Security Group)

3137: Real-time modelling of observation filter in the Remote Microphone Technique for an Active
Noise Control application
Chung Kwan Lai (Nanyang Technological University)*; Bhan Lam (NTU); Dongyuan Shi (NTU); Woon
Seng Gan (NTU )

20
3293: Single-anchor UWB Localization using Channel Impulse Response Distributions
Sitian Li (EPFL)*; Alexios Balatsoukas-Stimming (Eindhoven University of Technology); Andreas Burg
(EPFL)

3320: FedAudio: A Federated Learning Benchmark for Audio Tasks

Tuo Zhang (University of Southern California)*; Tiantian Feng (University of Southern California); Samiul
Alam (Michigan State University); Sunwoo Lee (Inha University); Mi Zhang (The Ohio State University);
Shrikanth Narayanan (University of Southern California); Salman Avestimehr (University of Southern
California)

3418: Implementing Continuous HRTF Measurement in Near-Field

Ee-Leng Tan (Nanyang Technological University)*; Santi Peksi (NTU Singapore); Woon Seng Gan (NTU)

3493: AN ANTISPOOFING APPROACH IN BIOMETRIC AUTHENTICATION SYSTEM FOR A

SMARTCARD
Han-Sol Lee (Samsung Electronics)*; Moon-Kyu Song (Samsung Electronics); Junseo Lee (Samsung
Electronics); Yeolmin Seong (Samsung Electronics); Ducksoo Kim (Samsung Electronics); Kwanghyuk
Bae (Samsung Electronics); Seongwook Song (Samsung Electronics)

3576: UNSUPERVISED DOMAIN ADAPTATION VIA SUBSPACE INTERPOLATING DEEP

DICTIONARY LEARNING: A CASE STUDY IN MACHINE INSPECTION
Kriti Kumar (TCS Research and Innovation)*; Angshul Majumdar (IIIT Delhi); Achanna Anil Kumar (Tata
Consultancy Services); Mariswamy Girish Chandra ( Tata Consultancy Services)

3733: Finding Optimal Numerical Format for Sub-8-bit Post-Training Quantization of Vision
Transformers
Janghwan Lee (Hanyang University)*; Youngdeok Hwang (Baruch College - The City University of New
York (CUNY)); Jungwook Choi (Hanyang University)

3925: Low-Complexity Low-Rank Approximation SVD for Massive Matrix in Tensor Train Format
Jung-Chun Chi (National Tsing Hua University); Chiao-En Chen (National Chung Hsing University); Yuan-
Hao Huang (National Tsing Hua University)*

3961: A Multi-Channel Aggregation Framework for Object Detection in Large-Scale SAR Image
Chule Yang (Defense Innovation Institute（DII）)*; Chao Zhang (College of Computer Science and
Technology, Harbin Engineering University); Zunlin Fan (National Innovation Institute of Defense
Technology, China); Zeting Yu ( Defense Innovation Institute（DII）); Qianchong Sun (Defense
Innovation Institute（DII）); Mengyuan Dai (Defense Innovation Institute (DII))

3994: Dynamic Split Computing for Efficient Deep Edge Intelligence

Arian Bakhtiarnia (Aarhus University)*; Nemanja B Milosevic (UNSPMF); Qi Zhang (Aarhus University);
Dragana Bajovic (University of Novi Sad, Serbia); Alexandros Iosifidis (Aarhus University)

4052: MULTIRESOLUTION SIGNAL PROCESSING OF FINANCIAL MARKET OBJECTS

Ioana Boier (Nvidia )*

4081: RIS REFLECTION AND PLACEMENT OPTIMISATION FOR UNDERLAY D2D

COMMUNICATIONS IN COGNITIVE CELLULAR NETWORKS
Sarbani Ghose (DSZ Innovation Labs Private Limited)*; Deepak Mishra (University of New South Wales);
Santi P. Maity (Indian Institution of Engineering Science and Technology); George Alexandropoulos
(National and Kapodistrian University of Athens)

21
4116: A Momentum Two-gradient Direction Algorithm with Variable Step Size Applied to Solve
Practical Output Constraint Issue for Active Noise Control
Xiaoyi Shen (Nanyang Technological University)*; Dongyuan Shi (Nanyang Technological University);
Zhengding Luo (Nanyang Technological University); Junwei Ji (Nanyang Technological University); Woon
Seng Gan (NTU )

4381: IMPROVED WIFI-BASED RESPIRATION TRACKING VIA CONTRAST ENHANCEMENT

Wei-Hsiang Wang (University of Maryland, College Park)*; Xiaolu Zeng (Beijing Institute of Technology);
Beibei Wang (Origin Wireless Inc.); K. J. Ray Liu (Origin Wireless Inc.)

4620: VAN-ICP: GPU-Accelerated Approximate Nearest Neighbor Search for ICP Registration via
Voxel Dilation
Weimin Wang (Dalian University of Technology)*; Qiong Chang (Tokyo Institute of Technology)

4820: Recursive/Iterative unique Projection-Aggregation decoding of Reed-Muller codes

Marzieh Hashemipour-Nazari (Eindhoven University of Technology)*; Renate Debets (Eindhoven
University of Technology); Kees Goossens (Eindhoven University of Technology); Alexios Balatsoukas-
Stimming (Eindhoven University of Technology)

4821: WIFI-BASED ROBUST CHILD PRESENCE DETECTION FOR SMART CARS

Sakila S Jayaweera (University of Maryland, College Park)*; Beibei Wang (Origin Wireless Inc.); Xiaolu
Zeng (Beijing Institute of Technology); Wei-Hsiang Wang (University of Maryland, College Park); K. J. Ray
Liu (Origin Wireless Inc.)

4835: Cochlear Decomposition: A Novel Bio-Inspired Multiscale Analysis Framework

Hessa Alfalahi (Khalifa University of Science and Technology)*; Ahsan Khandoker (Khalifa Univerisity);
Ghada Alhussein (Khalifa University of Science and Technology); Leontios Hadjileontiadis (Khalifa
University of Science and Technology)

4851: Joint Angle and Respiration Estimation for Passive and Device-Free Respiration Monitoring
Gerrit Maus (University of Wuppertal)*; Dieter Brückmann (University of Wuppertal)

4965: Benchmarking Convolutional Neural Network Inference on Low-Power Edge Devices

Oscar Ferraz (IT, Dep. of Electrical and Computer Engineering, University of Coimbra, Portugal)*; Helder
Araujo (University of Coimbra); Vitor Silva (IT, Dep. of Electrical and Computer Engineering, University of
Coimbra, Portugal); Gabriel Falcao (IT, University of Coimbra, Portugal)

4985: Boosting the Accuracy of SRAM-Based In-Memory Architectures via Maximum Likelihood-
based Error Compensation Methods
Hyungyo Kim (University of Illinois at Urbana-Champaign)*; Naresh Shanbhag (University of Illinois at
Urbana-Champaign)

5009: Unlimited Sampling Radar: Life Below the Quantization Noise

Thomas Feuillen (Imperial College London)*; Bhavani Shankar Mysore Ramarao (University of
Luxembourg); Ayush Bhandari (Imperial College London)

5094: SeliNet: A Lightweight Model for Single Channel Speech Separation

Ha Minh Tan (National Central University); Duc-Quang Vu (Thai Nguyen Univerisity of Education); Jia-
Ching Wang (National Central University)*

5196: ADAPTIVE TIME-SCALE MODIFICATION FOR IMPROVING SPEECH INTELLIGIBILITY BASED

ON PHONEME CLUSTERING FOR STREAMING SERVICES
Sohee Jang (Hanyang University)*; Jiye Kim (Hanyang University); Yeon-Ju Kim (Hanyang University);
Joon-Hyuk Chang (Hanyang University)

22
5231: TEFISTA-Net: GTD Parameter Estimation of Low-Frequency Ultra-Wideband Radar via
Model-Based Deep Learning
Rui Li (Tsinghua University)*; Xueqian Wang (Tsinghua University); Gang Li (Tsinghua University); Xiao-
Ping Zhang (Toronto Metropolitan University)

5441: Enhancing the Accuracy of Resistive In-memory Architectures using Adaptive Signal
Processing
Han-Mo Ou (University of Illinois Urbana-Champaign)*; Naresh Shanbhag (University of Illinois at
Urbana-Champaign)

5600: Improved Belief Propagation Decoding of Turbo Codes

Yifei Shen (EPFL); Yuqing Ren (EPFL); AndreasToftegaard Kristensen (Ecole Polytechnique Federale de
Lausanne (EPFL)); Xiaohu You (Southeast University); Chuan Zhang (Southeast University)*; Andreas
Burg (EPFL)

5723: DENSE ADVERSARIAL TRANSFER LEARNING BASED ON CLASS-INVARIANCE

Bach-Tung Pham ( National Central University); Ting-Yu Wang (National Central University); Le
Phuong (National Central University); Khai-Thinh Nguyen (National Central University); Yuan-Shan Lee
(National Central University); Tzu-Chiang Tai (Providence University); Jia-Ching Wang (National Central
University)*

5776: Clustering-based Supervised Contrastive Learning for Identifying Risk Items on

Heterogeneous Graph
Ao Li (Alibaba Group); Yugang Ji (Alibaba Group)*; Guanyi Chu (Alibaba Group); Xiao Wang (Beijing
University of Posts and Telecommunications); Dong Li ( Alibaba Group); Chuan Shi (Beijing University of
Posts and Telecommunications)

5872: ClassA Entropy for the analysis of structural complexity of physiological signals
Hongjian Xiao (Imperial College London)*; Ling Li (City, University of London ); Danilo P. Mandic
((Imperial College of London, UK))

5968: CANCELLING INTERMODULATION DISTORTIONS FOR OTOACOUSTIC EMISSION

MEASUREMENTS WITH EARBUDS
Berken Utku Demirel (Nokia Bell Labs); Khaldoon T Al-Naimi (Nokia Bell Labs); Fahim Kawsar (Nokia Bell
Labs); Alessandro Montanari (Nokia Bell Labs)*

6094: Optimization of Sensor Configurations for Fault Identification in Smart Buildings

Naveed Ahmad (INSA Lyon); Malcolm Egan (INRIA)*; Jean-Marie Gorce (INSA Lyon); Jilles Steeve
Dibangoye (INSA Lyon, INRIA); Frederic Le-Mouel (INSA Lyon)

6301: Multiple Target Measurements: Bayesian Framework for Moving Object Detection in MIMO
Radar
Bastian Eisele (Friedrich-Alexander-Universität Erlangen-Nürnberg)*; Ali Bereyhi (Friedrich-Alexander-
Universität Erlangen-Nürnberg); Ralf Müller (Friedrich-Alexander-Universität Erlangen-Nürnberg)

6355: Causal discovery and causal inference based counterfactual fairness in machine learning
Yajing Wang (BNU-HKBU United International College)*; Zongwei Luo (BNU ZH)

6365: CAN2V: CAN-BUS DATA-BASED SEQ2SEQ MODEL FOR VEHICLE VELOCITY PREDICTION
Jae-Heung Cho (Hanyang University); Joon-Hyuk Chang (Hanyang University)*

6443: LMBAO: A Landmark Map for Bundle Adjustment Odometry in LiDAR SLAM
Letian Zhang (Sun Yat-sen University); Jinping Wang (Sun Yat-sen University); Jie Lu (Sun Yat-sen
University); Nanjie Chen (Sun Yat-sen University); Xiaojun Tan (Sun Yat-sen University)*; Duan Zhifei
(XPeng Inc)

23
6491: Modulo EEG Signal Recovery using Transformer
Tianyu Geng (Nanyang Technological University); Feng Ji (Nanyang Technological University); Pratibha
Rana (Agency for Science, Technology and Research); Wee Peng Tay (Nanyang Technological
University)*

6551: ON THE QUANTIZATION OF RECURRENT NEURAL NETWORKS FOR SMILES GENERATION

Adriano Durao (IT / Dep. of Electrical and Computer Engineering, University of Coimbra, Portugal); Joel
Arrais (CISUC, University of Coimbra); Bernardete Ribeiro (CISUC, University of Coimbra); Gabriel
Falcao (IT, University of Coimbra, Portugal)*

24
 Audio and Acoustic Signal Processing

185: Play It Back: Iterative Attention for Audio Recognition

Alexandros Stergiou (Vrije Universiteit Brussel)*; Dima Damen (University of Bristol)

224: CLAP Learning Audio Concepts From Natural Language Supervision

Benjamin Elizalde (Microsoft)*; Soham Deshmukh (Microsoft); Mahmoud Al Ismail (Microsoft); Huaming
Wang (Microsoft)

249: Compose & Embellish: Well-Structured Piano Performance Generation via A Two-Stage
Approach
Shih-Lun Wu (National Taiwan University)*; Yi-Hsuan Yang (Academia Sinica)

267: RNN-based step-size estimation for the RLS algorithm with application to acoustic echo
cancellation
Ofer Schwartz (CEVA Inc.)*; Ayal Schwartz (BIU)

317: Few-shot continual learning with weight alignment and positive enhancement for bioacoustic
event detection
Xiaoxiao Wu (Shanghai Normal University); Dongxing Xu (Unisound AI Technology Co., Ltd., Beijing);
Haoran Wei (University of Texas at Dallas); yanhua long (Shanghai Normal University)*

325: Multiscale Audio Spectrogram Transformer for Efficient Audio Classification

Wentao Zhu (Amazon)*; Mohamed Omar (Amazon)

339: Pop2Piano : Pop Audio-based Piano Cover Generation

Jongho Choi (rebellions Inc.)*; Kyogu Lee (Seoul National University)

348: Soft Dynamic Time Warping for Multi-Pitch Estimation and Beyond
Michael Krause (International Audio Laboratories Erlangen)*; Christof Weiß (University of Würzburg);
Meinard Müller (International Audio Laboratories Erlangen)

407: Multitrack Music Transformer

Hao-Wen Dong (University of California San Diego)*; Ke Chen (University of California San Diego);
Shlomo Dubnov (UC San Diego); Julian McAuley (University of California, San Diego); Taylor Berg-
Kirkpatrick (UCSD)

408: Multi-Dimensional and Multi-Scale Modeling for Speech Separation Optimized by

Discriminative Learning
Zhaoxi Mu (Xi'an Jiaotong University)*; Xinyu Yang (Xi'an Jiaotong University); WenJing Zhu (DXM)

447: MAID: A Conditional Diffusion Model For Long Music Audio Inpainting
Kaiyang Liu (Sichuan university)*; Wendong Gan (Wiz Holdings Pte Ltd); Chenchen Yuan (Sichuan
university)

455: Phonation Mode Detection in Singing: a Singer Adapted Model

Yixin Wang (Xi'an Jiaotong University; National University of Singapore); Wei Wei (National University of
Singapore); Ye Wang (National University of Singapore)*

572: Deep Self-Supervised Hierarchical Metrical Structure Modeling

Junyan Jiang (NYU Shanghai)*; Gus Xia (New York University Shanghai)

25
647: Diverse and Vivid Sound Generation from Text Descriptions
Guangwei Li (Shanghai Jiao Tong University)*; Xuenan Xu (Shanghai Jiao Tong University); Lingfeng Dai
(Shanghai Jiao Tong University); Mengyue Wu (Shanghai Jiao Tong University); Kai Yu (Shanghai Jiao
Tong University)

659: Towards Controllable Audio Texture Morphing

Chitralekha Gupta (National University of Singapore)*; Purnima Kamath (National University of
Singapore); Yize Wei (National University of Singapore); Zhuoyao Li (National University of Singapore);
Suranga Nanayakkara (National University of Singapore); Lonce Wyse (National University of Singapore)

662: A NOVEL METRIC FOR EVALUATING AUDIO CAPTION SIMILARITY

Swapnil P Bhosale (TCS Research and Innovation); Rupayan Chakraborty (TCS Research); Sunil Kumar
Kopparapu (TCS Research)*

729: An Attention-based Approach to Hierarchical Multi-label Music Instrument Classification

Zhi Zhong (Sony Group Corporation)*; Masato Hirano (Sony Group Corporation); Kazuki Shimada
(SONY); Kazuya Tateishi (Sony Group Corporation); Shusuke Takahashi (Sony Group Corporation); Yuki
Mitsufuji (Sony Group Corporation)

784: I SEE WHAT YOU HEAR: A VISION-INSPIRED METHOD TO LOCALIZE WORDS

Mohammad Samragh (Apple)*; Arnav Kundu (Apple); Ting-Yao Hu (Carnegie Mellon University); Aman
Chadha (Stanford University/Amazon Inc.); Ashish Shrivastava (Apple); Minsik Cho (Apple ); Oncel Tuzel
(Apple); Devang Naik (Apple)

834: BTS-E: Audio Deepfake Detection using Breathing-Talking-Silence Encoder

Thien-Phuc Doan (Soongsil university)*; Long Nguyen-Vu (Soongsil university); Souhwan Jung (Soongsil
university); Kihun Hong (Soongsil university)

897: Breaking the trade-off in personalized speech enhancement with cross-task knowledge
distillation
Hassan Taherian (The Ohio State Universtiy)*; Sefik Emre Eskimez (Microsoft); Takuya Yoshioka
(Microsoft)

922: Subspace Hybrid Beamforming for Head-worn Microphone Arrays

Sina Hafezi (Imperial College London)*; Alastair H Moore (Imperial College London); Pierre Guiraud
(Imperial College London); Patrick A. Naylor (Imperial College London); Jacob Donley (Facebook);
Vladimir Tourbabin (Meta); Thomas Lunner (Meta)

927: SYNTHESIZER PRESET INTERPOLATION USING TRANSFORMER AUTO-ENCODERS

Gwendal Le Vaillant (University of Mons / IRISIB (HE2B-ISIB))*; Thierry Dutoit (University of Mons)

969: Long-term Synchronization of Wireless Acoustic Sensor Networks with Nonpersistent

Acoustic Activity using Coherence State
Aleksej Chinaev (Carl-von-Ossietzky University of Oldenburg)*; Niklas Knaepper (Carl-von-Ossietzky
University of Oldenburg); Gerald Enzner (Carl von Ossietzky University Oldenburg)

977: DiffRoll: Diffusion-based Generative Music Transcription with Unsupervised Pretraining

Capability
Kin Wai Cheuk (Singapore University of Technology and Design)*; ryosuke sawata (Sony); Toshimitsu
Uesaka (Sony Group Corporation); Naoki Murata (Sony Group Corporation); Naoya Takahashi (Sony
Group); Shusuke Takahashi (Sony Group Corporation); Dorien Herremans (Singapore University of
Technology and Design); Yuki Mitsufuji (Sony Group Corporation)

984: Improving Weakly Supervised Sound Event Detection with Causal Intervention
Yifei Xin (Peking University)*; Dongchao Yang (Peking university); fan cui (xiaomi); Yujun Wang (xiaomi);
Yuexian Zou (Peking University)

26
1035: End-to-End Amp Modelling: From Data to Controllable Guitar Amplifier Models
Lauri Juvela (Aalto University)*; Eero-Pekka Damskägg (Neural DSP); Aleksi Peussa (Neural DSP);
Jaakko Mäkinen (Neural DSP); Thomas Sherson (Neural DSP); Stylianos I Mimilakis (Neural DSP);
Kimmo Rauhanen (Neural DSP); Athanasios Gotsopoulos (Neural DSP)

1066: Graph neural networks for sound source localization on distributed microphone networks
Eric Grinstein (Imperial College London)*; Mike Brookes (Imperial College London); Patrick A. Naylor
(Imperial College London)

1117: Audio Coding With Unified Noise Shaping And Phase Contrast Control
Byeongho Jo (Electronics and Telecommunications Research Institute)*; Seung-Kwon Beack (IEEE
Broadcast Technology Society (BTS)); Taejin Lee (ETRI)

1207: Frame-Level Multi-Label Playing Technique Detection Using Multi-Scale Network and Self-
Attention Mechanism
Dichucheng Li (Fudan University)*; Mingjin Che (Sichuan Conservatory of Music); Wen wu Meng
(Sichuan Conservatory of Music); Yulun Wu (Fudan University); Yi Yu (NII); Fan Xia (Sichuan
Conservatory of Music ); Wei Li (Fudan University)

1222: Simple Pooling Front-ends for Efficient Audio Classification

Xubo Liu (University of Surrey)*; Haohe Liu (University of Surrey); Qiuqiang Kong (Byte Dance); Xinhao
Mei (University of Surrey); Mark D. Plumbley (University of Surrey); Wenwu Wang (University of Surrey)

1231: ANALYSIS AND RE-SYNTHESIS OF NATURAL CRICKET SOUNDS ASSESSING THE

PERCEPTUAL RELEVANCE OF IDIOSYNCRATIC PARAMETERS
Aníbal JS Ferreira (University of Porto - Faculty of Engineering)*; Marco Oliveira (University of Porto -
Faculty of Engineering); João Silva (University of Porto - Faculty of Engineering); Vitor Almeida
(University of Porto - Faculty of Engineering)

1325: SEMI-SUPERVISED SOUND EVENT DETECTION WITH PRE-TRAINED MODEL

Liang Xu (Beijing Institute of Technology)*; Lizhong Wang (Samsung); Sijun Bi (Beijing Institute of
Technology); Hanyue Liu (Beijing Institute of Technology); Jing Wang (Beijing Institute of Technology)

1329: Design Choices for Learning Embeddings from Auxiliary Tasks for Domain Generalization in
Anomalous Sound Detection
Kevin Wilkinghoff (Fraunhofer FKIE)*

1350: Visual onoma-to-wave: environmental sound synthesis from visual onomatopoeias and
sound-source images
Hien Ohnaka (National Institute of Technology, Tokuyama College)*; Shinnosuke Takamichi (The
University of Tokyo); Keisuke Imoto (Doshisha University); Yuki Okamoto (Ritsumeikan University);
Kazuki Fujii (The University of Tokyo); Hiroshi Saruwatari (The University of Tokyo)

1359: Noise PSD Insensitive RTF Estimation in a Reverberant and Noisy Environment
Changheng Li (Delft University of Technology)*; Richard Hendriks (TU Delft)

1367: UX-Net: Filter-and-Process-based Improved U-Net for Real-time Time-domain Audio

Separation
Kashyap Patel (The University of Texas at Dallas)*; Anton Kovalyov (Electrical and Computer
Engineering, University of Texas at Dallas, Richardson, TX, USA); Issa Panahi (UTD)

1368: SARdBScene: Dataset and ResNet Baseline for Audio Scene Source Counting and Analysis
Michael Nigro (Toronto Metropolitan University)*; Sri Krishnan (Ryerson University)

27
1393: A FREQUENCY-DOMAIN RECURSIVE LEAST-SQUARES ADAPTIVE FILTERING ALGORITHM
BASED ON A KRONECKER PRODUCT DECOMPOSITION
Hongsen He (Southwest University of Science and Technology)*; Jingdong Chen (Northwestern
Polytechnical University); Jacob Benesty (INRS); Yi Yu (Southwest University of Science and Technology)

1415: Neural Band-to-Piano Score Arrangement with Stepless Difficulty Control

Moyu Terao (Kyoto University)*; Eita Nakamura (Kyoto University); Kazuyoshi Yoshii (Kyoto University)

1468: TransAudio: Towards the Transferable Adversarial Audio Attack via Learning Contextualized
Perturbations
Gege Qi (Alibaba)*; Yuefeng Chen (Alibaba Group); Yao Zhu (Zhejiang University); Binyuan Hui (Alibaba
Group); Xiaodan Li (Alibaba Group); Xiaofeng Mao (Alibaba Group); rong zhang (Alibaba); hui xue
(Alibaba)

1493: NORD: Non-Matching Reference Based Relative Depth Estimation From Binaural Audio
Pranay Manocha (Princeton University)*; Israel D Gebru (Facebook); Anurag Kumar (Facebook
Research); Dejan Markovic (Facebook Reality Labs); Alexander Richard (Facebook Reality Labs)

1501: Multi-resolution Location-based training for multi-channel continuous speech separation

Hassan Taherian (The Ohio State Universtiy)*; DeLiang Wang (Ohio State University)

1509: Weight-sharing Supernet for Searching Specialized Acoustic Event Classification Networks
Across Device Constraints
Guan-Ting Lin (National Taiwan University)*; Qingming Tang (Amazon, Alexa); Chieh-Chi Kao (Amazon);
Viktor Rozgic (Amazon Alexa); Chao Wang (Amazon)

1513: EFFECT OF ACOUSTIC UNIT GRANULARITY ON SEQ2SEQ REPRESENTATION LEARNING

Ali Elkahky (Meta, Inc)*; Wei-Ning Hsu (Meta, Inc); Paden P Tomasello (Meta); Tu Anh Nguyen (Meta,
Inc); Robin Algayres (Inria, Paris, France); Yossi Adi (Facebook AI Research ); Jade Copet (Meta, Inc);
Emmanuel Dupoux (Meta, Inc); Abdelrahman Mohamed (Meta, Inc)

1516: Spherical vector quantization for spatial direction coding

Stéphane Ragot (Orange)*; Adriana Vasilache (Nokia Technologies)

1578: RANDMASKING AUGMENT: A SIMPLE AND RANDOMIZED DATA AUGMENTATION FOR

ACOUSTIC SCENE CLASSIFICATION
JuBum Han (Samsung Research)*; Mateusz Matuszewski (Samsung R&D Institute Poland); Olaf Sikorski
(Samsung R&D Poland); Hosang Sung (Samsung Research); Hoonyoung Cho (Samsung Research)

1587: Real-time speech enhancement with dynamic attention span

Chengyu Zheng (Communication University of China); Yuan Zhou (Microsoft Research Asia)*; Xiulian
Peng (Microsoft Research Asia); Yuan Zhang (Communication University of China); Yan Lu (Microsoft
Research Asia)

1606: CONTRAST-PLC: CONTRASTIVE LEARNING FOR PACKET LOSS CONCEALMENT

Huaying Xue (Microsoft)*; Xiulian Peng (Microsoft Research Asia); Yan Lu (Microsoft Research Asia)

1610: Efficient Large-scale Audio Tagging via Transformer-to-CNN Knowledge Distillation

Florian Schmid (Johannes Kepler University)*; Khaled Koutini (Johannes Kepler University); Gerhard
Widmer (Johannes Kepler University)

1620: Global HRTF Interpolation via Learned Affine Transformation of Hyper-conditioned Features
Jin Woo Lee (Seoul National University)*; Sungho Lee (Seoul National University); Kyogu Lee (Seoul
National University)

28
1663: Masked Spectrogram Prediction for Self-supervised Audio Pre-training
DaDing Chong (Peking university); Helin Wang (Johns Hopkins University)*; Peilin Zhou (The Hong Kong
University of Science and Technology); Qingcheng Zeng (Northwestern University)

1720: Linear Microphone Array Parallel to the Driving Direction for In-Car Speech Enhancement
Masanori Tsujikawa (NEC Corporation); Akihiko K. Sugiyama (Yahoo Japan Corporation)*; Ken
Hanazawa (NEC Laboratories America, Inc.); Yoshinobu Kajikawa (Kansai University)

1754: SPEECH DEREVERBERATION WITH A REVERBERATION TIME SHORTENING TARGET

Rui Zhou (Westlake University)*; Wenye Zhu (Zhejiang University); Xiaofei Li (Westlake University)

1755: SPATIALLY INFORMED INDEPENDENT VECTOR ANALYSIS FOR SOURCE EXTRACTION

BASED ON THE CONVOLUTIVE TRANSFER FUNCTION MODEL
Xianrui Wang (Northwestern Polytechnical University); Andreas Brendel ( Friedrich-Alexander-
University Erlangen-Nürnberg); Gongping Huang (University of Erlangen-Nuremberg); Yichen Yang (
Northwestern Polytechnical University); Walter Kellermann (Friedrich-Alexander-University
Erlangen-Nürnberg); Jingdong Chen (Northwestern Polytechnical University)*

1768: UPGLADE: Unplugged Plug-and-Play audio declipper based on consensus equilibrium of

DNN and sparse optimization
Tomoro Tanaka (Waseda University)*; Kohei Yatabe (Tokyo University of Agriculture and Technology);
Yasuhiro Oikawa (Waseda University)

1773: MASKED MODELING DUO: LEARNING REPRESENTATIONS BY ENCOURAGING BOTH

NETWORKS TO MODEL THE INPUT
Daisuke Niizumi (NTT Corporation)*; Daiki Takeuchi (NTT Corporation); Yasunori Ohishi (NTT
Corporation); Noboru Harada (NTT); Kunio Kashino (NTT Communication Science Laboratories)

1785: Robust FIR Filters for Wireless Low-frequency Sound Zones

Mo Zhou (Aalborg University)*; Martin Bo Møller (Bang & Olufsen); Christian Sejer Pedersen (Aalborg
University); Jan Ostergaard (Aalborg University)

1825: HybridFormer: Improving SqueezeFormer with Hybrid Attention and NSR Mechanism
Yuguang Yang (Ximalaya Inc., ShangHai, China)*; Yu Pan (University of Alberta); Jingjing Yin (Ximalaya);
jiangyu Han (Ximalaya ); Lei Ma (University of Alberta); heng lu (Ximalaya Inc., ShangHai, China )

1851: Can Knowledge of End-to-End Text-to-Speech Models Improve Neural MIDI-to-Audio

Synthesis Systems?
Xuan Shi (University of Southern California)*; Erica Cooper (); Xin Wang (National Institute of
Informatics); Junichi Yamagishi (National Institute of Informatics); Shrikanth Narayanan (USC)

1860: Spatial active noise control method based on sound field interpolation from reference
microphone signals
Kazuyuki Arikawa (The University of Tokyo)*; Shoichi Koyama (The University of Tokyo); Hiroshi
Saruwatari (The University of Tokyo)

1884: Kernel interpolation of acoustic transfer functions with adaptive kernel for directed and
residual reverberations
Juliano G. C. Ribeiro (The University of Tokyo)*; Shoichi Koyama (The University of Tokyo); Hiroshi
Saruwatari (The University of Tokyo)

1953: Improving Speech Enhancement via Event-based Query

Yifei Xin (Peking University)*; Xiulian Peng (Microsoft Research Asia); Yan Lu (Microsoft Research Asia)

29
1958: Better Together: Dialogue Separation and Voice Activity Detection for Audio Personalization
in TV
Matteo Torcoli (International Audio Laboratories Erlangen)*; Emanuel Habets (AudioLabs Erlangen)

2001: Audio-Text Models Do Not Yet Leverage Natural Language

Ho-Hsiang Wu (New York University)*; Oriol Nieto (Pandora); Juan P Bello (New York University); Justin
Salamon (Adobe Research)

2008: On the importance of different cough phases for COVID-19 detection

Yi Zhu (Institut national de la recherche scientifique (INRS))*; Mahil Shaik (Indian Institute of Technology
Kharagpur); Tiago Falk (Institut national de la recherche scientifique (INRS))

2027: GCT: GATED CONTEXTUAL TRANSFORMER FOR SEQUENTIAL AUDIO TAGGING

Yuanbo Hou (Ghent University)*; Yun Wang (Meta); Wenwu Wang (University of Surrey); Dick
Botteldooren (Ghent University)

2089: SPEECH EMOTION RECOGNITION VIA HETEROGENEOUS FEATURE LEARNING

Ke Liu (Northwest University)*; Dongya Wu (Northwest University); Dekui Wang (Northwest University);
Jun Feng (Northwest University)

2110: SWITCHING KRONECKER PRODUCT LINEAR FILTERING FOR MULTISPEAKER ADAPTIVE

SPEECH DEREVERBERATION
Gongping Huang (University of Erlangen-Nuremberg)*; Jacob Benesty (INRS); Israel Cohen (Technion);
Emil Winebrand (Insoundz Ltd.); Jingdong Chen (Northwestern Polytechnical University); Walter
Kellermann (Friedrich-Alexander-University Erlangen-Nürnberg)

2121: Improving performance of real-time full-band blind packet-loss concealment with predictive
network
Nguyen Viet Anh (NamiTech JSC)*; Anh Nguyen (NamiTech JSC); Andy W H Khong (Nanyang
Technological University)

2148: INTER-PULSE ESTIMATION FOR SPERM WHALE CLICK DETECTION

Guy Gubnitsky (University of Haifa)*; Roee Diamant (University of Haifa)

2200: TAPE: An End-to-End Timbre-Aware Pitch Estimator

Nazif Can Tamer (Universitat Pompeu Fabra)*; Yigitcan Özer (International Audio Laboratories Erlangen);
Meinard Müller (International Audio Laboratories Erlangen); Xavier Serra (Universitat Pompeu Fabra)

2232: RAT: Radial Attention Transformer for Singing Technique Recognition

Guan-Yuan Chen (National Tsing Hua University)*; Ya-Fen Yeh (National Tsing Hua University); Von-Wun
Soo (nthu)

2247: Heterogeneous Graph Learning for Acoustic Event Classification

Amir Shirian (University of Warwick)*; Mona Ahmadian (University of Surrey); Krishna Somandepalli
(University of Southern California); Tanaya Guha (University of Glasgow)

2248: EPIC-SOUNDS : A LARGE-SCALE DATASET OF ACTIONS THAT SOUND

Jaesung Huh (University of Oxford)*; Jacob Chalk (University of Bristol); Evangelos Kazakos (Dept. of
Computer Science and Engineering - University of Ioannina); Dima Damen (University of Bristol); Andrew
Zisserman (University of Oxford)

2264: Unsupervised vocal dereverberation with diffusion-based generative models

Koichi Saito (Sony Gruop Corporation)*; Naoki Murata (Sony Group Corporation); Toshimitsu Uesaka
(Sony Group Corporation); Chieh-Hsin Lai (Sony Group Corporation); Yuhta Takida (Sony Group
Corporation); Takao Fukui (Sony Group Corporation); Yuki Mitsufuji (Sony Group Corporation)

30
2305: ICCRN: INPLACE CEPSTRAL CONVOLUTIONAL RECURRENT NEURAL NETWORK FOR
MONAURAL SPEECH ENHANCEMENT
Jinjiang Liu (College of Computer Science, Inner Mongolia University)*; Xueliang zhang (Inner Mongolia
University)

2350: A LIGHTWEIGHT FOURIER CONVOLUTIONAL ATTENTION ENCODER FOR MULTI-CHANNEL

SPEECH ENHANCEMENT
Siyu Sun (Wuhan University); Jian Jin (RTC Lab, ByteDance); Zhe Han (RTC Lab, ByteDance); Xianjun
Xia (RTC Lab, ByteDance)*; Li Chen (ByteDance); Yijian Xiao (RTC Lab, ByteDance); Piao Ding (RTC
Lab, ByteDance); Shenyi Song (RTC Engineering, ByteDance); Roberto Togneri (The University of
Western Australian); Haijian Zhang (Wuhan University)

2356: Generalized Relative Harmonic Coefficients

Yonggang Hu (Australian National University)*; Sharon Gannot (Bar-Ilan University ); thushara
abhayapala (The Australian National University)

2362: Self-Transriber: Few-shot Lyrics Transcription with Self-training

Xiaoxue Gao (National University of Singapore)*; Xianghu Yue (National University of Singapore );
Haizhou Li (The Chinese University of Hong Kong, Shenzhen)

2376: Speaker Diaphragm Excursion Prediction: deep attention and online adaptation
Yuwei Ren (Qualcomm AI Research, QUALCOMM Wireless Communication Technologies (China)
Limited)*; Matt Zivney (Qualcomm AI Research, Qualcomm Technologies, Inc.); Yin Huang (Qualcomm);
Eddie Choy (Qualcomm AI Research, Qualcomm Technologies, Inc.); Chirag Patel (Qualcomm); Hao Xu
(Qualcomm AI Research, Qualcomm Technologies, Inc.)

2387: TT-NET: DUAL-PATH TRANSFORMER BASED SOUND FIELD TRANSLATION IN THE

SPHERICAL HARMONIC DOMAIN
Yiwen Wang (Peking University); Zijian Lan (Peking University); Xihong Wu (Peking University); Tianshu
Qu (Peking University)*

2393: A DNN-based hearing-aid strategy for real-time processing: One size fits all
Fotios Drakopoulos (Ghent University)*; Arthur Van Den Broucke (Ghent University); Sarah Verhulst
(Ghent University)

2454: Fast Low-latency Convolution by Low-rank Tensor Approximation

Martin Jälmby (KU Leuven)*; Filip Elvander (Aalto University); Toon van Waterschoot (Department of
Electrical Engineering (ESAT-STADIUS/ETC))

2514: Fast Online Source Steering Algorithm for Tracking Single Moving Source Using Online
Independent Vector Analysis
Taishi Nakashima (Tokyo Metropolitan University)*; Rintaro Ikeshita (NTT); Nobutaka Ono (Tokyo
Metropolitan University); Shoko Araki (NTT Corporation); Tomohiro Nakatani (NTT Communication
Science Laboratories)

2572: Hyperbolic Audio Source Separation

Darius Petermann (Indiana University - Bloomington)*; Gordon Wichern (Mitsubishi Electric Research
Laboratories (MERL)); Aswin Shanmugam Subramanian (Mitsubishi Electric Research Laboratories
(MERL)); Jonathan LeRoux (Mitsubishi Electric Research Laboratories (MERL))

2620: SPARSE AND STRUCTURED MODELLING OF UNDERWATER ACOUSTIC CHANNEL

IMPULSE RESPONSES
Chaoran Yang (Harbin Engineering University); Qing Ling (Harbin Engineering University); Xueli Sheng
(Harbin Engineering University)*; Mengfei Mu (Harbin Engineering University); Andreas Jakobsson (Lund
University)

31
2656: SCA: STREAMING CROSS-ATTENTION ALIGNMENT FOR ECHO CANCELLATION
Yang Liu (Meta)*; Yangyang Shi (Facebook); Yun Li (Meta); Kaustubh Kalgaonkar (Meta); Sriram
Srinivasan (Meta); Xin Lei (Meta)

2743: EVALUATING VARIANTS OF WAV2VEC 2.0 ON AFFECTIVE VOCAL BURST TASKS

Bagus Tris Atmaja (Sepuluh Nopember Institute of Technology)*; Akira Sasou (AIST)

2751: NEURAL OPTIMIZATION OF GEOMETRY AND FIXED BEAMFORMER FOR LINEAR

MICROPHONE ARRAYS
Longfei Yan (Victoria University of Wellington)*; Weilong Huang (Alibaba Group); W. Bastiaan Kleijn
(Victoria University of Wellington); thushara abhayapala (The Australian National University)

2866: Zero-shot Sound Event Classification Using a Sound Attribute Vector with Global and Local
Feature Learning
Yi-Han Lin (Kobe University)*; Xunquan Chen (Kobe University); Ryoichi Takashima (Kobe University);
Tetsuya Takiguchi (Kobe University)

2877: Speech Enhancement with Intelligent Neural Homomorphic Synthesis

Shulin He (College of Computer Science, Inner Mongolia University)*; Wei Rao (Tencent); Jinjiang Liu
(College of Computer Science, Inner Mongolia University); Jun Chen (Tencent); Yukai Ju (Tencent);
Xueliang zhang (Inner Mongolia University); Yannan Wang (Tencent); Shi-dong Shang (tencent)

2881: DEEPSPACE: DYNAMIC SPATIAL AND SOURCE CUE BASED SOURCE SEPARATION FOR
DIALOG ENHANCEMENT
Aaron S Master (Dolby Laboratories, Inc)*; Lie Lu (Dolby Laboratories); Jonas Samuelsson (Dolby
Laboratories, Inc); Heidi-Maria Lehtonen (Dolby Sweden AB); Scott Norcross (Dolby Laboratories, Inc);
Nathan Swedlow (Dolby Laboratories, Inc); Audrey Howard (Dolby Laboratories, Inc)

2895: AST-SED: an Effective Sound Event Detection Method Based on Audio Spectrogram
Transformer
Kang Li (University of Science and Technology of China,National Engineering Research Center of
Speech and Language Information Processing.); Yan Song (USTC)*; Lirong Dai (University of Science
and Technology of China); Ian McLoughlin (Singapore Institute of Technology); Xin Fang (iFlytek
Research); Lin Liu (iFlytek Research)

2920: Deep Generative Fixed-filter Active Noise Control

Zhengding Luo (Nanyang Technological University)*; Dongyuan Shi (Nanyang Technological University);
Xiaoyi Shen (Nanyang Technological University); Junwei Ji (Nanyang Technological University); Woon
Seng Gan (NTU )

2956: A practical distributed active noise control algorithm overcoming communication

restrictions
Junwei Ji (Nanyang Technological University)*; Dongyuan Shi (Nanyang Technological University);
Zhengding Luo (Nanyang Technological University); Xiaoyi Shen (Nanyang Technological University);
Woon Seng Gan (NTU )

2988: Ensemble of Deep Neural Network Models for MOS Prediction

Marie Kunešová (University of West Bohemia)*; Jindrich Matousek (University of West Bohemia, Pilsen,
Czech Republic); Jan Lehečka (University of West Bohemia); Jan Svec (University of West Bohemia);
Josef Michalek (University of West Bohemia); Daniel Tihelka (University of West Bohemia); Martin Bulin
(University of West Bohemia); Zdenek Hanzlicek (University of West Bohemia); Marketa Rezackova
(University of West Bohemia)

32
3007: Ripple Sparse Self-Attention For Monaural Speech Enhancement
Qiquan Zhang (The University of New South Wales); Hongxu Zhu (Department of Electrical and
Computer Engineering, National University of Singapore); Qi Song (Alibaba)*; Xinyua Qian (Department
of Electrical and Computer Engineering, National University of Singapore); Zhaoheng Ni (Meta AI);
Haizhou Li (The Chinese University of Hong Kong, Shenzhen)

3074: SPECTRO-TEMPORAL POST-FILTERING VIA SHORT-TIME TARGET CANCELLATION FOR

DIRECTIONAL SPEECH ENHANCEMENT IN A DUAL-MICROPHONE HEARING AID
Marcos A Cantu (Carl von Ossietzky University of Oldenburg)*; Volker Hohmann (Carl von Ossietzky
University of Oldenburg)

3088: Improving Text-Audio Retrieval by Text-aware Attention Pooling and Prior Matrix Revised
Loss
Yifei Xin (Peking University)*; Dongchao Yang (Peking university); Yuexian Zou (Peking University)

3196: Optimal Transport in Diffusion Modeling for Conversion Tasks in Audio Domain
Vadim Popov (Huawei Noah's Ark Lab); Amantur Amatov (Huawei); Mikhail Kudinov (Huawei Noah's Ark
Lab); Vladimir Gogoryan (Huawei Noah's Ark Lab)*; Tasnima Sadekova (Huawei Noah's Ark Lab); Ivan
Vovk (Huawei Noah's Ark Lab)

3307: DATASET BALANCING CAN HURT MODEL PERFORMANCE

Richard C Moore (Google Research)*; Dan Ellis (Google, Inc); Eduardo Fonseca (Google Research);
Shawn Hershey (Google); Aren Jansen (Google); Manoj Plakal (Google, Inc.)

3356: TRANSFORMER-BASED BIOACOUSTIC SOUND EVENT DETECTION ON FEW-SHOT

LEARNING TASKS
Liwen You (Amazon)*; Erika Pelaez Coyotl (Amazon); Suren Gunturu (Amazon); Maarten Van Segbroeck
(Amazon)

3383: BEANS: The Benchmark of Animal Sounds

Masato Hagiwara (Earth Species Project)*; Benjamin Hoffman (Earth Species Project); Jen-Yu Liu (Earth
Species Project); Maddie Cusimano (Earth Species Project); Felix Effenberger (Earth Species Project);
Katie Zacarian (Earth Species Project)

3421: Efficient similarity-based passive filter pruning for compressing CNNs

Arshdeep Singh (University of Surrey)*; Mark D. Plumbley (University of Surrey)

3426: Blind source counting and separation with relative harmonic coefficients
Huiyuan Sun (The Australian National University)*; Prasanga Samarasinghe (Australian National
University); thushara abhayapala (The Australian National University)

3434: U-BEAT: A MULTI-SCALE BEAT TRACKING MODEL BASED ON WAVE-U-NET

Tian Cheng (National Institute of Advanced Industrial Science and Technology (AIST))*; Masataka Goto
(National Institute of Advanced Industrial Science and Technology (AIST))

3513: The R3VIVAL dataset: Repository of room responses and 360 videos of a variable acoustics
room
Florian Klein (TU Ilmenau); Sebastia V. Amengual Garí (Reality Labs Research, Meta)*

3527: COVID-19 Detection from Speech in Noisy Conditions

Shuo Liu (University of Augsburg)*; Adria Mallol-Ragolta (University of Augsburg); Björn Schuller
(University of Augsburg)

3549: SingNet: A Real-time Singing Voice Beat and Downbeat Tracking System
Mojtaba Heydari (University of Rochester)*; Ju-Chiang Wang (TikTok); Zhiyao Duan (Unversity of
Rochester)

33
3595: Active Noise control over 3D space: A realistic error microphone geometry design
Huiyuan Sun (The Australian National University)*; Prasanga Samarasinghe (Australian National
University); thushara abhayapala (The Australian National University)

3610: AVES: Animal Vocalization Encoder based on Self-Supervision

Masato Hagiwara (Earth Species Project)*

3674: Joint Generative-Contrastive Representation Learning for Anomalous Sound Detection

Xiaomin Zeng (University of Science and Technology of China); Yan Song (USTC)*; ZHU ZHUO
(alibaba); Yu Zhou (alibaba); Yuhong Li (Alibaba); hui xue (Alibaba); Lirong Dai (University of Science and
Technology of China); Ian McLoughlin (Singapore Institute of Technology)

3676: TG-Critic: A Timbre-Guided Model for Reference-Independent Singing Evaluation

Xiaoheng Sun (NetEase Cloud Music); Yuejie Gao (Hangzhou Netease cloud Music Technology Co., Ltd);
Hanyao Lin (Fudan University); Huaping Liu ( Hangzhou Netease cloud Music Technology Co., Ltd)*

3680: Self-supervised learning of audio representations using angular contrastive loss

Shanshan Wang (Tampere University)*; Soumya Tripathy (Tampere University of Technology); Annamaria
Mesaros (Tampere University)

3700: REAL-TIME TARGET SOUND EXTRACTION

Bandhav Veluri (University of Washington)*; Justin Chan (University of Washington); Malek Itani
(University of Washington); Tuochao Chen (University of Washington); Takuya Yoshioka (Microsoft);
Shyamnath Gollakota (University of Washington)

3718: LEARNING TO AUTO-CORRECT FOR HIGH-QUALITY SPECTROGRAMS

Zhiyang Zhou (Beijing Bombax XiaoIce Technology Co., Ltd)*; Shihui Liu (Beijing Bombax XiaoIce
Technology Co., Ltd)

3726: Improving phase-vocoder-based time stretching by time-directional spectrogram squeezing

Natsuki Akaishi (Waseda University)*; Kohei Yatabe (Tokyo University of Agriculture and Technology);
Yasuhiro Oikawa (Waseda University)

3765: A study of audio mixing methods for piano transcription in violin-piano ensembles
Hyemi Kim (KAIST / ETRI)*; Jiyun Park (KAIST); Taegyun Kwon (KAIST); Dasaem Jeong (Sogang
University); Juhan Nam (KAIST)

3819: Show Me the Instruments: Musical Instrument Retrieval from Mixture Audio
Kyungsu Kim (Seoul National University)*; Minju Park (Seoul National University); Haesun Joung (Seoul
National University); Yunkee Chae (Seoul National University); Yeongbeom Hong (Seoul National
University); Seonghyeon Go (Seoul National University); Kyogu Lee (Seoul National University)

3894: REAL-TIME MULTICHANNEL SPEECH SEPARATION AND ENHANCEMENT USING A

BEAMSPACE-DOMAIN-BASED LIGHTWEIGHT CNN
Marco Olivieri (Politecnico di Milano)*; Luca Comanducci (Politecnico di Milano); Mirco Pezzoli
(Politecnicno di Milano); Davide Balsarri (BdSound); Luca Menescardi (BdSound); Michele Buccoli
(BdSound S.r.l.); Simone Pecorino (BdSound); Antonio Grosso (BdSound); Fabio Antonacci (Politecnico
di Milano); Augusto Sarti (Politecnico di Milano)

3898: GRAD-CAM-INSPIRED INTERPRETATION OF NEARFIELD ACOUSTIC HOLOGRAPHY USING

PHYSICS-INFORMED EXPLAINABLE NEURAL NETWORK
Hagar Kafri (Bar Ilan University); Marco Olivieri (Politecnico di Milano)*; Fabio Antonacci (Politecnico di
Milano); Mordehay Moradi (Bar illan University); Augusto Sarti (Politecnico di Milano); Sharon Gannot
(Bar-Ilan University )

34
3908: GENERAL OR SPECIFIC? INVESTIGATING EFFECTIVE PRIVACY PROTECTION IN
FEDERATED LEARNING FOR SPEECH EMOTION RECOGNITION
Chao Tan (Kyoto University )*; Yang Cao (Hokkaido University); Sheng Li (National Institute of Information
& Communications Technology (NICT)); Masatoshi Yoshikawa (Kyoto University)

4002: Time-weighted Frequency Domain Audio Representation with GMM Estimator for
Anomalous Sound Detection
Jian Guan (Harbin Engineering University)*; Youde Liu ( Harbin Institute of Technology); Qiaoxi Zhu
(University of Technology Sydney); 铁然 郑 (哈尔滨工业大学 ); jiqing Han (Harbin Institute of Technology);
Wenwu Wang (University of Surrey)

4051: F0 ESTIMATION FROM TELEPHONE SPEECH USING DEEP FEATURE LOSS

Supritha M Shetty (Indian Institute of Information Technology, Dharwad)*; Shraddha Revankar (K L E
Technological University); Nalini Iyer ("KLETech, Hubballi"); Deepak T (IIIT-Dharwad)

4094: Training sound event detection with soft labels from crowdsourced annotations
Irene Martin (Tampere University)*; Manu Harju (Tampere University); Paul Ahokas (Tampere University);
Annamaria Mesaros (Tampere University)

4106: AN EXPERIMENTAL STUDY ON SOUND EVENT LOCALIZATION AND DETECTION UNDER

REALISTIC TESTING CONDITIONS
Shutong Niu (University of Science and Technology of China ); Jun Du (University of Science and
Technology of China)*; Qing Wang (University of Science and Technology of China); Li Chai (University of
Science and Technologoy of China); Huaxin Wu (iFlytek Research); Zhaoxu Nian (University of Science
and Technology of China); Lei Sun (University of Science and Technologoy of China); Yi Fang (iFlytek
Research); Jia Pan (University of Science and Technology of China); Chin-Hui Lee (Georgia Institute of
Technology)

4119: Attention Mixup: An Accurate Mixup Scheme based on Interpretable Attention Mechanism
for Multi-label Audio Classification
Wuyang Liu (School of Cyber Science and Engineering, Wuhan University)*; Yanzhen Ren (Computer
School of Wuhan University); Jingru Wang (School of Cyber Science and Engineering, Wuhan University)

4137: CONVOLUTIONAL RECURRENT NEURAL NETWORKS FOR THE CLASSIFICATION OF

CETACEAN BIOACOUSTIC PATTERNS
Dimitris Makropoulos (National Technical University of Athens)*; Antigoni Tsiami (National Technical
University of Athens); Aristides M Prospathopoulos (HCMR); DIMITRIS KASSIS (HCMR); Alexandros
Frantzis (Pelagos Cetacean Research Institute); Emmanuel Skarsoulis (Foundation of Research and
Technology - HELLAS); George Piperakis (Foundation of Research and Technology -HELLAS); Petros
Maragos (National Technical University of Athens)

4152: Frequency bin-wise single channel speech presence probability estimation using multiple
DNNs
Shuai Tao (Aalborg University)*; Himavanth Reddy Pundla (Aalborg University); Jesper Rindom Jensen
(Aallborg University); Mads G. Christensen (Audio Analysis Lab., AD:MT, Aalborg University, Denmark)

4192: Analysis of Noisy-target Training for DNN-based speech enhancement

Takuya Fujimura (Nagoya University)*; Tomoki Toda (Nagoya University)

4205: Dereverberation in Acoustic Sensor Networks using Weighted Prediction Error with
Microphone-dependent Prediction Delays
Anselm Lohmann (University of Oldenburg)*; Toon van Waterschoot (Department of Electrical
Engineering (ESAT-STADIUS/ETC)); Joerg Bitzer (Institute of Hearing Technology and Audiology, Jade
University of Applied Sciences, Oldenburg); Simon Doclo (University of Oldenburg)

35
4214: SPEAKERAUGMENT: DATA AUGMENTATION FOR GENERALIZABLE SOURCE SEPARATION
VIA SPEAKER PARAMETER MANIPULATION
Kai Wang (Xinjiang University); Yuhang Yang (School of Information Science and Engineering, Xinjiang
University, China); Hao Huang (Xinjiang University)*; Ying Hu (Xinjiang University); Sheng Li (National
Institute of Information & Communications Technology (NICT))

4215: SW-WaveNet: Learning Representation from Spectrogram and Wavegram Using WaveNet for
Anomalous Sound Detection
Haihui Chen (Huazhong University of Science and Technology)*; Likai Ran (Huazhong University of
Science and Technology); Xixia Sun (Nanjing University of Posts and Telecommunications); Chao Cai
(Huazhong University of Science and Technology)

4227: ROBUST BINAURAL SOUND LOCALISATION WITH TEMPORAL ATTENTION

Qi Hu (Institute of Acoustics of Chinese Academy of Sciences)*; Ning Ma (University of Sheffield); Guy J.
Brown (University of Sheffield)

4303: Geometry-aware DoA Estimation using a Deep Neural Network with mixed-data input
features
Ulrik Kowalk (Institute of Hearing Technology and Audiology, Jade University of Applied Sciences,
Oldenburg)*; Simon Doclo (University of Oldenburg); Joerg Bitzer (Institute of Hearing Technology and
Audiology, Jade University of Applied Sciences, Oldenburg)

4341: SUBBAND DEPENDENCY MODELING FOR SOUND EVENT DETECTION

Yadong Guan (Harbin Institute of Technology)*; 贵滨 郑 (哈尔滨工业大学计算机科学与技术学院); jiqing
Han (Harbin Institute of Technology); huanliang wang (Qdreamer)

4388: Faster Than Fast: Accelerating The Griffin-Lim Algorithm

Rossen Nenov (Austrian Academy of Sciences - Acoustics Research Institute)*; Dang-Khoa Nguyen
(University of Vienna); Peter Balazs (Acoustics Research Institute, Austrian Academy of Sciences)

4446: Adversarial Guitar Amplifier Modelling With Unpaired Data

Alec P Wright (Aalto University)*; Vesa Valimaki (Aalto University); Lauri Juvela (Aalto University)

4448: On Crowdsourcing-Design with Comparison Category Rating for Evaluating Speech

Enhancement algorithms
Angélica Stephania Zambrano Suárez (DTU)*; Clement Laroche (GN Audio); Line Clemmensen (DTU);
Sneha Das (Technical University of Denmark)

4461: CONTRASTIVE SPEECH MIXUP FOR LOW-RESOURCE KEYWORD SPOTTING

Dianwen Ng (Alibaba Group/Nanyang Technological University)*; Ruixi Zhang (National University of
Singapore); Jia Qi Yip (Alibaba Group); Chong Zhang (Alibaba Group); Yukun Ma (Alibaba Group); Trung
Hieu Nguyen (Alibaba Group); Chongjia Ni (Alibaba); Eng Siong Chng (Nanyang Technological
University); Bin Ma ("Alibaba, Singapore R&D Center")

4462: Low-Complexity Acoustic Echo Cancellation with Neural Kalman Filtering

Dong Yang (Tencent); Fei Jiang (Tencent)*; Wei Wu (Tencent); Xuefei Fang (Tencent); Muyong Cao
(Tencent)

4485: AN EFFECTIVE ANOMALOUS SOUND DETECTION METHOD BASED ON REPRESENTATION

LEARNING WITH SIMULATED ANOMALIES
Han Chen (University of Science and Technology of China); Yan Song (USTC)*; ZHU ZHUO (alibaba); Yu
Zhou (alibaba); Yuhong Li (Alibaba); hui xue (Alibaba); Ian McLoughlin (Singapore Institute of
Technology)

36
4516: Disentangling the Horowitz factor: Learning content and style from expressive piano
performance
Huan Zhang (Queen Mary University of London)*; Simon Dixon (Queen Mary University of London)

4540: Pre-training strategies using contrastive learning and playlist information for music
classification and similarity
Pablo Alonso-Jiménez (Universitat Pompeu Fabra)*; Xavier Favory (Utopia Music); Hadrien
Foroughmand (Utopia Music); Grigoris Bourdalas (Utopia Music); Xavier Serra (Universitat Pompeu
Fabra ); Thomas Lidy (Utopia Music); Dmitry Bogdanov (Universitat Pompeu Fabra)

4542: Assisted RTF-Vector-Based Binaural Direction of Arrival Estimation Exploiting a Calibrated

External Microphone Array
Daniel Fejgin (University of Oldenburg)*; Simon Doclo (University of Oldenburg)

4575: A Frequency-weighted Leaky FxLMS Algorithm with Application to Feedback Active Noise
Control Systems
Yu Tang (Southwest Jiaotong University)*; Hongwei Zhang (Harbin Institute of Tech. Shenzhen)

4577: SPEECH MODELING WITH A HIERARCHICAL TRANSFORMER DYNAMICAL VAE

Xiaoyu Lin (Inria Grenoble-Rhône-Alpes)*; Xiaoyu Bie (INRIA); Simon Leglaive (CentraleSupelec);
Laurent Girin (); Xavier Alameda-Pineda (INRIA)

4586: STUDY AND DESIGN OF ROBUST PERSONAL SOUND ZONES WITH VAST USING LOW
RANK RIRs
Sankha Subhra Bhattacharjee (Audio Analysis Lab, CREATE, Aalborg University)*; Liming Shi (CIE,
Chongqing University of Posts and Telecommunications); Guoli Ping (Acoustic Engineering Lab, Huawei
Technologies Co., Ltd); Xiaoxiang Shen (Acoustic Engineering Lab, Huawei Technologies Co., Ltd); Mads
G. Christensen (Audio Analysis Lab., AD:MT, Aalborg University, Denmark)

4589: Online Binaural Speech Separation of Moving Speakers With a Wavesplit Network
Cong Han (Columbia Univeristy)*; Nima Mesgarani (Columbia University)

4591: Target Sound Extraction with Variable Cross-modality Clues

Chenda Li (Shanghai Jiao Tong University)*; Yao Qian (Microsoft); Zhuo Chen (Microsoft); Dongmei
Wang (Microsoft); Takuya Yoshioka (Microsoft); Shujie Liu (Microsoft Research Asia); Yanmin Qian
(Shanghai Jiao Tong University); Michael Zeng (Microsoft)

4660: EFFICIENT INTELLIGIBILITY EVALUATION USING KEYWORD SPOTTING: A STUDY ON

AUDIO-VISUAL SPEECH ENHANCEMENT
Cassia Valentini (University of Edinburgh)*; Andrea L Aldana (Edinburgh University); Ondrej Klejch
(University of Edinburgh); Peter Bell (University of Edinburgh )

4670: Distributed Adaptive Norm Estimation for Blind System Identification in Wireless Sensor
Networks
Matthias Blochberger (KU Leuven)*; Filip Elvander (Aalto University); Randall Ali (KU Leuven); Jan
Ostergaard (Aalborg University); Jesper Jensen (Aalborg University); Marc Moonen (KU Leuven); Toon
van Waterschoot (Department of Electrical Engineering (ESAT-STADIUS/ETC))

4677: On the relevance of the differences between HRTF measurement setups for machine
learning
Johan Pauwels (Queen Mary University of London)*; Lorenzo Picinali (Imperial College London)

4685: Speech Intelligibility Classifiers from 550k Disordered Speech Samples

Subhashini Venugopalan (Google)*; Jimmy Tobin (Google); Samuel J. Yang (Google); Katie Seaver
(Google); Richard Cave (Google); Pan-Pan Jiang (Google); Neil Zeghidour (Google); Rus Heywood
(Google); Jordan Green (MGH Institute of Health Professions); Michael Brenner (Google/Harvard)

37
4702: HiSSNet: Sound Event Detection and Speaker Identification via Hierarchical Prototypical
Networks for Low-Resource Headphones
N Shashaank (Columbia University)*; Berker Banar (Queen Mary University of London); Mohammad Izadi
(BOSE); Jeremy Kemmerer (BOSE); Shuo Zhang (Bose); Chuan-Che Huang (BOSE)

4790: HRTF Field: Unifying Measured HRTF Magnitude Representation with Neural Fields
You Zhang (University of Rochester)*; Yuxiang Wang (university of rochester); Zhiyao Duan (Unversity of
Rochester)

4848: Acoustic source localization in the spherical harmonics domain exploiting low-rank
approximations
Maximo Cobos (Universitat de Valencia)*; Mirco Pezzoli (Politecnicno di Milano); Fabio Antonacci
(Politecnico di Milano); Augusto Sarti (Politecnico di Milano)

4886: SIMULTANEOUSLY LEARNING ROBUST AUDIO EMBEDDINGS AND BALANCED HASH

CODES FOR QUERY-BY-EXAMPLE
Anup Singh (Ghent University)*; Kris Demuynck (Ghent Universitty); Vipul Arora (IIT Kanpur)

4894: Optimal Condition Training for Target Source Separation

Efthymios Tzinis (University of Illinois at Urbana-Champaign)*; Gordon Wichern (Mitsubishi Electric
Research Laboratories (MERL)); Paris Smaragdis (University of Illinois at Urbana-Champaign); Jonathan
LeRoux (Mitsubishi Electric Research Laboratories (MERL))

4898: TORCHAUDIO-SQUIM: REFERENCE-LESS SPEECH QUALITY AND INTELLIGIBILITY

MEASURES IN TORCHAUDIO
Anurag Kumar (Facebook Reality Labs)*; Ke Tan (Meta Platforms, Inc.); Zhaoheng Ni (Meta); Pranay
Manocha (Princeton University); Xiaohui Zhang (Meta); Ethan Henderson (Meta Reality Labs Research);
Buye Xu (Meta Reality Labs Research )

4900: SPICE+: Evaluation of Automatic Audio Captioning Systems with Pre-trained Language
Models
Felix Gontier (INRIA)*; romain serizel (Université de Lorraine); Christophe Cerisara (CNRS)

4903: Neural-AFC: Learning-Based Step-Size Control for Adaptive Feedback Cancellation with
Closed-loop Model Training
Behrad Soleimani (Starkey Hearing Technologies)*; Henning Schepker (Starkey Hearing Technologies);
Majid Mirbagheri (Starkey Hearing Technologies)

4908: Contrastive Learning-based Audio to Lyrics Alignment for Multiple Languages

Simon Durand (Spotify)*; Daniel Stoller (Spotify); Sebastian Ewert (Spotify)

4930: Exploiting speaker embeddings for improved microphone clustering and speech separation
in ad-hoc microphone arrays
Stijn Kindt (UGent)*; Jenthe Thienpondt (IDLab, Ghent University); Nilesh Madhu (IDLab, Ghent
University - imec)

4936: Explainable Audio Classification of Playing Techniques with Layer-wise Relevance

Propagation
Changhong Wang (LS2N)*; Vincent Lostanlen (Cornell Lab of Ornithology); Mathieu Lagrange (LS2N)

4946: MASKED AUTOENCODERS ARE ARTICULATORY LEARNERS

Ahmed A Attia (University Of Maryland College Park)*; Carol Y Espy-Wilson (University of Maryland)

38
4976: LEARNING ENVIRONMENTAL STRUCTURE USING ACOUSTIC PROBES WITH A DEEP
NEURAL NETWORK
Toros ARIKAN (MIT)*; Amir Weiss (Massachusetts Institute of Technology); Hari Vishnu (NUS); Grant
Deane (UCSD); Andrew C Singer (University of Illinois); Gregory W Wornell (MIT)

4980: Speech MOS multi-task learning and rater bias correction

Haleh Akrami (Signal and Image Processing Institute at University of Southern California)*; Hannes
Gamper (Microsoft)

4981: IMPROVING AUDIO CAPTIONING USING SEMANTIC SIMILARITY METRICS

Rehana Mahfuz (Qualcomm)*; Yinyi Guo (Qualcomm); Erik Visser (Qualcomm)

5003: AERO: AUDIO SUPER RESOLUTION IN THE SPECTRAL DOMAIN

Moshe Mandel (Hebrew University of Jerusalem)*; Or Tal (Hebrew University of Jerusalem); Yossi Adi
(Bar-Ilan University)

5004: On the Reduction of Large-Scale Room Acoustic Models

Pavlos Stoikos (University of Thessaly); Olympia Axelou (University of Thessaly); George Floros
(University of Thessaly)*; Nestor Evmorfopoulos (University of Thessaly); George Stamoulis (University of
Thessaly)

5008: SpeechLMScore: Evaluating speech generation using speech language model

Soumi Maiti (CMU)*; Yifan Peng (Carnegie Mellon University); Takaaki Saeki (The University of Tokyo);
Shinji Watanabe (Carnegie Mellon University)

5041: Learning to Personalize Equalization for High-Fidelity Spatial Audio Reproduction

Arjun Gupta (Meta)*; Pablo Hoffmann (Meta); Sebastian Prepeliţă (Meta); Philip Robinson (Meta); Vamsi
Krishna Ithapu (Meta); David Alon (Met)

5056: Deep AHS: A Deep Learning Approach to Acoustic Howling Suppression

Hao Zhang (Tencent AI Lab)*; Meng Yu (Tencent); Dong Yu (Tencent AI Lab)

5071: SEMANTICAC: SEMANTICS-ASSISTED FRAMEWORK FOR AUDIO CLASSIFICATION

Yicheng Xiao (Tsinghua Shenzhen International Graduate School, Tsinghua University); Yue Ma
(Tsinghua University); SHUYAN LI (University of Cambridge); Hantao Zhou (Tsinghua Shenzhen
International Graduate School, Tsinghua University); Ran Liao (Tsinghua Shenzhen International
Graduate School, Tsinghua University); Xiu Li (Tsinghua University)*

5089: TF-GridNet: Making Time-Frequency Domain Models Great Again for Monaural Speaker
Separation
Zhong-Qiu Wang (Carnegie Mellon University)*; Samuele Cornell (Università Politecnica delle Marche);
Shukjae Choi (Hyundai Motor Company); Younglo Lee (42dot); Byeong-Yeol Kim (42dot); Shinji
Watanabe (Carnegie Mellon University)

5098: Does a quieter city mean fewer complaints? The Sounds of New York City During COVID-19
Lockdown
Mark Cartwright (New Jersey Institute of Technology)*; Magdalena Fuentes (New York University);
Charlie Mydlarz (New York University); Fabio Miranda (University of Illinois, USA); Juan P Bello (New
York University)

5112: Mouth Breathing Detection Using Audio Captured Through Earbuds

Tousif Ahmed (Samsung Research America, Inc.)*; Md Mahbubur Rahman (Samsung Research
America); Ebrahim Nemati (Samsung Research America); Jilong Kuang (Samsung Research America);
Jun Alex Gao (Samsung Research America)

39
5153: ESTIMATING ACOUSTIC DIRECTION OF ARRIVAL USING A SINGLE STRUCTURAL SENSOR
ON A RESONANT SURFACE
Tre DiPassio (University of Rochester)*; Michael Heilemann (University of Rochester); Benjamin`
Thompson (University of Rochester); Mark Bocko (University of Rochester)

5195: RAPID AUDIOMETRIC EVALUATION FOR PERSONALIZED HEADPHONE LISTENING

Matthew J. Goupell (University of Maryland - College Park)*; Marjan Davoodian (University of Maryland -
College Park); Sarah Weinstein (University of Maryland - College Park); David Gadzinski (Visisonics
Corporation); Dmitry Zotkin (Visisonics); Kaushik Sethunath (Visisonics Corporation); Ramani
[email protected] (Visisonics Corporation)

5245: Cold Diffusion for Speech Enhancement

Hao Yen (Georgia Institute of Technology)*; François G Germain (Mitsubishi Electric Research
Laboratories (MERL)); Gordon Wichern (Mitsubishi Electric Research Laboratories (MERL)); Jonathan
LeRoux (Mitsubishi Electric Research Laboratories (MERL))

5275: FEDRPO: FEDERATED RELAXED PARETO OPTIMIZATION FOR ACOUSTIC EVENT

CLASSIFICATION
Meng Feng (MIT)*; Chieh-Chi Kao (Amazon); Qingming Tang (Amazon, Alexa); Amit Solomon (Amazon);
Viktor Rozgic (Amazon Alexa); Chao Wang (Amazon)

5278: Spherical sector harmonics based soundfield radial extrapolation and robustness analysis
Hanwen Bi (ANU)*; thushara abhayapala (The Australian National University); fei ma (Australian National
University); Prasanga Samarasinghe (Australian National University)

5297: LOSS FUNCTION DESIGN FOR DNN-BASED SOUND EVENT LOCALIZATION AND
DETECTION ON LOW-RESOURCE REALISTIC DATA
Qing Wang (University of Science and Technology of China); Jun Du (University of Science and
Technology of China)*; Zhaoxu Nian (University of Science and Technology of China); Shutong Niu
(University of Science and Technology of China ); Li Chai (University of Science and Technologoy of
China); Huaxin Wu (iFlytek Research); Jia Pan (University of Science and Technology of China); Chin-Hui
Lee (Georgia Institute of Technology)

5316: FretNet: Continuous-Valued Pitch Contour Streaming for Polyphonic Guitar Tablature
Transcription
Frank Cwitkowitz (University of Rochester)*; Toni Hirvonen (Yousician); Anssi Klapuri (Yousician)

5328: IMPROVING ACOUSTIC ECHO CANCELLATION BY MIXING SPEECH LOCAL AND GLOBAL
FEATURES WITH TRANSFORMER
yajie liu (School of Computer Science, Wuhan University)*; Xinmeng Xu (Wuhan University); Weiping Tu
(Wuhan University); Yuhong Yang (Wuhan University); Li Xiao (School of Computer Science, Wuhan
University)

5376: On Negative Sampling for Contrastive Audio-Text Retrieval

Huang Xie (Tampere University)*; Okko Räsänen (Tampere University); Tuomas Virtanen (Tampere
University)

5400: JACAPPELLA CORPUS: A JAPANESE A CAPPELLA VOCAL ENSEMBLE CORPUS

Tomohiko Nakamura (The University of Tokyo)*; Shinnosuke Takamichi (The University of Tokyo); Naoko
Tanji (The University of Tokyo); Satoru Fukayama (National Institute of Advanced Industrial Science and
Technology (AIST)); Hiroshi Saruwatari (The University of Tokyo)

5425: Progressive Multi-stage Neural Audio Codec with Psychoacoustic Loss and Discriminator
Byeong Hyeon Kim (Yonsei University)*; Hyungseob Lim (Yonsei University); Jihyun Lee (yonsei
university); Inseon Jang (Electronics and Telecommunications Research Institution); Hong-Goo Kang
(Yonsei University)

40
5442: LEARNING TO DETECT NOVEL AND FINE-GRAINED ACOUSTIC SEQUENCES USING
PRETRAINED AUDIO REPRESENTATIONS
Vasudha Kowtha (Apple)*; Miquel Espi (Apple); Jonathan J Huang (Apple); Yichi Zhang (Apple); Carlos
Avendano (Apple)

5457: Reverberation as supervision for speech separation

Rohith Aralikatti (University of Maryland at College Park); Christoph B Boeddeker (Paderborn University);
Gordon Wichern (Mitsubishi Electric Research Laboratories (MERL)); Aswin Shanmugam Subramanian
(Mitsubishi Electric Research Laboratories (MERL)); Jonathan LeRoux (Mitsubishi Electric Research
Laboratories (MERL))*

5466: A Phoneme-Informed Neural Network Model for Note-Level Singing Transcription

Sangeon Yong (KAIST)*; Li Su (Academia Sinica); Juhan Nam (KAIST)

5468: Improving Music Genre Classification from Multi-Modal Properties of Music and Genre
Correlations Perspective
Ganghui Ru (Fudan University); Xulong Zhang (Ping An Technology (Shenzhen) Co., Ltd.); Jianzong
Wang (Ping An Technology (Shenzhen) Co., Ltd)*; Ning Cheng (Ping An Technology (Shenzhen) Co.,
Ltd); Jing Xiao (Ping An Insurance (Group) Company of China)

5519: On the robustness of non-intrusive speech quality model by adversarial examples

Hsin-Yi Lin (Academia Sinica)*; Huan-Hsin Tseng (Academia Sinica); Yu Tsao (Academia Sinica)

5545: NAS-DYMC: NAS-based Dynamic Multi-Scale Convolutional Neural Network for Sound Event
Detection
Wang Jun (Kuaishou Technology)*; Peng Yao (Kuaishou Inc.); Feng Deng (Kuaishou); Jianchao Tan
(Kwai Inc.); Chengru Song (Kuaishou); Xiaorui Wang (Kwai)

5566: Unsupervised Anomaly Detection and Localization of Machine Audio: A GAN-based

Approach
Anbai Jiang (Tsinghua University); Wei-Qiang Zhang (Tsinghua University); Yufeng Deng (Tsinghua
University); Pingyi Fan (Tsinghua University)*; Jia Liu (Tsinghua University)

5588: JOINT NOISE REDUCTION AND LISTENING ENHANCEMENT FOR FULL-END SPEECH
ENHANCEMENT
Haoyu Li (National Institute of Informatics)*; Yun Liu (National Institute of Informatics); Junichi Yamagishi
(National Institute of Informatics)

5610: Partially Adaptive Multichannel Joint Reduction of Ego-noise and Environmental Noise
Huajian Fang ( Universität Hamburg)*; Niklas Wittmer (Universität Hamburg); Johannes Twiefel
(Universität Hamburg); Stefan Wermter (University of Hamburg); Timo Gerkmann (Universität Hamburg)

5637: Solving audio inverse problems with a diffusion model

Eloi Moliner (Aalto University)*; Jaakko Lehtinen (NVIDIA & Aalto University); Vesa Valimaki (Aalto
University)

5672: Multi-dimensional frequency dynamic convolution with confident mean teacher for sound
event detection
shengchang xiao (UCAS)*; xueshuai zhang (UCAS); pengyuan zhang ( Institute of Acoustics, Chinese
Academy of Sciences)

5676: The Potential of Neural Speech Synthesis-Based Data Augmentation for Personalized
Speech Enhancement
Anastasia Kuznetsova (Indiana University)*; Aswin Sivaraman (Indiana University Bloomington); Minje
Kim (Indiana University)

41
5709: Analysing Diffusion-based Generative Approaches versus Discriminative Approaches for
Speech Restoration
Jean-Marie Lemercier (Universität Hamburg)*; Julius Richter (Universität Hamburg); Simon Welker
(Universität Hamburg); Timo Gerkmann (Universität Hamburg)

5721: COSMOPOLITE SOUND MONITORING (COSMO) : A STUDY OF URBAN SOUND EVENT

DETECTION SYSTEMS GENERALIZING TO MULTIPLE CITIES
Florian Angulo (LTCI - Télécom Paris, IP Paris)*; Slim Essid (Telecom Paristech); Geoffroy Peeters (LTCI
- Télécom Paris, IP Paris); Christophe Mietlicki (Bruitparif)

5724: Uncertainty Estimation in Deep Speech Enhancement Using Complex Gaussian Mixture
Models
Huajian Fang ( Universität Hamburg)*; Timo Gerkmann (Universität Hamburg)

5734: Performance above all ? Energy consumption vs. performance, a study on sound event
detection with heterogeneous data
romain serizel (Université de Lorraine)*; Samuele Cornell (Università Politecnica delle Marche); Nicolas
Turpault (Inria)

5736: SELF-REMIXING: UNSUPERVISED SPEECH SEPARATION VIA SEPARATION AND REMIXING

Kohei Saijo (Waseda University)*; Tetsuji Ogawa (Waseda University)

5759: Convolutive NTF for Ambisonic Source Separation Under Reverberant Conditions
Mateusz Guzik (AGH University of Science and Technology)*; Konrad Kowalczyk (AGH University of
Science and Technology)

5778: DiffPhase: Generative Diffusion-based STFT Phase Retrieval

Tal Peer (Universität Hamburg)*; Simon Welker (Universität Hamburg); Timo Gerkmann (Universität
Hamburg)

5842: AUDIO SIGNAL ENHANCEMENT WITH LEARNING FROM POSITIVE AND UNLABELLED
DATA
Nobutaka Ito (UTokyo)*; Masashi Sugiyama (RIKEN/The University of Tokyo)

5884: NOTE AND PLAYING TECHNIQUE TRANSCRIPTION OF ELECTRIC GUITAR SOLOS IN REAL-
WORLD MUSIC PERFORMANCE
TungSheng Huang (Georgia Institute of Technology)*; Ping-Chung Yu (National Tsing Hua University); Li
Su (Academia Sinica)

5908: CENTRALIZED CASCADE MULTI-CHANNEL NOISE REDUCTION AND ACOUSTIC

FEEDBACK CANCELLATION IN A WIRELESS ACOUSTIC SENSOR AND ACTUATOR NETWORK
Santiago Ruiz (KU Leuven)*; Toon van Waterschoot (Department of Electrical Engineering (ESAT-
STADIUS/ETC)); Marc Moonen (Department of Electrical Engineering (ESAT-STADIUS), KU Leuven)

5924: Immersive enhancement and removal of loudspeaker sound using wireless assistive
listening systems and binaural hearing devices
Ryan M Corey (University of Illinois Chicago)*; Andrew C Singer (University of Illinois)

5992: An empirical study on speech restoration guided by self-supervised speech representation

Jaeuk Byun (Naver Corporation)*; Youna Ji (NAVER Corperation); Soo-Whan Chung (Naver
Corporation); Soyeon Choe (NAVER Corporation); Min-Seok Choi (NAVER)

42
6101: Wireless Deep Speech Semantic Transmission
Zixuan Xiao (Beijing University of Posts and Telecommunications); Shengshi Yao (Beijing University of
Posts and Telecommunications); Jincheng Dai (Beijing University of Posts and Telecommunications)*;
Sixian Wang (Beijing University of Posts and Telecommunications); kai niu (Beijing University of Posts
and Telecommunications); Ping Zhang ( Beijing University of Posts and Telecommunications)

6117: POSITIVE-PAIR REDUNDANCY REDUCTION REGULARISATION FOR SPEECH-BASED

ASTHMA DIAGNOSIS PREDICTION
Georgios Rizos (Imperial College London)*; Rafael Calvo (Imperial College London); Bjoern W. Schuller
(Imperial College London)

6119: Incorporating lip features into audio-visual multi-speaker DOA estimation by gated fusion
Ya Jiang (University of Science and Technology of China)*; Hang Chen (USTC); Jun Du (University of
Science and Technology of China); Qing Wang (University of Science and Technology of China); Chin-Hui
Lee (Georgia Institute of Technology)

6130: Toward Universal Text-to-Music Retrieval

Seungheon Doh (KAIST)*; Minz Won (ByteDance); Keunwoo Choi (Gaudio Lab); Juhan Nam (KAIST)

6135: Lightweight Annotation and Class Weight Training for Automatic Estimation of Alarm
Audibility in Noise
François Effa (INRS)*; romain serizel (Université de Lorraine); Jean-Pierre Arz (INRS); Nicolas Grimault
(Université Lyon 1)

6141: Textless Speech-to-Music Retrieval Using Emotion Similarity

Seungheon Doh (KAIST)*; Minz Won (ByteDance); Keunwoo Choi (Gaudio Lab); Juhan Nam (KAIST)

6169: A MODEL-BASED HEARING COMPENSATION METHOD USING A SELF-SUPERVISED

FRAMEWORK
Yadong Niu (Peking University); Nan Li (peking university); Xihong Wu (Peking University); Jing Chen
(Peking University)*

6176: Multitrack Music Transcription with a Time-Frequency Perceiver

Wei-Tsung Lu (TikTok)*; Ju-Chiang Wang (TikTok); Yun-Ning Hung (TikTok)

6209: Modelling black-box audio effects with time-varying feature modulation

Marco Comunita (Queen Mary University of London)*; Christian J. Steinmetz (Queen Mary University of
London); Huy Phan (Amazon Alexa); Joshua D. Reiss (Queen Mary University of London)

6220: AUDIO QUALITY ASSESSMENT OF VINYL MUSIC COLLECTIONS USING SELF-SUPERVISED

LEARNING
Alessandro Ragano (University College Dublin)*; Emmanouil Benetos (Queen Mary University of
London); Andrew Hines (University College Dublin)

6288: Extreme Audio Time Stretching using Neural Synthesis

Leonardo Fierro (Aalto University)*; Alec P Wright (Aalto University); Vesa Valimaki (Aalto University);
Matti Hämäläinen (Nokia Technologies)

6341: Effectiveness of Inter- and Intra-Subarray Spatial Features for Acoustic Scene Classification
Takao Kawamura (Tokyo Metropolitan University)*; Yuma Kinoshita (Tokai University); Nobutaka Ono
(Tokyo Metropolitan University); Robin Scheibler (LINE Corporation)

43
6346: Piecewise position encoding in convoutional neural network for cough-based COVID-19
detection
Jiakun Shen (Institute of Acoustics, Chinese Academy of Sciences)*; XueShuai Zhang (University of
Chinese Academy of Sciences); pengyuan zhang (Institute of Acoustics, Chinese Academy of Sciences);
Yonghong Yan (Institute of Acoustics, Chinese Academy of Sciences); Shaoxing Zhang (Peking
University Third Hospital); Zhihua Huang (Xinjiang University); Yanfen Tang (Beijing Ditan Hospital Capital
Medical University); Yu Wang (Beijing Ditan Hospital Capital Medical University); Fujie Zhang (Beijing
Ditan Hospital Capital Medical University); Aijun Sun (Dalian Public Health Clinical Center)

6350: TransPlayer: Timbre Style Transfer with Flexible Timbre Control

Yuxuan Wu (Carnegie Mellon University)*; Yifan He (Carnegie Mellon University); Xinlu Liu (Carnegie
Mellon University); Yi Wang (Carnegie Mellon University); Roger B. Dannenberg (School of Computer
Science, Carnegie Mellon University)

6362: Neural Fourier Shift for Binaural Speech Rendering

Jin Woo Lee (Seoul National University)*; Kyogu Lee (Seoul National University)

6381: ByteCover3: Accurate Cover Song Identification on Short Queries

Xingjian Du (ByteDance)*; Xia Liang (Bytedance); Zijie Wang (Zhejiang Univerisity); Huidong Liang
(Oxford University); Bilei Zhu (ByteDance AI Lab); Zejun Ma (Bytedance)

6388: Aiding speech harmonic recovery in DNN-based single channel noise reduction using
cepstral excitation manipulation (CEM) components
Yanjue Song (Ghent University - imec)*; Nilesh Madhu (IDLab, Ghent University - imec)

6433: Building Keyword Search System from End-to-End ASR Systems

Ruizhe Huang (Johns Hopkins University)*; Matthew S Wiesner (Johns Hopkins University); Paola Garcia
(Johns Hopkins University); Daniel Povey (Johns Hopkins University); Jan Trmal (Johns Hopkins
University); Sanjeev Khudanpur (Johns Hopkins University)

6487: Image source method based on the directional impulse responses

Jiarui Wang (The Australian National University)*; Prasanga Samarasinghe (Australian National
University); thushara abhayapala (The Australian National University); Jihui (Aimee) Zhang (University of
Southampton)

6488: MUSIC REARRANGEMENT USING HIERARCHICAL SEGMENTATION

Christos Plachouras (Universitat Pompeu Fabra)*; Marius Miron (Music Technology Group, Universitat
Pompeu Fabra)

6537: A Contrastive Embedding-based Domain Adaptation method for Lung Sound Recognition in
Children Community-Acquired Pneumonia
Dongmin Huang (Southern University of Science and Technology); Lingwei Wang (Shenzhen People's
Hospital); Hongzhou Lu (Department of Infectious Diseases, Shanghai Public Health Clinical Center,
Fudan University, Shanghai, China); Wenjin Wang (Southern University of Science and Technology)*

44
 Biomedical Imaging and Signal Processing

133: Tensor-Based Complex-valued Graph Neural Network for Dynamic Coupling Multimodal Brain
Networks
Yanwu Yang (HIT at shenzhen)*; Guoqing Cai (Harbin Institute of Technology, Shenzhen); Chenfei Ye
(Harbin Institute of Technology at Shenzhen); Yang Xiang (Peng Cheng Laboratory); Ting Ma (Harbin
Institute of Technology,Shenzhen)

139: A new Semi-supervised classification method using a supervised autoencoder for biomedical
applications
Cyprien Gille (UMONS); Frederic Guyard (Orange Labs); Michel Barlaud (University of Nice)*

197: DIGITAL PHENOTYPE REPRESENTATION BY STATISTICAL, INFORMATION THEORY, DATA-

DRIVEN APPROACH WITH DIGITAL HEALTH DATA
Binh Nguyen (TMU)*; Michael Nigro (Toronto Metropolitan University); Alice Rueda (Ryerson University);
Venkat Bhat (University of Toronto); Sri Krishnan (Ryerson University)

201: Towards simultaneous segmentation of liver tumors and intrahepatic vessels via cross-
attention mechanism
Haopeng Kuang (Fudan University); Dingkang Yang (Fudan University); Shunli Wang (Fudan University);
Xiaoying Wang (Zhongshan Hospital, Fudan University); Lihua Zhang (Fudan University)*

269: Parasympathetic-Sympathetic Causal Interactions and Perceived Workload for Varying

Difficulty Affective Computing Tasks
Pravallika Lavanuru (Human Space Flight Centre, Indian Space Research Organization, Bangalore,
India.); Sawon Pratiher (IIT Kharagpur)*; Karuna P Sahoo (IIT Kharagpur); Mrinal Acharya (Dr. B C Roy
Multi-speciality Medical Research Centre, Indian Institute of Technology Kharagpur, India.); Sreejith S
(Human Space Flight Centre, Indian Space Research Organization, Bangalore, India.); Nirmalya Ghosh
(Indian Institute of Technology Kharagpur); Amit Patra (IIT Kharagpur)

280: OCT image blind despeckling based on gradient guided filter with speckle statistical prior
sanqian Li (Southern University of Science and Technology); Muxing Xiong (Southern University of
Science and Technology); Bing Yang (Southern University of Science and Technology); Xiaoqing Zhang
(Southern University of Science and Technology); Risa Higashita (tomey corporation)*; Jiang Liu
(Southern University of Science and Technology)

370: ViTASD: Robust Vision Transformer Baselines for Autism Spectrum Disorder Facial
Diagnosis
Xu Cao (NYU)*; Wenqian Ye (NYU); Elena Sizikova (FDA); Xue Bai (Shenzhen children's hospital );
Megan Coffee (NYU); Hongwu Zeng (Shenzhen Children's Hospital); Jianguo Cao (Shenzhen Children's
Hospital)

387: LDTSF: A LABEL-DECOUPLING TEACHER-STUDENT FRAMEWORK FOR SEMI-SUPERVISED

ECHOCARDIOGRAPHY SEGMENTATION
Jiapeng Zhang (University Of Shanghai For Science And Technology); Yongxiong Wang (University of
Shanghai for Science and Technology)*; Zhiqun Pan (University of Shanghai for Science and
Technologyh); Zhenhui Tang (Shanghai Jiao Tong University); Lijun Chen (Shanghai Children’s Medical
Center); Jinlong Liu (Shanghai Children’s Medical Center, School of Medicine, Shanghai Jiao Tong
University)

415: END-TO-END CLASSIFICATION OF CELL-CYCLE STAGES WITH CENTER-CELL FOCUS

TRACKER USING RECURRENT NEURAL NETWORKS
Abin Jose (RWTH)*; Rijo Roy (RWTH Aachen); Dennis Eschweiler (RWTH Aachen University); Ina Laube
(Lehrstuhl für Bildverarbeitung, RWTH Aachen); reza azad (rwth); Daniel Moreno-Andreas (RWTH
Aachen University); Johannes Stegmaier (RWTH Aachen University)

45
424: Cardiac Disease Diagnosis on Imbalanced Electrocardiography Data Through Optimal
Transport Augmentation
Jielin Qiu (Carnegie Mellon University)*; Jiacheng Zhu (Carnegie Mellon University); Mengdi Xu
(Carnegie Mellon University); Peide Huang (Carnegie Mellon University); Michael Rosenberg (University
of Colorado Denver - Anschutz Medical Campus); Douglas J Weber (Carnegie Mellon University);
Emerson Liu (Allegheny General Hospital ); DING ZHAO (Carnegie Mellon University)

468: IR-ECG: Invertible Reconstruction of ECG

Peng Wang (Institute of Computing Technology)*; Xi Huang (Institute of computing technology of the
Chinese Academy of Sciences); Li Cui ( Institute of computing technology of the Chinese Academy of
Sciences)

511: Two-Phase Prototypical Contrastive Domain Generalization for Cross-Subject EEG-Based

Emotion Recognition
Honghua Cai (South China Normal University); Jiahui Pan (South China Normal University)*

538: IDEAL: Improved DEnse LocAL Contrastive Learning for Semi-Supervised Medical Image
Segmentation
Hritam Basak (Stony Brook University)*; Soumitri Chattopadhyay (Jadavpur University); Rohit Kundu
(University of California, Riverside); Sayan Nag (University of Toronto); Rammohan Mallipeddi
(Kyungpook national University)

601: Efficient implementation of robust CUSUM algorithm to characterize nanogaps

measurements with heavy-tailed noise
Javier Kipen (KTH)*; Joakim Jalden (KTH); Shyamprasad Raja (KTH); Saumey Jain (KTH Royal Institute
of Technology)

634: LOW-DOSE CT RECONSTRCTION VIA OPTIMIZATION-INSPIRED GAN

jiawei jiang (zhejiang university of technology)*; Yuchao Feng (Zhejiang University of Technology);
Honghui Xu (Zhejiang University of Technology); Jianwei Zheng (Zhejiang University of Technology)

645: Exploiting Interactivity and Heterogeneity for Sleep Stage Classification via Heterogeneous
Graph Neural Network
Ziyu Jia (Beijing Jiaotong University); Youfang Lin (Beijing Jiaotong University); Yuhan Zhou (Beijing
Jiaotong University); Xiyang Cai ( University of California, Los Angeles); Peng Zheng (Beijing Jiaotong
University); Qiang Li (RWTH Aachen University); Jing Wang (Beijing Jiaotong University)*

788: CONSTRAINED INDEPENDENT COMPONENT ANALYSIS BASED ON ENTROPY BOUND

MINIMIZATION FOR SUBGROUP IDENTIFICATION FROM MULTISUBJECT FMRI DATA
Hanlu Yang (University of Maryland, Baltimore County)*; Fateme Ghayem (University of Maryland,
Baltimore County); Ben Gabrielson (University of Maryland, Baltimore County); Mohammad Akhonda
(UMBC); Vince Calhoun (TReNDS); Tulay Adali (University of Maryland, Baltimore County)

888: Wavelet2Vec: A Filter Bank Masked Autoencoder for EEG-based Seizure Subtype
Classification
Ruimin Peng (Huazhong University of Science and Technology); changming zhao (Huazhong University
of Science and Technology); Yifan Xu (Huazhong University of Science and Technology); Jun Jiang
(Wuhan Children's Hospital); Guangtao Kuang (Wuhan Children's Hospital); Jianbo Shao (Wuhan
Children's Hospital); Dongrui Wu (Huazhong University of Science and Technology)*

925: Subject-specific Adaptation for a Causally-Trained Auditory-Attention Decoding System

Christine Beauchene (MIT Lincoln Laboratory)*; Mike Brandstein (MIT Lincoln Laboratory); Stephanie
Haro (Harvard University ); Thomas Quatieri (Massachusetts Institute of Technology Lincoln Laboratory);
Christopher Smalt (Massachusetts Institute of Technology Lincoln Laboratory)

46
1049: EEG2IMAGE: Image Reconstruction from EEG Brain Signals
Prajwal Singh (Indian Institute of Technology Gandhinagar, Gujarat, India)*; Pankaj Pandey (Indian
Institute of Technology Gandhinagar); Krishna P Miyapuram (Indian Institute of
Technology,Gandhinagar,India); Shanmuganathan Raman (Indian Institute of Technology (IIT)
Gandhinagar)

1147: MLP-GAN for Brain Vessel Image Segmentation

Bin Xie (Illinois Institute of Techonology)*; Hao Tang (ETH Zurich); Bin Duan (Illinois Institute of
Technology); Dawen Cai ( University of Michigan); Yan Yan (Illinois Institute of Technology)

1164: SCSGNet: Spatial-Correlated and Shape-Guided Network for Breast Mass Segmentation
Qingqiu Li (Fudan University)*; Jilan Xu (Fudan University); Runtian Yuan ( Fudan University);
Yuejie Zhang (Fudan University); Rui Feng (Fudan University)

1270: Generative De Novo Protein Design with Global Context

Cheng Tan (Zhejiang University & Westlake University)*; Zhangyang Gao (westlake university); Jun Xia
(Westlake University); Bozhen Hu (Zhejiang University & Westlake University); Stan Z. Li (Westlake
University)

1295: Elastic Graph Transformer Networks for EEG-based Emotion Recognition

Wei-Bang Jiang (Shanghai Jiao Tong University)*; Xu Yan (University of Washington); Wei-Long Zheng
(Shanghai Jiao Tong University); Bao-Liang Lu (Shanghai Jiao Tong University)

1342: FedEEG: Federated EEG Decoding via Inter-subject Structure Matching

Wenlong Hang (Nanjing TECH University); Jiaxing Li (School of Computer Science and Technology,
Nanjing Tech University); Shuang Liang (Nanjing University of Posts and Telecommunications)*; yuan wu
(Nanjing Tech University); Baiying Lei (Shenzhen University); Jing Qin (The Hong Kong Polytechnic
University); Yu Zhang (Lehigh University, BIOE); Kup-Sze Choi (The Hong Kong Polytechnic University)

1384: Coarse-to-Fine Covid-19 Segmentation via Vision-Language Alignment

dandan shan (Xiamen University); Zihan Li (University of Illinois at Urbana-Champaign); Wentao Chen
(Beijing University of Posts and Telecommunications); Qingde Li (University of Hull); Jie Tian (); Qingqi
Hong (Xiamen University)*

1539: A Mathematical Model for Neuronal Activity and Brain Information Processing Capacity
Yu Zheng (Michigan State University); David Zhu (Michigan State University); Jian Ren (Michigan State
University); Taosheng Liu (Michigan State University); Karl Friston (University College London); Tongtong
Li (Michigan State University)*

1667: Unbiased unsupervised stimulus reconstruction for EEG-based auditory attention decoding
Nicolas Heintz (KU Leuven)*; Simon Geirnaert (KU Leuven); Tom Francart (KU Leuven); Alexander
Bertrand (KU Leuven)

1771: This changes to that : Combining causal and non-causal explanations to generate disease
progression in capsule endoscopy
Anuja Vats (NTNU)*; Ahmed Mohammed (NTNU); Marius Pedersen (NTNU); Nirmalie Wiratunga (Robert
Gordon University)

1852: Perspective Projection-Based 3D CT Reconstruction from Biplanar X-rays

Daeun Kyung (KAIST)*; Kyungmin Jo (Korea Advanced Institute of Science and Technology); Jaegul
Choo (Korea Advanced Institute of Science and Technology); Joonseok Lee (Google Research & Seoul
National University); Edward Choi (KAIST)

47
1865: Domain Generalized Fundus Image Segmentation via Dual-Level Mixing
Xin Luo (College of Computer, National University of Defense Technology)*; Wei Chen (College of
Computer, National University of Defense Technology); Chen Li (National University of Defense
Technology); Bin Zhou (National University of Defense Technology); yusong tan (College of Computer,
National University of Defense Technology)

2029: Real-time Wireless ECG-derived Respiration Rate Estimation Using an Autoencoder with a
DCT Layer
Hongyi Pan (University of Illinois Chicago)*; Xin Zhu (UIC); Zhilu Ye (University of Illinois Chicago); Pai-
Yen Chen (University of Illinois Chicago); Ahmet E Cetin (University of Illinois at Chicago)

2097: Prototype Knowledge Distillation for Medical Segmentation with Missing Modality
Shuai Wang (Tsinghua University)*; Zipei Yan (The Hong Kong Polytechnic University); Daoan Zhang
(Southern University of Science and Technology); Haining Wei (Tsinghua University); Zhongsen Li
(Tsinghua University); Rui Li (Tsinghua University)

2114: DIFFUSIONNET: AN EFFICIENT FRAMEWORK TO CLASSIFY SINGLE-MOLECULE IMAGES

WITH LATENT ENTROPY MINIMIZATION
Soumee Guha (University of Virginia); Olivia de Cuba (University of Virginia); Andreas Gahlmann
(University of Virginia); Scott Acton (University of Virginia)*

2116: HIERARCHICAL FILTERING WITH ONLINE LEARNED PRIORS FOR ECG DENOISING
Timur Locher (ETH Zurich); Guy Revach (ETH Zürich)*; Nir Shlezinger (Ben-Gurion University); Ruud J.
G. van Sloun (Technical university of Eindhoven); Rik Vullings ( Technical university of Eindhoven)

2159: Assessing the Robustness of Deep Learning-Assisted Pathological Image Analysis under
Practical Variables of Imaging System
YUXUAN SUN (Westlake University)*; Chenglu Zhu (Westlake University); Yunlong Zhang (Westlake
University); Honglin Li (Westlake University); Pingyi Chen (Westlake University); Lin Yang (Westlake
University)

2206: Diabetic Retinopathy Grading with Weakly-supervised Lesion Priors

Junlin Hou (Fudan University)*; Fan Xiao (Fudan University); Jilan Xu (Fudan University); Rui Feng
(Fudan University); Yuejie Zhang (Fudan University); Haidong Zou (Shanghai Eye Diseases Prevention
and Treatment Center); Lina Lu (Shanghai Eye Diseases Prevention and Treatment Center); Wenwen
Xue (Shanghai Eye Diseases Prevention and Treatment Center)

2213: BrainNetFormer: Decoding Brain Cognitive States With Spatial-Temporal Cross Attention
Leheng Sheng (Tsinghua University); Wenhan Wang (Southeast University); Zhiyi Shi (Carnegie Mellon
University); Jichao Zhan (Southeast University); Youyong Kong (Southeast University)*

2228: Benchmarking White Blood Cell Classification Under Domain Shift

Satoshi Tsutsui (Nanyang Technological University, Singapore)*; Zhengyang Su (NTU); Bihan Wen
(Nanyang Technological University)

2297: Multi-stage Aggregation Transformer for Medical Image Segmentation

Xiaoyan Wang (Zhejiang University of Technology); Minghan Shao (Zhejiang University of Technology);
Dongyan Guo (Zhejiang University of Technology)*; Ying Cui (Zhejiang University of Technology); Xiaojie
Huang (Zhejiang University); Ming Xia (Zhejiang University of Technology); Cong Bai (Zhejiang University
of Technology)

2298: ULTRASOUND IMAGE QUALITY CONTROL USING SPEECH-ASSISTED SWITCHABLE

CYCLEGAN
Jaeyoung Huh (KAIST)*; Shujaat Khan (Korea Advanced Institute of Science and Technology (KAIST));
Eun Sun Lee (Chung-Ang University Hospital); Jong Chul Ye (Kim Jaechul Graduate School of AI, KAIST,
Korea)

48
2378: A Novel Heart Rate Estimation Method Exploiting Heartbeat Second Harmonic
Reconstruction via Millimeter Wave Radar
Tao Li (China University of Mining and Technology)*; Huayu Shou (China University of Mining and
Technology); Yuchen Deng (China University of Mining and Technology); Yu Zhou (China University of
Mining and Technology); Chenqi Shi (China University of Mining and Technology); Pengpeng Chen
(China University of Mining and Technology)

2441: CROSS-SITE GENERALIZATION FOR IMBALANCED EPILEPTIC CLASSIFICATION

Tala Raif Abdallah (Université d'Angers)*; Nisrine Jrad (Université d'Angers/UCO); Fahed Abdallah
(Lebanese University); Anne heurtier (Université d'Angers); Patrick Van Bogaert (CHU)

2466: ECG Artifact Removal from Single-Channel Surface EMG Using Fully Convolutional
Networks
Kuan-Chen Wang (National Taiwan University); Kai-Chun Liu (Academia Sinica); Sheng-Yu Peng
(National Taiwan University of Science and Technology); Yu Tsao (Academia Sinica)*

2673: A New Approach to Extract Fetal Electrocardiogram Using Affine Combination of Adaptive
Filters
Yu Xuan (University of California San Diego); Xiangyu Zhang (Johns Hopkins University)*; Shuyue Stella
Li (Johns Hopkins University); zihan shen (University of Chinese Academy of Sciences); XIN XIE
(University of Califonia, San Diego); Paola Garcia (Johns Hopkins University); Roberto Togneri (The
University of Western Australian)

2754: ECGT2T: Towards Synthesizing Twelve-Lead Electrocardiograms from Two Asynchronous

Leads
Yong-Yeon Jo (Medical AI Inc.)*; Young Sang Choi (National Cancer Center); Jong-Hwan Jang (Medical
AI); Joon-myoung Kwon (Medical AI Co. Ltd.)

2836: Spatio-Temporal Structure Consistency for Semi-supervised Medical Image Classification

Lei Wentao (The Chinese University of Hongkong, Shenzhen)*; Lei Liu (The Chinese University of Hong
Kong, Shenzhen); Li Liu (Shenzhen Research Institute of Big Data, the chinese university of hong kong
shenzhen)

2854: LSSED: A robust segmentation network for inflamed appendix from CT images
Wing W.Y. Ng (South China University of Technology); Peixin Zheng (South China University of
Technology)*; Ting Wang (South China University of Technology); Jianjun Zhang (South China University
of Technology); Hui Zhou (The Sixth Affiliated Hospital of Guangzhou Medical University, Qingyuan
People’s Hospital); GuangMing Li (The Sixth Affiliated Hospital of Guangzhou Medical University,
Qingyuan People’s Hospital); Dan Liang (Guangzhou First People’s Hospital/The Second Affiliated
Hospital, South China University of Technology); Yinhao Liang (South China University of Technology);
Xinhua Wei (Department of Radiology, Guangzhou First People's Hospital, South China University of
Technology)

2926: Decoding musical pitch from human brain activity with automatic voxel-wise whole-brain
fMRI feature selection
Vincent K.M. Cheung (Sony Computer Science Laboratories, Inc.)*; Yueh-Po Peng (Institute of
Information Science, Academia Sinica); Jing-Hua Lin (Academia Sinica); Li Su (Academia Sinica)

2964: LightVessel: Exploring Lightweight Coronary Artery Vessel Segmentation via Similarity
Knowledge Distillation
Hao Dang (Henan University of Chinese Medicine)*; Yuekai Zhang (Beijing University of Posts and
Telecommunications); Xingqun Qi (University of Technology Sydney); Wanting Zhou (Beijing University of
Posts and Telecommunications); Muyi Sun (CRIPAC, Institute of Automation, Chinese Academy of
Sciences)

49
2984: BLOOD OXYGEN SATURATION ESTIMATION FROM FACIAL VIDEO VIA DC AND AC
COMPONENTS OF SPATIO-TEMPORAL MAP
Yusuke Akamatsu (NEC Corporation)*; Yoshifumi Onishi (NEC Corporation); Hitoshi Imaoka (NEC
Corporation)

3019: Semantic Memory Guided Image Representation for Polyp Segmentation

Zijin Yin (Beijing University of Posts and Telecommunications); Runpu Wei (Beijing University of Posts
and Telecommunications); Kongming Liang (Beijing University of Posts and Telecommunications)*;
Yiyang Lin (Beijing University of Posts and Telecommunications); Wei Liu (Beijing University of Posts and
Telecommunications); Zhanyu Ma (Beijing University of Posts and Telecommunications); Min Min (The
Fifth Medical Center of Chinese PLA General Hospital); Jun Guo (Beijing University of Posts and
Telecommunications)

3055: Estimation of cardiac fibre direction based on activation maps

Johannes W. de Vries (TU Delft)*; Miao Sun (TU Delft); Natasja de Groot (Erasmus MC); Richard
Hendriks (TU Delft)

3058: BIMODAL FUSION NETWORK FOR BASIC TASTE SENSATION RECOGNITION FROM
ELECTROENCEPHALOGRAPHY AND ELECTROMYOGRAPHY
Han Gao (Zhejiang University)*; Shuo Zhao (Zhejiang university); Huiyan Li (Zhejiang University); Li Liu
(Zhejiang University); You Wang (Zhejiang University); Ruifen Hu (Zhejiang University); Jin Zhang (Hunan
Normal University); Guang Li (Zhejiang University)

3124: Interpretable Nonnegative Incoherent Deep Dictionary Learning for fMRI data analysis
Manuel Morante (AAU)*; Jan Ostergaard (Aalborg University); Sergios Theodoridis (Aalborg University)

3205: SS-ADMM: STATIONARY AND SPARSE GRANGER CAUSAL DISCOVERY FOR CORTICO-
MUSCULAR COUPLING
Farwa Abbas (Imperial College London)*; Verity McClelland (King's College London); Zoran Cvetkovic
(King's College London); Wei Dai (Imperial College London)

3219: Time-Resolved fMRI Shared Response Model Using Gaussian Process Factor Analysis
MohammadReza Ebrahimi (University of Toronto)*; Navona Calarco (University of Toronto); Colin Hawco
(Centre for Addiction and Mental Health); Aristotle Voineskos (CAMH); Ashish Khisti (University of
Toronto)

3224: AUTOMATIC CAMERA POSE ESTIMATION BY KEY-POINT MATCHING OF REFERENCE

OBJECTS
Jinchen Zeng (TU Delft); Rick Butler (TU Delft); Benno Hendriks (Philips); John.J van den Dobbelsteen (
Delft university of technology); Maarten Van der Elst (Reinier de Graaf Groep); Justin Dauwels
(TU Delft)*

3237: A PATIENT INVARIANT MODEL TOWARDS THE PREDICTION OF FREEZING OF GAIT

Nasimuddin Ahmed (TCS Research)*; Shivam Singhal (TCS Research); Aniruddha Sinha (TCS
Research); Avik Ghose (TCS)

3246: FAN-Net: Fourier-based Adaptive Normalization for Cross-Domain Stroke Lesion

Segmentation
Weiyi Yu (Fudan University); Yiming Lei (Fudan University)*; Hongming Shan (Fudan University)

3248: Structured Errors-in-variables Modelling for Cortico-muscular Coherence Enhancement

Zhenghao Guo (King's College London)*; Verity McClelland (King's College London); Wei Dai (Imperial
College London); Zoran Cvetkovic (King's College London)

50
3342: A non-contact SpO2 estimation using video magnification and infrared data
Thomas Stogiannopoulos (DUTH Dept. of Electrical Engineering); Grigorios-Aris Cheimariotis (DUTH
Dept. of Electrical Engineering); Nikolaos Mitianoudis (DUTH Dept. of Electrical Engineering)*

3346: High-dimensional confidence regions in sparse MRI

Frederik Hoppe (RWTH Aachen University)*; Felix Krahmer (Technical University of Munich); Claudio
Mayrink Verdun (Technical University of Munich); Marion Menzel (GE Global Research); Holger Rauhut
(RWTH Aachen University)

3419: EFFICIENT PROTEIN STRUCTURAL CLASS PREDICTION VIA CHAOS GAME

REPRESENTATION AND RECURRENT NEURAL NETWORKS
Michaela Areti Zervou (University of Crete, ICS-FORTH)*; Effrosyni Doutsi (Foundation for Research and
Technology - Hellas (FORTH)); Panagiotis Tsakalides (University of Crete, Foundation for Research and
Technology - Hellas (FORTH))

3424: MTDL-Net: Morphological and Temporal Discriminative Learning for Heartbeat Classification
Can Han (Shanghai Jiao Tong University); Suncheng Xiang (Shanghai Jiao Tong University)*; Dahong
Qian (Shanghai Jiao Tong Univerisity)

3445: ADHD Classification with biomarker identification using a triplet loss attention auto-
encoding network
Yibin Tang (Hohai University); Ying Chen (Changzhou University); Yuan Gao (Hohai University); Aimin
Jiang (Hohai University); Lin Zhou (Southeast University)*

3469: UNeXt: a Low-Dose CT denoising UNet model with the modified ConvNeXt block
Farzan Niknejad Mazandarani (Toronto Metropolitan university)*; Paul Babyn (Physician Executive,
Saskatchewan Health Authority, Saskatoon, S7K 0M7, Canada, ); Javad Alirezaie (Toronto Metropolitan
University, Dept of Electrical Eng.)

3547: Simultaneous Reconstruction and Uncertainty Quantification for Tomography

Agnimitra Dasgupta (University of Southern California)*; Carlo Graziani (Argonne National Laboratory);
Zichao Di (Argonne National Laboratory)

3619: A SPATIAL-TEMPORAL ECG EMOTION RECOGNITION MODEL BASED ON DYNAMIC

FEATURE FUSION
Shuo Xiao (China University of Mining and Technology); Xiaojing Qiu (China University of Mining and
Technology); Chaogang Tang (China Univsersity of Mining and Technology)*; Zhenzhen Huang (China
Univsersity of Mining and Technology)

3757: Heart Rate Estimation and Performance Analysis using MIMO Radar with Dispersed
Antennas
PeiChao Wang (University of Electronic Science and Technology of China); Qian He (University of
Electronic Science and Technology of China)*

3763: Automatic segmentation of nasopharyngeal carcinoma in CT images using dual attention

and edge detection
Qizhi Wang (Xiangtan University); Wei Huang (The First Hospital of ChangSha); Yuan Zhang (Xiangtan
University); Xuanya Li (Baidu); Xiongjun Ye (Chinese Academy of Medical Sciences and Peking Union
Medical College); Kai Hu (Xiangtan University)*

3910: Brain network features differentiate intentions from different emotional expressions of the
same text
Zhongjie Li (Tianjin University)*; Bin Zhao (Japan Advanced Institute of Science and Technology);
Gaoyan Zhang (Tianjin University); Jianwu Dang (Tianjin University)

51
4009: Pseudo Multi-Source Domain Extension and Selective Pseudo-labeling for Unsupervised
Domain Adaptive Medical Image Segmentation
Xiaokang Liu (Xiangtan University); Zhiqiang Wang (Xiangnan University); Kai Hu (Xiangtan University)*;
Xieping Gao (Hunan Normal University)

4185: TOPGFORMER: TOPOLOGICAL-BASED GRAPH TRANSFORMER FOR MAPPING BRAIN

STRUCTURAL CONNECTIVITY TO FUNCTIONAL CONNECTIVITY
Dalu Guo (Southeast University); Ke Zhang (Southeast University); Jiaxing Li (Southeast University);
Youyong Kong (Southeast University)*

4195: Constrained non-negative PARAFAC2 for electromyogram separation

MAGBONDE Abilé Serge (GIPSA LAB)*; QUAINE Franck (GIPSA LAB); Bertrand Rivet (Grenoble-INP)

4226: ADAPTIVE NON-LOCAL GENERATIVE ADVERSARIAL NETWORKS FOR LOW-DOSE CT

IMAGE DENOISING
Linlin Yang (Xidian University); Hongying Liu (Key Lab. of Intelligent Perception and Image Understanding
of Ministry of Education, School of Artificial Intelligence, Xidian University, China)*; Fanhua Shang (Tianjin
University); Yuanyuan Liu (Xidian University)

4270: Multi-Head Feature Pyramid Networks for Breast Mass Detection

Hexiang Zhang (Hebei University of Technology); Zhenghua Xu (Hebei University of Technology)*; Dan
Yao (Hebei University of Technology); Shuo Zhang (Hebei University of Technology); Junyang Chen
(Shenzhen Univeristy); Thomas Lukasiewicz (University of Oxford)

4279: Learning from single-expert annotated labels for automatic sleep staging
Zhiheng Luan (School of Cyber Science and Engineering, Wuhan University)*; Yanzhen Ren (Computer
School of Wuhan University); Li Peng (Wuhan University); Xiong Chen (Sleep Medicine Centre,
Zhongnan Hospital of Wuhan University); Xiuping Yang (Sleep Medicine Centre, Zhongnan Hospital of
Wuhan University); Weiping Tu (Wuhan University); Yuhong Yang (Wuhan University)

4357: U-Shiftformer: brain tumor segmentation using a shifted attention mechanism

Chih-Wei Lin (Fujian Agriculture and Forestry University)*; Zhongsheng Chen (Fujian Agriculture and
Forestry University)

4393: MPS-AMS: Masked Patches Selection and Adaptive Masking Strategy Based Self-
Supervised Medical Image Segmentation
Xiangtao Wang (Hebei University of Technology); Ruizhi Wang (Hebei University of Technology); Tian
Biao (Hebei University of Technology); Jiaojiao Zhang (Hebei University of Technology); Shuo Zhang
(Hebei University of Technology); Junyang Chen (Shenzhen Univeristy); Thomas Lukasiewicz (University
of Oxford); Zhenghua Xu (Hebei University of Technology)*

4430: Exploiting Multi-Decision and Deep Refinement for Ultrasound Image Segmentation
Wenjing Liu (Xiangtan University); Xuanya Li (Baidu); Kai Hu (Xiangtan University)*; Xieping Gao (Hunan
Normal University)

4439: TRANSFORMER-BASED MULTI-PROTOTYPE APPROACH FOR DIABETIC MACULAR EDEMA

ANALYSIS IN OCT IMAGES
Plácido L. Vidal (University of A Coruña); José Joaquim de Moura Ramos (University of A Coruña)*; Jorge
Novo (University of A Coruña); Marcos Ortega (University of A Coruña); Jaime S Cardoso (INESC Porto,
Universidade do Porto)

4560: DISAMBIGUATION OF COGNITIVE IMPAIRMENT DIAGNOSIS WITH EEG-BASED DUAL-

CONTRASTIVE LEARNING
Zhenxi Song (Harbin Institute of Technology (Shenzhen))*; Zian Pei (Shenzhen Bay Laboratory); Huixia
Ren (Shenzhen People's Hospital); Lin Zhu (Shenzhen People’s Hospital); Yi Guo (Shenzhen People’s
Hospital;Shenzhen Bay Laboratory); Zhiguo Zhang (Harbin Institute of Technology (Shenzhen))

52
4600: RETINAL BIOMARKERS FOR DETECTING DIABETIC RETINOPATY USING SMARTPHONE-
BASED DEEP LEARNING FRAMEWORKS
Mahmut Karakaya (Kennesaw State University)*; Ramazan Aygun (Kennesaw State University)

4647: Optimizing Vision Transformers for Medical Image Segmentation

qianying liu (university of glasgow)*; Chaitanya Kaul (University of Glasgow); Jun Wang (University of
Warwick); Christos Anagnostopoulos (University of Glasgow); Roderick Murray-Smith (University of
Glasgow); Fani Deligianni (University of Glasgow)

4661: A Meta-GNN approach to personalized seizure detection and classification

Abdellah RAHMANI (École polytechnique fédérale de Lausanne)*; Arun VENKITARAMAN (École
polytechnique fédérale de Lausanne); Pascal Frossard (EPFL)

4663: Smart Split-Federated Learning Over Noisy Channels for Embryo Image Segmentation
Zahra Hafezi Kafshgari (Simon Fraser University); Ivan Bajic (Simon Fraser University)*; Parvaneh
Saeedi (Simon Fraser University)

4674: RELAPSE PREDICTION FROM LONG-TERM WEARABLE DATA USING SELF-SUPERVISED

LEARNING AND SURVIVAL ANALYSIS
Evangelos Fekas (National Technical University of Athens)*; Athanasia Zlatintsi (National Technical Univ.
of Athens, Greece); Panagiotis P Filntisis (National Technical University of Athens); Christos Garoufis
(National Technical University of Athens); Niki Efthymiou (NTUA); Petros Maragos (National Technical
University of Athens)

4743: Robust online multiband drift estimation in electrophysiology data

Charles Windolf (Columbia University)*; Angelique Paulk (Massachusetts General Hospital); Yoav Kfir
(Massachusetts General Hospital); Eric Eric Trautmann (Columbia University); Domokos Meszéna (MGH
/ Harvard Medical School); William Muñoz (Massachusetts General Hospital); Irene Caprara
(Massachusetts General Hospital); Mohsen Jamali (Massachusetts General Hospital); Julien Boussard
(Columbia University); Ziv Williams (Massachusetts General Hospital); Sydney Cash (Harvard Medical
School ); Liam Paninski (Department of Statistics, Columbia University); Erdem Varol (Columbia
University)

4782: Improving Automatic Sleep Staging via Temporal Smoothness Regularization

Huy Phan (Amazon Alexa)*; Elisabeth Heremans (KU Leuven); Oliver Y. Chén (University of Bristol);
Philipp Koch (University of Luebeck); Alfred Mertins (University of Luebeck); Maarten De Vos (KU
Leuven)

4918: Applying Independent Vector Analysis on EEG-based motor imagery classification

Caroline P. A. Moraes (Federal University of ABC (UFABC))*; Bruno Aristimunha (Federal University of
ABC); Lucas Heck dos Santos (UFABC); Walter Hugo Lopez Pinaya (King's College London); Raphael Y
de Camargo (UFABC); Denis Fantinato (Federal University of ABC); Aline Neves (Federal University of
ABC)

4927: BreathIE: Estimating Breathing Inhale Exhale Ratio Using Motion Sensor Data from
Consumer Earbuds
Nafiul Rashid (Samsung Research America)*; Md Mahbubur Rahman (Samsung Research America);
Tousif Ahmed (Samsung Research America, Inc.); Jilong Kuang (Samsung Research America); Jun Alex
Gao (Samsung Research America)

4973: CO-OPERATIVE CNN FOR VISUAL SALIENCY PREDICTION ON WCE IMAGES

George Dimas (Department of Computer Science and Biomedical Informatics, University of Thessaly,
Greece); Anastasios Koulaouzidis (The Royal Infirmary of Edinburgh); Dimitris K Iakovidis (Department of
Computer Science and Biomedical Informatics, University of Thessaly, Greece)*

53
4982: Glacier: Glass-box Transformer for Interpretable Dynamic Neuroimaging
Usman Mahmood (Georgia State University)*; Zening Fu (Georgia State University); Vince Calhoun
(TReNDS); Sergey Plis (Georgia State University)

4990: COUPLED CP TENSOR DECOMPOSITION WITH SHARED AND DISTINCT COMPONENTS

FOR MULTI-TASK FMRI DATA FUSION
Ricardo Borsoi (CNRS)*; Isabell Lehmann (University of Padeborn); Mohammad Akhonda (UMBC); Vince
Calhoun (TReNDS); Konstantin Usevich (CNRS); David BRIE (Université de Lorraine); Tulay Adali
(University of Maryland, Baltimore County)

4999: HYDRA-HGR: A Hybrid Transformer-based Architecture for Fusion of Macroscopic and

Microscopic Neural Drive Information
Mansooreh Montazerin (Concordia University); Elahe Rahimian (Concordia University); Farnoosh
Naderkhani (Concordia University); S. Farokh Atashzar (NYU); Hamid Alinejad-Rokny (UNSW); Arash
Mohammadi (Concordia University)*

5007: Light-weighted CNN-Attention based architecture for Hand Gesture Recognition via
ElectroMyography
Soheil Zabihi (Concordia University); Elahe Rahimian (Concordia University); Amir Asif (York University);
Arash Mohammadi (Concordia University)*

5024: TEXT-TO-ECG: 12-LEAD ELECTROCARDIOGRAM SYNTHESIS CONDITIONED ON CLINICAL

TEXT REPORTS
Hyunseung Chung (KAIST)*; Jiho Kim (KAIST); Joon-myoung Kwon (Medical AI); Ki-Hyun Jeon (Seoul
National University Bundang Hospital); Min Sung Lee (Medical AI); Edward Choi (KAIST)

5086: AN ADAPTIVE ENHANCEMENT METHOD FOR GASTROINTESTINAL LOW-LIGHT IMAGES

OF CAPSULE ENDOSCOPE
Peixuan Liu (Jiangnan University)*; Yinghui Wang (Jiangnan University); Jinlong Yang (Jiangnan
University); Wei Li (Jiangnan University)

5102: Spatio-Temporal Attention in Multi-Granular Brain Chronnectomes for Detection of Autism

Spectrum Disorder
James Orme-Rogers (University of Southern California)*; Ajitesh Srivastava (University of Southern
California)

5105: Active selection of source patients in transfer learning for epileptic seizure detection using
Riemannian Manifold
Toshiki Orihara (Tokyo University of Agriculture and Technology); Kazi Mahmudul Hassan (Tokyo
University of Agriculture and Technology)*; Toshihisa Tanaka (Tokyo University of Agriculture and
Technology)

5180: A LEARNABLE SPATIAL MAPPING FOR DECODING THE DIRECTIONAL FOCUS OF

AUDITORY ATTENTION USING EEG
Yuanming Zhang (Nanjing University)*; Haoxin Ruan (Nanjing University); Ziyan Yuan (Nanjing
University); Haoliang Du (Nanjing Drum Tower Hospital); Xia Gao (Nanjing Drum Tower Hospital); Jing Lu
(Nanjing University)

5223: Multimodal microscopy image alignment using spatial and shape information and a branch-
and-bound algorithm
Shuonan Chen (Columbia University)*; Bovey Y Rao (Columbia University); Stephanie Herrlinger
(Columbia University); Attila Losonczy (Columbia University); Liam Paninski (Department of Statistics,
Columbia University); Erdem Varol (Columbia University)

5228: Rethinking Learning-based Method for Lossless Genome Compression

Han Yang (Alibaba Group)*; Fei Gu (Alibaba Group); Jieping Ye (Alibaba Group)

54
5234: A New Personalized Efficacy Atlas for Pallidal Deep Brain Stimulation
Xiongbiao Luo (Xiamen University)*

5301: Multi-object Localization and Irrelevant-semantic Separation for Nuclei Segmentation in

Histopathology Images
Ya Tang (Xiangtan University); Xiongjun Ye (Department of Urology, Chinese Academy of Medical
Sciences and Peking Union Medical College, Beijing, 100021); Xuanya Li (Baidu); Zhineng Chen (School
of Computer Science, Fudan University)*

5360: Representation Learning of Clinical Multivariate Time Series with Random Filter Banks
Alireza Keshavarzian (University of Toronto)*; Hojjat Salehinejad (Mayo Clinic); Shahrokh Valaee
(University of Toronto)

5501: Improving EEG-based Emotion Recognition by Fusing Time-frequency And Spatial

Representations
Kexin Zhu (Fudan University); Xulong Zhang (Ping An Technology (Shenzhen) Co., Ltd.); Jianzong Wang
(Ping An Technology (Shenzhen) Co., Ltd)*; Ning Cheng (Ping An Technology (Shenzhen) Co., Ltd); Jing
Xiao (Ping An Insurance (Group) Company of China)

5582: Adversarial Attacks on Genotype Sequences

Daniel Mas Montserrat (Stanford University)*; Alexander Ioannidis (Stanford University)

5626: DGN: DESCRIPTOR GENERATION NETWORK FOR FEATURE MATCHING IN MONOCULAR

ENDOSCOPY 3D RECONSTRUCTION
KaiYun Zhang (Xiamen University); Wenkang Fan (Xiamen University); Yinran Chen (Xiamen
University)*; Xiongbiao Luo (Xiamen University)

5648: Deep Triple-Supervision Learning Unannotated Surgical Endoscopic Video Data for
Monocular Dense Depth Estimation
Wenkang Fan (Xiamen University)*; KaiYun Zhang (Xiamen University); Hong Shi (Fujian Cancer
Hospital & Fujian Medical University Cancer Hospital); Jianhua Chen (Fujian Cancer Hospital & Fujian
Medical University Cancer Hospital); Yinran Chen (Xiamen University); Xiongbiao Luo (Xiamen
University)

5652: Local-Global Progressive U-Transformers for Accurate Hepatic and Portal Veins
Segmentation in Abdominal MR Images
Yu Wu (XiaMen University)*; Dongfang Shen (Xiamen University); Jiabao Jin (Xiamen University);
Guanping Xu (Xiamen University); Yinran Chen (Xiamen University); Xiongbiao Luo (Xiamen University)

5655: DB-UNet: MLP Based Dual Branch UNet for Accurate Vessel Segmentation in OCTA Images
Chengliang Wang (Chongqing University)*; Haojian Ning (Chongqing University); Xinrun Chen
(Chongqing University); Shiying Li (Xiamen University)

5691: Attention-Guided Deep Learning Framework for Movement Quality Assessment

Aditya S Kanade (Indian Institute of Technology Madras); Mansi Sharma (Department of Computer
Science and Engineering, Amrita School of Computing, Coimbatore, Amrita Vishwa Vidyapeetham, India
and Department of Electrical Engineering, IIT Madras)*; M Manivannan ("Indian Institute of Technology
Madras, India")

5722: IMPROVING HEART RATE AND HEART RATE VARIABILITY ESTIMATION FROM VIDEO
THROUGH A HR-RR-TUNED FILTER
Michael Chan (Georgia Institute of Technology)*; Li Zhu (Samsung Research America); Korosh
Vatanparvar (Samsung Research America); Hewon Jung (Georgia Institute of Technology); Jilong Kuang
(Samsung Research America); Alex Gao (Samsung Research America)

55
5926: CROSS-SUBJECT MENTAL FATIGUE DETECTION BASED ON SEPARABLE SPATIO-
TEMPORAL FEATURE AGGREGATION
Yalan Ye (University of Electronic Science and Technology of China)*; Yutuo He (University of Electronic
Science and Technology of China); Wanjing Huang (University of Electronic Science and Technology of
China ); Qiaosen Dong (Sichuan University); Chong Wang (University of Electronic Science and
Technology of China); Guoqing Wang (University of Electronic Science and Technology of China)

6028: A NOVEL TRANSFORMER-BASED PIPELINE FOR LUNG CYTOPATHOLOGICAL WHOLE

SLIDE IMAGE CLASSIFICATION
Gaojie Li ( Central South University)*; Qing Liu (Central South University); Haotian Liu (Central South
University); Yixiong Liang (Central South University)

6034: Spatio-Temporal Hybrid Fusion of CAE and SWIn Transformers for Lung Cancer Malignancy
Prediction
Sadaf Khademi (Concordia University); Shahin Heidarian (Concordia University); Parnian Afshar
(Concordia Uniersity); Farnoosh Naderkhani (Concordia University); Anastasia Oikonomou (University of
Toronto); Konstantinos N Plataniotis (UofT); Arash Mohammadi (Concordia University)*

6068: VISION TRANSFORMER WITH PROGRESSIVE TOKENIZATION FOR CT METAL ARTIFACT

REDUCTION
Songwei Zheng (Fuzhou University)*; Dong Zhang (Fuzhou University); ChunYan Yu (Fuzhou University);
Danhong Zhu (Fuzhou University); Longlong Zhu (Fuzhou University); Hao Liu (Fuzhou University);
Zhongzheng Huang (Fuzhou University)

6083: Heart Rate Extraction from Abdominal Audio Signals

Jake Stuchbury-Wass (University of Cambridge)*; Erika Bondareva (University of Cambridge); Kayla-
Jade Butkow (University of Cambridge); Sanja scepanovic (NOKIA BELL LABS); Zoran Radivojevic
(NOKIA BELL LABS); Cecilia Mascolo (University of Cambridge)

6097: Hankel Structured Low Rank and Sparse Representation via L0-Norm Optimization for
Compressed Ultrasound Plane Wave Signal Reconstruction
Miaomiao Zhang (Capital Normal University); Ji Chen (Capital Normal University); Xiaoyan Fu (Capital
Normal University); Xin Ge (Beijing Jiaotong University); Jingzhi Zhang (Capital Normal University); Na
Jiang (Information Engineering College, Capital Normal University)*; Jan D'Hooge (KU Leuven)

6193: Synthesizing Speech from ECoG with a Combination of Transformer-based Encoder and
Neural Vocoder
Kai Shigemi (Tokyo University of Agriculture and Technology); Shuji Komeiji (Tokyo University of
Agriculture and Technology)*; Takumi Mitsuhashi (Juntendo University School of Medicine); Yasushi
Iimura (Juntendo University School of Medicine); Hiroharu Suzuki (Juntendo University School of
Medicine); Hidenori Sugano (Juntendo University School of Medicine); Koichi SHINODA (Tokyo Institute
of Technology); Kohei Yatabe (Tokyo University of Agriculture and Technology); Toshihisa Tanaka (Tokyo
University of Agriculture and Technology)

6227: Graph based semantic ensemble of Riemannian Neural Structured Learning for BCI-EEG
signal classification
KURUSETTI VINAY GUPTA (IIT KANPUR)*; Prof Laxmidhar Behera (IIT Kanpur); Tushar Sandhan
(Indian Institute of Technology Kanpur)

6265: MLCGAN: MULTI-LEAD ECG SYNTHESIS WITH MULTI LABEL CONDITIONAL GENERATIVE
ADVERSARIAL NETWORK
Jian Wu (East China Normal University); Liping Wang (ECNU)*; Hailin Pan (East China Normal
University); Binyu Wang ( East China Normal University)

56
6402: New Interpretable Patterns and Discriminative Features from Brain Functional Network
Connectivity Using Dictionary Learning
Fateme Ghayem (UMBC)*; Hanlu Yang (University of Maryland, Baltimore County); Furkan Kantar
(UMBC); Seung-Jun Kim (University of Maryland, Baltimore County); Vince Calhoun (TReNDS); Tulay
Adali (University of Maryland, Baltimore County)

6444: Multi-Observation Hidden Semi-Markov Model for Photoplethysmogram Signal Semantic

Segmentation
Navid Hasanzadeh (University of Toronto)*; Shahrokh Valaee (University of Toronto); Hojjat Salehinejad
(Mayo Clinic)

6504: MvCo-DoT: Multi-View Contrastive Domain Transfer Network for Medical Report Generation
Ruizhi Wang (Hebei University of Technology); Xiangtao Wang (Hebei University of Technology);
Zhenghua Xu (Hebei University of Technology)*; Wenting Xu (Hebei University of Technology); Junyang
Chen (Shenzhen Univeristy); Thomas Lukasiewicz (University of Oxford)

6506: MOTOR ACTIVITY RECOGNITION USING EEG DATA AND ENSEMBLE OF STACKED BLSTM-
LSTM NETWORK AND TRANSFORMER MODEL
Pallavi Kaushik (Indian Institute of Technology Roorkee)*; Ilina Tripathi (Thapar Institute of Engineering);
Dr. Partha Pratim Roy (IIT Roorkee)

6528: NODE-WISE DOMAIN ADAPTATION BASED ON TRANSFERABLE ATTENTION FOR

RECOGNIZING ROAD RAGE VIA EEG
Xueqi Gao (College of Intelligence and Computing, Tianjin University)*; Chao Xu (College of Intelligence
and Computing, Tianjin University); Yihang Song (College of Intelligence and Computing, Tianjin
University); Jing Hu (College of Intelligence and Computing, Tianjin University); Jian Xiao (College of
Intelligence and Computing,Tianjin University); Zhaopeng Meng (College of Intelligence and Computing,
Tianjin University)

57
 Computational Imaging

127: Dual-Cycle: Self-Supervised Dual-View Fluorescence Microscopy Image Reconstruction

using CycleGAN
Tomas Kerepecky (Czech Academy of Sciences)*; Jiaming Liu (Washington University in St. Louis); Xue
Wen Ng (Washington University School of Medicine); David Piston (Washington University School of
Medicine); Ulugbek S. Kamilov (Washington University in St. Louis)

385: Event-Based Visual Microphone

Matthew D Howard (Air Force Research Laboratory)*; Keigo Hirakawa (University of Dayton)

435: Single-Shot Fractional Fourier Phase Retrieval

Yixiao Yang (Beijing Institute of Technology); Ran Tao (Beijing Institute of Technology)*

441: Ultra Real-Time Portrait Matting via Parallel Semantic Guidance

Xin Huang (University of Maryland, Baltimore County); Jiake Xie (PicUP.Ai); Bo Xu (OPPO Research
Institute)*; Han Huang (OPPO Research Institute); Ziwen Li (OPPO Research Institute); Cheng Lu
(XPENG); Yandong Guo (OPPO Research Institute); Yong Tang (PicUP.Ai)

532: Minimising Distortion for GAN-based Facial Attribute Manipulation

Mingyu Shao (Dongguan University of Technology); Li Lu (Dongguan University of Technology); Ye Ding
(Dongguan University of Technology)*; Qing Liao (Harbin Institute of Technology (Shenzhen))

731: LIGHT FIELD COMPRESSION VIA COMPACT NEURAL SCENE REPRESENTATION

Jinglei Shi (Nankai University)*; Christine Guillemot (INRIA)

860: Transient Dictionary Learning for Compressed Time-of-Flight Imaging

Miguel Heredia Conde (University of Siegen)*

1042: Unrolled Fourier Disparity Layer optimization for scene reconstruction from few-shots focal
stacks
Brandon Le Bon (Centre INRIA de l'Université de Rennes)*; Mikaël Le Pendu (InterDigital, Rennes);
Christine Guillemot (INRIA)

1068: A DEEP DISENTANGLED APPROACH FOR INTERPRETABLE HYPERSPECTRAL UNMIXING

Ricardo Borsoi (CNRS)*; Tales C O Imbiriba (Northeastern University); Deniz Erdogmus (Northeastern
University)

1097: Semi-SwinDerain: Semi-supervised Image Deraining Network using Swin Transformer

Chun Ren (Beijing University of Posts and Telecommunications)*; Danfeng Yan (State Key Laboratory of
Networking and Switching Technology Beijing University of Posts and Telecommunications); Yuanqiang
Cai (Beijing University of Posts and Telecommunications); Li Yang-chun (Chinese Academy of
Cyberspace Studies)

1287: CTTSR: A Hybrid CNN-Transformer Network for Scene Text Image Super-Resolution
Kaiwei Dai (Central South University); Nan Kang (Central South University); Li Kuang (Central South
University)*

1341: Long Range Imaging Using Multispectral Fusion of RGB and NIR Images
Hao Zhang (Xidian University); Lin Mei (Xidian University); Cheolkon Jung (Xidian University)*

1541: Attention Based Relation Network for Facial Action Units Recognition
Yao Wei (South China University of Technology); Haoxiang Wang (South China University of
Technology)*; Mingze Sun (South China University of Technology); Liu Jiawang (SCUT)

58
1641: A Targeted Sampling Strategy for Compressive Cryo Focused Ion Beam Scanning Electron
Microscopy
Daniel Nicholls (University of Liverpool)*; Jack Wells (University of Liverpool); Alex W Robinson
(University of Liverpool); Amirafshar Moshtaghpour (Rosalind Franklin Institute); Maryna Kobylynska
(King's College London); Roland Fleck (King's College London); Angus Kirkland (University of Oxford);
Nigel Browning (University of Liverpool)

1811: Hardware Friendly Spline Sketched Lidar

Michael Sheehan (University of Edinburgh); Julián Tachella (CNRS & ENS de Lyon); Mike Davies
(University of Edinburgh)*

1898: DEEP LOW LIGHT IMAGE ENHANCEMENT VIA MULTI-SCALE RECURSIVE FEATURE
ENHANCEMENT AND CURVE ADJUSTMENT
Haiyan Jin (Xi'an University of Technology); Dawei Wei (Xi'an University of Technology); Haonan Su
(Xi'an University of Technology)*

1954: Capturing Cross-Scale Disparity for Stereo Image Super-Resolution

Kun He (University of Electronic Science and Technology of China); Changyu Li (University of Electronic
Science and Technology of China); Dongyang Zhang (University of Electronic Science and Technology of
China); Jie Shao (University of Electronic Science and Technology of China)*

1996: Super-Resolution for Macro X-ray Fluorescence Data Collected from Old Master Paintings
Su Yan (Imperial College London)*; Herman Jadan (Imperial College London); Jun-Jie Huang (National
University of Defense Technology); Nathan S Daly (The Fitzwilliam Museum); Catherine Higgitt (The
National Gallery); Pier Luigi Dragotti (Imperial College London)

2419: DMSA: DYNAMIC MULTI-SCALE UNSUPERVISED SEMANTIC SEGMENTATION BASED ON

ADAPTIVE AFFINITY
Kun Yang (Heilongjiang University)*; Jun Lu (Heilongjiang University)

2519: Single-photon Image Super-resolution via Self-supervised Learning

Yiwei Chen (Zhejiang University)*; Chen Jiang (Zhejiang University); Yu Pan (Zhejiang University)

2603: BLOCK-BASED COLOR CONSTANCY: THE DEVIATION OF SALIENT PIXELS

Oguzhan Ulucan (Universität Greifswald)*; Diclehan Ulucan (Universität Greifwald); Marc Ebner
(Universität Greifswald)

3104: Self-Supervised Learning with Explorative knowledge Distillation

Tongtong Su (Nankai Univerisity)*; Jinsong Zhang (Nankai Univerisity); Wang Gang (Nankai Univerisity);
Liu Xiaoguang (Nankai Univerisity)

3245: Joint Neural Representation for Multiple Light Fields

Guillaume Le Guludec (Inria)*; Christine Guillemot (INRIA)

3323: Deep Adaptive Superpixels for Hadamard Single Pixel Imaging in Near-Infrared Spectrum
Brayan Monroy (Universidad Industrial de Santander)*; Jorge Bacca (Universidad Industrial de
Santander); Henry Arguello (Universidad Industrial Santander)

3393: SINCO: A NOVEL STRUCTURAL REGULARIZER FOR IMAGE COMPRESSION USING

IMPLICIT NEURAL REPRESENTATIONS
Harry Gao (Washington University in St. Louis); Weijie Gan (Washington University in St. Louis); Zhixin
Sun (Washington University in St Louis); Ulugbek S. Kamilov (Washington University in St. Louis)*

4131: Zone Plate Virtual Lenses for Memory-Constrained NLOS Imaging

Pablo Luesia-Lahoz (Universidad de Zaragoza)*; Diego Gutierrez (University of Zaragoza); Adolfo Mu_oz
(U. Zaragoza)

59
4292: Fast Multiscale 3D Reconstruction Using Single-Photon LiDaR Data
Sandor Plosz (Heriot-Watt University)*; Istvan Gyongy (University of Edinburgh); Jonathan Leach (Heriot-
Watt University); Stephen McLaughlin (School of Engineering, Heriot-Watt University); Gerald S. Buller
(Heriot-Watt University); Abderrahim Halimi (Heriot-Watt university)

4478: DEEP NETWORK SERIES FOR LARGE-SCALE HIGH-DYNAMIC RANGE IMAGING

Amir Aghabiglou (Heriot Watt university)*; Matthieu Terris (Heriot-Watt University); Adrian Jackson
(EPCC, University of Edinburgh); Yves Wiaux (Heriot-Watt University)

4937: An Edge Alignment-based Orientation Selection Method for Neutron Tomography

Diyu Yang (Purdue University,); Shimin Tang (Oak Ridge National Laboratory)*; Singanallur
Venkatakrishnan (Oak Ridge National Laboratory); Mohammad Samin Nur Chowdhury (Purdue
University); Yuxuan Zhang (Oak Ridge National Laboratory); Hassina Bilheux (Oak Ridge National
Laboratory); Gregery T Buzzard (Purdue University); Charles Bouman (Purdue University)

5061: Hadamard Layer to Improve Semantic Segmentation

Angello Hoyos (Centro de Investigación en Matemáticas, A.C.)*; Mariano Rivera (Centro de Investigacion
en Matematicas AC)

5082: DEEP BORN OPERATOR LEARNING FOR REFLECTION TOMOGRAPHIC IMAGING

Qingqing Zhao (Stanford University); Yanting Ma (Mitsubishi Electric Research Laboratories, USA);
Petros Boufounos (Mitsubishi Electric Research Laboratories); Saleh Nabi (); Hassan Mansour
(Mitsubishi Electric Research Laboratories (MERL))*

5111: FACTORIZED PROJECTION-DOMAIN SPATIO-TEMPORAL REGULARIZATION FOR DYNAMIC

TOMOGRAPHY
Berk Iskender (University of Illinois at Urbana-Champaign)*; Marc L Klasky (Los Alamos National
Laboratory); Brian M Patterson (Los Alamos National Laboratory); Yoram Bresler (UIUC)

5264: ROBUST SPATIOTEMPORAL FUSION OF SATELLITE IMAGES VIA CONVEX OPTIMIZATION

Ryosuke Isono (Tokyo Institute of Technology)*; Kazuki Naganuma (Tokyo Institute of Technology);
Shunsuke Ono (Tokyo Institute of Technology)

5629: Alternating Phase Langevin Sampling with Implicit Denoiser Priors for Phase Retrieval
Rohun Agrawal (California Institute of Technology)*; Oscar Leong (California Institute of Technology)

6370: G2CNN: GEOMETRIC PRIOR BASED GCNN FOR SINGLE-VIEW 3D RECONSTRUCTION

WITH LOOP SUBDIVISION
Kun Cao (Beijing University of Technology)*; Na Qi (Beijing University of Technology); Wei Xu (Faculty of
Information Technology, Beijing University of Technology); Qing Zhu (Beijing University of Technology);
Shibo Xu (Beijing University of Technology); Changxin Pan ( Beijing University of Technology)

6475: Model-based spectral reconstruction of interferometric acquisitions

Mohamad Jouni (Grenoble INP)*; Daniele Picone (Grenoble INP); Mauro Dalla Mura (Grenoble INP)

60
 Image, Video, and Multidimensional Signal Processing

100: Counterfactual Two-stage Debiasing for Video Corpus Moment Retrieval

Sunjae Yoon (KAIST)*; Ji Woo Hong (KAIST); SooHwan Eom (KAIST); Hee Suk Yoon (KAIST); Eunseop
Yoon (KAIST); Daehyeok Kim (KAIST); Junyeong Kim (Chung-Ang University); Chanwoo Kim (Samsung
Electronics); Chang D. Yoo (KAIST)

105: Multispectral image fusion based on super pixel segmentation

Nati Ofir (Kingston University London)*

107: LEARNABLE FLOW MODEL CONDITIONED ON GRAPH REPRESENTATION MEMORY FOR

ANOMALY DETECTION
ziyu zhu (Tsinghua University)*; Wenlei Liu (Tsinghua University); ZHIDONG Deng (Tsinghua University)

110: Learning Generalizable Light Field Networks from Few Images

QIAN LI (INRIA)*; Franck Multon (INRIA); Adnane Boukhayma (INRIA)

117: Hyperspectral Image Denoising via Nonlocal Rank Residual Modeling

Zhiyuan Zha (Nanyang Technological University); Bihan Wen (Nanyang Technological University)*; Xin
Yuan (Westlake University); Jiantao Zhou (University of Macau); Ce Zhu (University of Electronic Science
& Technology of China)

138: Cross-Modality Depth Estimation via Unsupervised Stereo RGB-to-Infrared Translation

Shi Tang (Tsinghua University); Xinchen Ye (Dalian University of Technology)*; Fei Xue (Dalian University
of Technology); Rui Xu (Dalian University of Technology)

142: HTNET: HUMAN TOPOLOGY AWARE NETWORK FOR 3D HUMAN POSE ESTIMATION
Jialun Cai (Peking university)*; Hong Liu (Peking University Shenzhen Graduate School); Runwei Ding
(Peking University Shenzhen Graduate School); Wenhao Li (Peking University); Jianbing Wu (Peking
University); Miaoju Ban (Peking University )

190: LOG-CAN: LOCAL-GLOBAL CLASS-AWARE NETWORK FOR SEMANTIC SEGMENTATION OF

REMOTE SENSING IMAGES
Xiaowen Ma (Zhejiang University); Mengting Ma (Zhejiang University); Chenlu Hu (Zhejiang University);
Zhiyuan Song (Zhejiang University); Ziyan Zhao (Zhejiang University); Tian Feng (Zhejiang University;
Alibaba-Zhejiang University Joint Research Institute of Frontier Technologies)*; Wei Zhang (Zhejiang
University)

212: M2TSR: Multi-range and Mix-grained Transformer for Single Image Super-Resolution
Zhong-Han Niu (State Key Laboratory for Novel Software Technology, Nanjing University); Qinglong
Zhang (State Key Laboratory for Novel Software Technology, Nanjing University ); Yi Fan (State Key
Laboratory for Novel Software Technology, Nanjing University); Yu-Bin Yang (State Key Laboratory for
Novel Software Technology, Nanjing University)*

217: ENHANCED GM-PHD FILTER FOR REAL TIME SATELLITE MULTI-TARGET TRACKING
Camilo G Aguilar (Inria)*; Mathias Ortner (Airbus); Josiane Zerubia (n/a)

242: IMAGE COMPLETION VIA DUAL-PATH COOPERATIVE FILTERING

Pourya Shamsolmoali (East China Normal University)*; Masoumeh Zareapoor (Shanghai Jiao Tong
University); Eric Granger (ETS Montreal )

243: Hyneter: Hybrid Network Transformer for Object Detection

Dong Chen (Tongji University)*; duoqian miao (tongji university); Xuerong Zhao (Tongji University)

61
273: DEHRFormer: Real-time Transformer for Depth Estimation and Haze Removal from
Varicolored Haze Scenes
Sixiang Chen (Jimei University)*; Tian Ye (Jimei University); Shi Jun (XinJiang University); Yun Liu
(Southwest University); JingXia Jiang (jimei university); Erkang Chen (Jimei University); Peng Chen
(Jimei University)

274: MSP-Former: Multi-Scale Projection Transformer for Single Image Desnowing

Sixiang Chen (Jimei University)*; Tian Ye (Jimei University); Yun Liu (Southwest University); Tao Dong
Liao (JiMei University); JingXia Jiang (jimei university); Erkang Chen (Jimei University); Peng Chen (Jimei
University)

275: PFT-SSR: Parallax Fusion Transformer for Stereo Image Super-Resolution

Hansheng GUO (The Chinese University of Hong Kong); Juncheng Li (The Chinese University of Hong
Kong)*; Guangwei Gao (Nanjing University of Posts and Telecommunications); Zhi Li (East China Normal
University); Tieyong Zeng (The Chinese University of Hong Kong)

283: Multi-modal domain generalization for Cross-Scene Hyperspectral Image Classification

Yuxiang Zhang (Beijing Institute of Technology )*; Mengmeng Zhang (Beijing Institute of Technology); Wei
Li (Beijing Institute of Technology, Beijing, China); Ran Tao (Beijing Institute of Technology)

295: A discriminative multi-channel noise feature representation method for image manipulation
localization
yang zhou (sichuan university); Hongxia Wang (Sichuan University)*; Qiang Zeng (Sichuan University);
Rui Zhang (Sichuan University); Sijiang Meng (Sichuan University)

296: Group-wise Co-salient Object Detection with Siamese Transformers via Brownian Distance
Covariance Matching
Yang Wu (nuist); Hao Zhang (Nuist); lingyan liang (inspur); Yaqian Zhao (Inspur); Kaihua Zhang (Inspur，
NUIST)*

301: INTERWEAVED GRAPH AND ATTENTION NETWORK FOR 3D HUMAN POSE ESTIMATION
Ti Wang (Peking University Shenzhen Graduate School); Hong Liu (Peking University Shenzhen
Graduate School); Runwei Ding (Peking University Shenzhen Graduate School)*; Wenhao Li (Peking
University); Yingxuan You (Peking University); Xia Li (ETH Zurich)

302: OAFormer: Learning Occlusion Distinguishable Feature for Amodal Instance Segmentation
Zhixuan Li (Peking University); Ruohua Shi (Peking University); Tiejun Huang (Peking University);
Tingting Jiang (Peking University)*

309: OPT: One-shot Pose-Controllable Talking Head Generation

Jin Liu (1. Institute of Information Engineering,Chinese Academy of Sciences. 2. School of Cyber
Security, University of Chinese Academy of Sciences); Xi Wang (Institute of Information Engineering,
Chinese Academy of Sciences )*; Xiaomeng Fu (1. Institute of Information Engineering, Chinese
Academy of Sciences. 2. School of Cyber Security, University of Chinese Academy of Sciences); chai
yesheng (Institute of Information Engineering，Chinese Academy of Sciences); Cai Yu (1. Institute of
Information Engineering,Chinese Academy of Sciences. 2. School of Cyber Security, University of
Chinese Academy of Sciences); Jiao Dai (Institute of Information Engineering,Chinese Academy of
Sciences); Jizhong Han (Institute of Information Engineering,Chinese Academy of Sciences)

319: ProContEXT: Exploring Progressive Context Transformer for Tracking

Jin-Peng Lan (DAMO Academy, Alibaba Group); Zhi-Qi Cheng (Carnegie Mellon University); Jun-Yan He
(DAMO Academy, Alibaba Group)*; Chenyang Li (DAMO Academy, Alibaba Group); Bin Luo (DAMO
Academy, Alibaba Group); Xu Bao (DAMO Academy, Alibaba Group); Wangmeng Xiang (DAMO
Academy, Alibaba Group); Yifeng Geng (Alibaba Group); Xuansong Xie (DAMO Academy, Alibaba Group)

62
320: LongShortNet: Exploring Temporal and Semantic Features Fusion in Streaming Perception
Chenyang Li (DAMO Academy, Alibaba Group); Zhi-Qi Cheng (Carnegie Mellon University); Jun-Yan He
(DAMO Academy, Alibaba Group); Pengyu Li (Alibaba Group); Bin Luo (DAMO Academy, Alibaba
Group)*; Hanyuan Chen (Alibaba); Yifeng Geng (Alibaba Group); Jin-Peng Lan (DAMO Academy, Alibaba
Group); Xuansong Xie (DAMO Academy, Alibaba Group)

326: RAISING THE LIMIT OF IMAGE RESCALING USING AUXILIARY ENCODING

Chenzhong Yin (University of Southern California); Zhihong Pan (Baidu Research (USA))*; Xin Zhou
(Baidu USA); Le Kang (Baidu Research); Paul Bogdan (USC)

335: Jointly Visual- and Semantic-Aware Graph Memory Networks for Temporal Sentence
Localization in Videos
Daizong Liu (Peking University)*; Pan Zhou (Huazhong University of Science and Technology)

337: Enhancing Multimodal Alignment with Momentum Augmentation for Dense Video Captioning
yiwei wei (Tianjin university)*; Shaozu Yuan (JD AI ); Meng Chen (JD AI); Longbiao Wang (Tianjin
University)

347: Flow-Guided Deformable Alignment Network with Self-Supervision for Video Inpainting
Zhiliang Wu (Nanjing University of Science and Technology)*; Kang Zhang (Nanjing University of Science
and Technology); Changchang Sun (Illinois Institute of Technology); Hanyu Xuan (Anhui University); Yan
Yan (Illinois Institute of Technology)

362: A Flow-Guided Non-Local Alignment Network for Video Compressive Sensing Reconstruction
Chao Zhou (Nanjing University of Posts and Telecommunications)*; Can Chen (Nanjing University of
Posts and Telecommunications); Dengyin Zhang (School of Internet of Things Nanjing University of Posts
and Telecommunications Nanjing, China)

372: Saliency-Driven Hierarchical Learned Image Coding for Machines

Kristian Fischer (Friedrich-Alexander-Univerity Erlangen-Nürnberg)*; Fabian Brand (Friedrich-Alexander
University Erlangen-Nürnberg (FAU)); Christian Blum (Friedrich-Alexander University Erlangen-Nürnberg
(FAU)); Andre Kaup (Friedrich-Alexander-Universität Erlangen-Nürnberg)

375: Tracking Objects and Activities with Atention for Temporal Sentence Grounding
Zeyu Xiong (Huazhong University of Science and Technology)*; Daizong Liu (Peking University); Pan
Zhou (Huazhong University of Science and Technology); Jiahao Zhu (Huazhong University of Science
and Technology)

377: LEARNING SCENE FLOW FROM 3D POINT CLOUDS WITH CROSS-TRANSFORMER AND
GLOBAL MOTION CUES
Mingliang Zhai (Nanjing University of Posts and Telecommunications)*; Kang Ni (Nanjing University of
Posts and Telecommunications); Jiucheng Xie (Nanjing University of Posts and Telecommunications);
Hao Gao (Nanjing University of Posts and Telecommunications)

379: SPIKE-BASED OPTICAL FLOW ESTIMATION VIA CONTRASTIVE LEARNING

Mingliang Zhai (Nanjing University of Posts and Telecommunications)*; Kang Ni (Nanjing University of
Posts and Telecommunications); Jiucheng Xie (Nanjing University of Posts and Telecommunications);
Hao Gao (Nanjing University of Posts and Telecommunications)

380: CROSS-MODAL OPTICAL FLOW ESTIMATION VIA MODALITY COMPENSATION AND

ALIGNMENT
Mingliang Zhai (Nanjing University of Posts and Telecommunications)*; Kang Ni (Nanjing University of
Posts and Telecommunications); Jiucheng Xie (Nanjing University of Posts and Telecommunications);
Hao Gao (Nanjing University of Posts and Telecommunications)

63
382: MovieNet-PS: A Large-Scale Person Search Dataset in the Wild
Jie Qin (Nanjing University of Aeronautics and Astronautics)*; Peng Zheng (NUAA, MBZUAI, Aalto
University); Yichao Yan (Shanghai Jiao Tong University); Rong Quan (Nanjing University of Aeronautics
and Astronautics); Xiaogang CHENG (Nanjing University of Posts and Telecommunications); Bingbing Ni
(Shanghai Jiao Tong University)

388: SELF-SUFFICIENT FRAMEWORK FOR CONTINUOUS SIGN LANGUAGE RECOGNITION

Youngjoon Jang (KAIST)*; Youngtaek Oh (KAIST); Jae Won Cho (KAIST); Myungchul Kim (KAIST);
Dong-Jin Kim (Hanyang University); In So Kweon (KAIST); Joon Son Chung (KAIST)

396: DPTNet: A Dual-Path Transformer Architecture for Scene Text Detection

Jingyu Lin (厦门大学); Yan Yan (Xiamen University); Hanzi Wang (Xiamen University)*

398: Subspace Modeling enabled High-sensitivity X-ray Chemical Imaging

Jizhou Li (City University of Hong Kong)*; Bin Chen (Max-Planck-Institut für Informatik); Guibin Zan
(Stanford University); Guannan Qian (Stanford University); Piero Pianetta (Stanford University); Yijin Liu
(SLAC National Accelerator Laboratory)

403: Multistage Spatial Context Models for Learned Image Compression

Fangzheng Lin (Waseda University)*; Heming Sun (Waseda University, Japan); Jinming Liu (Shanghai
Jiao Tong University); Jiro Katto (Waseda University)

406: WUDA: Unsupervised Domain Adaptation Based on Weak Source Domain Labels
Shengjie Liu (Beijing University of Posts and Telecommunications)*; Chuang Zhu (Beijing University of
Posts and Telecommunications ); Yuan Li (Peking University); Wenqi Tang (Beijing University of Posts
and Telecommunications)

413: SR-init: An Interpretable Layer Pruning Method

Hui Tang (Zhejiang University of Technology); Yao Lu (Zhejiang University of Technology); Qi Xuan
(Zhejiang University of Technology)*

437: Dual-Feature Enhancement for Weakly Supervised Temporal Action Localization

Siying Liu (University of Science and Technology of China); Qiankun Liu (Beijing Institute of Technology);
Qi Chu (University of Science and Technology of China)*; Bin Liu (University of Science and Technology
of China); Nenghai Yu (University of Science and Technology of China)

438: CORSD: Class-Oriented Relational Self Distillation

Muzhou Yu (Xi'an Jiaotong University)*; Sia Huat Tan (Tsinghua University); Kailu Wu (Tsinghua
University); Runpei Dong (Xi'an Jiaotong University); Linfeng Zhang (Tsinghua University ); Kaisheng Ma
(Tsinghua University )

450: I-Tuning: Tuning Frozen Language Models with Image for Lightweight Image Captioning
Ziyang Luo (Hong Kong Baptist University)*; Zhipeng Hu (NetEase Fuxi AI Lab); Yadong Xi (Fuxi AI Lab,
Netease Inc.); Rongsheng Zhang (Fuxi AI Lab, Netease Inc.); Jing Ma (Hong Kong Baptist University)

453: Towards Reliable Image Outpainting: Learning Structure-Aware Multimodal Fusion with
Depth Guidance
Lei Zhang (Beijing Jiaotong University); Chunyu Lin (Beijing Jiaotong University)*; Kang Liao (Beijing
Jiaotong University); Yao Zhao (Beijing Jiaotong University)

476: Learning to Reconnect Interrupted Trajectories for Weakly Supervised Multi-Object Tracking
Yu-Lei Li (Xiamen University); Yang Lu (Xiamen University); Jie Li (Xidian University); Hanzi Wang
(Xiamen University)*

64
490: PRIME: 3D Human Pose and Body Shape Recovery with Perspective Projection
Baobei Xu (Hikvision Research Institute )*; Shukai Fang (Hikvision Research Institute); Zhaoyang Li
(Hikvision Research Institute); Shicai Yang (Hikvision Research Institute); Di Xie (Hikvision Research
Institute); Shiliang Pu (Hikvision Research Institute)

498: A parallel attention mechanism for image manipulation detection and localization
Qiang Zeng (Sichuan University); Hongxia Wang (Sichuan University)*; yang zhou (sichuan university);
Rui Zhang (Sichuan University); Sijiang Meng (Sichuan University)

528: MABNet: Master Assistant Buddy Network with Hybrid Learning for Image Retrieval
Rohit Agarwal (UiT The Arctic University of Norway, Tromsø)*; Gyanendra Das (Indian Institute of
Technology, Dhanbad); Saksham Aggarwal (IIT (ISM) Dhanbad); Alexander Horsch (UiT The Arctic
University of Norway); Dilip K Prasad (UiT The Arctic University of Norway)

530: EMCLR: Expectation Maximization Contrastive Learning Representations

Meng Liu ( Shanghai Jiao Tong University)*; Ran Yi (Shanghai Jiao Tong University); Lizhuang Ma
(Shanghai Jiao Tong University)

553: HPFTN: Hierarchical Progressive Fusion Transformer Network for Video Denoising
Shuaitao Zhang (Hikvision Research Institute); Yuan Zhang (Hikvision Research Institute); Zheng Zhao
(Hikvision Research Institute); Di Xie (Hikvision Research Institute); Shiliang Pu (Hikvision Research
Institute)*

555: Class-Aware Contextual Information for Semantic Segmentation

Huadong Tang (University of Technology Sydney); Youpeng Zhao (University of Central Florida); yingying
jiang ( Samsung Research China,Beijing); Zhuoxin Gan (Samsung Research Institute China-Beijing
(SRC-B);); Qiang Wu (University of Technology Sydney)*

564: MRNet: Multi-Refinement Network for Dual-pixel Images Defocus Deblurring

dafeng zhang (Samsung Research China – Beijing (SRCB))*; Xiaobing Wang (Samsung Research
China-Beijing); Zhezhu Jin (Samsung Research Institute China – Beijing (SRC-B))

575: Building Change Detection using Cross-temporal Feature Interaction Network

Yuchao Feng (Zhejiang University of Technology)*; jiawei jiang (zhejiang university of technology);
Honghui Xu (Zhejiang University of Technology); Jianwei Zheng (Zhejiang University of Technology)

577: Deformable cross attention for learning optical flow

Rokia Mohsen Abdein (Harbin Engineering University); Xuezhi Xiang (Harbin Engineering University)*;
Ning Lv (Harbin Engineering University); Abdulmotaleb EI Saddik (University of Ottawa)

613: One-shot Action Detection via Attention Zooming In

He-Yen Hsieh (Academia Sinica); Ding-Jie Chen (Academia Sinica)*; Cheng-Wei Chang (Academia
Sinica); Tyng-Luh Liu (Academia Sinica)

619: ScaleMix: Intra- and inter-layer multiscale feature combination for change detection
Rui Huang (Civil Aviation University of China)*; Qingyi Zhao (Civil Aviation University of China); Ruofei
Wang (Civil Aviation University of China); Caihua Liu (College of Computer Science and Technology, Civil
Aviation University of China); Sihua Gao (Civil Aviation University of China); yuxiang zhang (Civil Aviation
University of China); Wei Fan (Civil Aviation University of China)

620: Semantic-Preserving Augmentation For Robust Image-Text Retrieval

Sunwoo Kim (Seoul National University)*; Kyuhong Shim (Seoul National University); Luong Trung
Nguyen (Seoul National University); Byonghyo Shim (Seoul National University)

65
642: Efficient Feature Fusion for Learning-based Photometric Stereo
Yakun Ju (The Hong Kong Polytechnic University)*; Kin-Man Lam (The Hong Kong Polytechnic
University); Jun Xiao (The Hong Kong Polytechnic University); Cong Zhang (The Hong Kong Polytechnic
University); Cuixin Yang (The Hong Kong Polytechnic University); Junyu Dong (Ocean University of
China)

653: RETIFORMER: RETINEX-BASED ENHANCEMENT IN TRANSFORMER FOR LOW-LIGHT

IMAGE
Junxiang Ruan (Tsinghua University)*; Xiangtao Kong (SIAT); Wenqi Huang (China southern power grid);
Wenming Yang (Tsinghua University)

658: EXPLORATION INTO TRANSLATION-EQUIVARIANT IMAGE QUANTIZATION

Woncheol Shin (Korea Advanced Institute of Science and Technology, KAIST)*; Gyubok Lee (KAIST);
Jiyoung Lee (KAIST); Eunyi Lyou (Seoul national university); Joonseok Lee (Google Research & Seoul
National University); Edward Choi (KAIST)

660: SELF-SUPERVISED AUDIO-VISUAL SPEECH REPRESENTATIONS LEARNING BY

MULTIMODAL SELF-DISTILLATION
Jing-Xuan Zhang (University of Science and Technology of China)*; Genshun Wan (University of Science
and Technology of China); Zhen-Hua Ling (University of Science and Technology of China); Jia Pan
(iFlytek Research); Jianqing Gao (iFLYTEK); Cong Liu (iFLYTEK Research)

665: Continuous Learning for Blind Image Quality Assessment with Contrastive Transformer
Jifan Yang (National Engineering Research Center for Multimedia Software, School of Computer Science,
Wuhan University)*; Zhongyuan Wang (Wuhan University); Baojin Huang (National Engineering Research
Center for Multimedia Software, School of Computer Science, Wuhan University); Lianbing Deng
(Guangdong-Macau Joint Laboratory for Advanced and Intelligent Computing)

670: Composition of Motion From Video Animation Through Learning Local Transformations
Michalis Vrigkas (University of Western Macedonia)*; Virginia Tagka (University of Ioannina); Marina
Plissiti (University of Ioannina); Christophoros Nikou (University of Ioannina)

698: Encoder-Decoder Graph Convolutional Network for Automatic Timed-Up-and-Go and Sit-to-
Stand Segmentation
Bo Wen (University of California, San Diego)*; Chen Du (University of California, San Diego); Truong
Nguyen (UC San Diego)

707: Learnt Mutual Feature Compression for Machine Vision

Tie Liu (BUAA); Mai Xu (BUAA); Shengxi Li (Beihang University)*; Chaoran Chen (Beihang University); Li
Yang (Beihang university); Zhuoyi Lv (vivo)

711: BOOSTING PERSON RE-IDENTIFICATION WITH VIEWPOINT CONTRASTIVE LEARNING AND

ADVERSARIAL TRAINING
Xingyue Shi (Peking University Shenzhen Graduate School); Hong Liu (Peking University Shenzhen
Graduate School)*; Wei Shi (Peking University Shenzhen Graduate School); Zihui Zhou (Peking
University, Shenzhen Graduate School); Yidi Li (Peking University Shenzhen Graduate School)

736: LOGOVIT: LOCAL-GLOBAL VISION TRANSFORMER FOR OBJECT RE-IDENTIFICATION

Phan Nguyen (VinBrain)*; Ta Duc Huy (Vinbrain); Soan T. M. Duong (Le Quy Don Technical University/
VinBrain JSC); Nguyen Hoang Tran (VinBrain); Sam Bao Tran (Vinbrain); Dao Huu Hung (VinBrain);
Chanh D Tr Nguyen (VinBrain); Trung Bui (Individual); QUOC HUNG TRUONG (VINBRAIN)

737: Semantics-Guided Object Removal for Facial Images: with Broad Applicability and Robust
Style Preservation
Jookyung Song (Seoul National University )*; Yeonjin Chang (Seoul National University); SeongUk Park
(Seoul National University); Nojun Kwak (Seoul National University)

66
746: Context-Aware Face Clustering with Graph Convolutional Networks
dafeng zhang (Samsung Research China – Beijing (SRCB))*; Jiangbo Guo (Samsung Research China –
Beijing (SRCB)); Zhezhu Jin (Samsung Research Institute China – Beijing (SRC-B))

748: A Lightweight Convolutional Neural Network Using Feature Filtering Module

Nan Jing ( Inner Mongolia University)*; Yu Zhang (Inner Mongolia University )

758: Meta++ Network for Few-shot Aerospace Crack Segmentation

Chengyuan Xu (Northwestern Polytechnical University)*; Kang Liu (Northwestern Polytechnical
University); Xuelong Li (Northwestern Polytechnical University)

772: HYPERNETWORK-BASED ADAPTIVE IMAGE RESTORATION

Gil Ben-Artzi (Ariel University)*; Shai S.Y Aharon (Ariel University)

776: VISION2TOUCH: IMAGING ESTIMATION OF SURFACE TACTILE PHYSICAL PROPERTIES

Jie Chen (Hunan University); ZHOU SHIZHE (Hunan University)*

803: Image Generation is MAY All You Need for VQA

Kyung Ho Kim (ActionPower)*; Junseo Lee (ActionPower); Jihwa Lee (ActionPower)

812: TOP-K VISUAL TOKENS TRANSFORMER: SELECTING TOKENS FOR VISIBLE-INFRARED

PERSON RE-IDENTIFICATION
Bin Yang (Wuhan University)*; Jun Chen (Wuhan University); Mang Ye (Wuhan University)

872: Nested Attention Network with Graph Filtering for Visual Question and Answering
Jing Lu (China University of Petroleum (East China)); Chunlei Wu (China University Of Petroleum(East
China))*; Leiquan Wang (UPC); Shaozu Yuan (UPC); Jie Wu (China University Of Petroleum)

889: SEMANTICS-AWARE GAMMA CORRECTION FOR UNSUPERVISED LOW-LIGHT IMAGE

ENHANCEMENT
Yu-Hsuan Chen (National Taiwan University)*; Fu-Cheng Pan (National Taiwan University); Yu-Chien Liao
(National Taiwan University); Jao-Hong Kao (novatek inc.); Yu-Chiang Frank Wang (National Taiwan
University)

890: ST360IQ: No-Reference Omnidirectional Image Quality Assessment with Spherical Vision
Transformers
Nafiseh Jabbari Tofighi (Koc University)*; Mohamed Hedi elfkir (hacettepe university); Nevrez Imamoglu
(AIST); Cagri Ozcinar (Samsung); Erkut Erdem (Hacettepe University); Aykut Erdem (Koc University)

907: Data-aware Zero-shot Neural Architecture Search for Image Recognition

Yi Fan (State Key Laboratory for Novel Software Technology, Nanjing University); Zhong-Han Niu (State
Key Laboratory for Novel Software Technology, Nanjing University); Yu-Bin Yang (State Key Laboratory
for Novel Software Technology, Nanjing University)*

908: STRUCTURE-PRESERVING AND REDUNDANCY-FREE FEATURES REFINEMENT FOR

GENERALIZED ZERO-SHOT LEARNING
Jian Ni (University of Science and Technology of China)*; Yong Liao (University of Sciences and
Technology of China)

914: Depth Estimation for a Single Omnidirectional Image with Reversed-gradient Warming-up
Thresholds Discriminator
Yihong Wu (University of Southampton)*; Yuwen Heng (University of Southampton); Mahesan Niranjan
(University of Southampton); Hansung Kim (University Of Southampton)

67
916: A Template Matching Approach for Reference Picture Padding in Video Coding
Nicolas Horst (Institute of Imaging & Computer Vision, RWTH Aachen University)*; Priyanka Das (RWTH
Aachen University, Germany); Mathias Wien (RWTH Aachen University, Germany)

932: SINE: SIMILARITY-REGULARIZED INTRA-CLASS EXPLOITATION FOR CROSS-GRANULARITY

FEW-SHOT LEARNING
Jinhai Yang (Shanghai Jiao Tong University)*; Hua Yang (Shanghai Jiao Tong University)

940: Deep Quantigraphic Image Enhancement via Comparametric Equations

Xiaomeng Wu (NTT Corporation)*; Yongqing Sun (NTT, Japan); Akisato Kimura (NTT Communication
Science Laboratories)

972: VIDEO CAPTIONING VIA RELATION-AWARE GRAPH LEARNING

Yi Zheng (Fudan University); Heming Jing (Fudan University); Qiujie Xie (School of Computer Science,
Fudan University); Yuejie Zhang (Fudan University)*; Rui Feng (Fudan University); Tao Zhang (Shanghai
University of Finance and Economics); Shang Gao (Deakin University)

997: A Spatio-Temporal Decomposition Network for Compressed Video Quality Enhancement

Kai Wang (Hikvision Research Institute)*; Fangdong Chen (Hikvision Research Institute); Zongmiao Ye
(Hikvision Research Institute); Li Wang (Hikvision Research Institute); xiaoyang wu (Hikvision Research
Institute); Shiliang Pu (Hikvision Research Institute)

998: A Physically Explainable Framework for Human-Related Anomaly Detection

Yalong Jiang (Beihang University)*; huining Li (Beihang University); changkang li (Beihang University)

1014: TransLink: Transformer-based Embedding for Tracklets' Global Link

Yanting Zhang (Donghua University)*; Shunghong Wang (Donghua University); Yuxuan Fan (Donghua
University); Gaoang Wang (Zhejiang University); Cairong Yan (Donghua University)

1015: Burst Perception-Distortion Tradeoff: Analysis and Evaluation

Danna Xue (Northwestern Polytechnical University)*; Luis Herranz (Computer Vision Center); Javier
Vazquez-Corral (Autonomous University of Barcelona); Yanning Zhang (Northwestern Polytechnical
University)

1031: ESTIMATION OF VISUAL CONTENTS FROM HUMAN BRAIN SIGNALS VIA VQA BASED ON
BRAIN-SPECIFIC ATTENTION
Ryo Shichida (Hokkaido University)*; Ren Togo (Hokkaido University); Keisuke Maeda (Hokkaido
University); Takahiro Ogawa (Hokkaido University); Miki Haseyama (Hokkaido University)

1033: COMBINING THE SILHOUETTE AND SKELETON DATA FOR GAIT RECOGNITION
Likai Wang (Tianjin University)*; Ruize Han (College of Intelligence and Computing, Tianjin University);
Wei Feng (College of Intelligence and Computing, Tianjin University, China)

1041: Robust Video Anomaly Detection Framework via Prior Knowledge and Multi-Path Frame
Prediction
Menghao Zhang (Beijing University of Posts and Telecommunications)*; Jingyu Wang (Beijing University
of Posts and Telecommunications); Jing Wang (Beijing University of Posts and Telecommunications); Qi
Qi (Beijing University of Posts and Telecommunications); Zirui Zhuang (Beijing University of Posts and
Telecommunications); Haifeng Sun (Beijing university of posts and telecommunications); Ning Xiao (Didi
Chuxing)

1056: HIERARCHICAL TRANSFORMER FOR MULTI-LABEL TRAILER GENRE CLASSIFICATION

Zihui Cai (School of Cyber Science and Engineering, Wuhan University)*; Hongwei Ding (School of Cyber
Science and Engineering, Wuhan University); Xuemeng Wu (School of Cyber Science and Engineering,
Wuhan University); Mohan Xu (School of Cyber Science and Engineering, Wuhan University); Xiaohui
Cui (School of Cyber Science and Engineering, Wuhan University)

68
1077: PCSalMix: Gradient Saliency-based Mix Augmentation for Point Cloud Classification
Tao Hong (Peking University)*; Zeren Zhang (Peking University); Jinwen Ma (Peking University)

1107: Improving Occluded Human Pose Estimation via Linked Joints

Suhang Ye (Xiamen University)*; Zebo Hong (Xiamen University); Jiawen Zheng (Xiamen University);
ShengChuan Zhang (Xiamen University)

1119: Binary Image Fast Perfect Recovery From Sparse 2D-DFT Coefficients
Soo-Chang Pei (Department of Electrical Engineering, National Taiwan University); Kuo-Wei Chang
(Chunghwa Telecom)*

1132: SEMI-SUPERVISED SEMANTIC SEGMENTATION WITH STRUCTURED OUTPUT SPACE

ADAPTION
Weiquan Huang (Northeastern University(China)); Fu Zhang (Northeastern University)*

1139: Learning from the raw domain: cross modality distillation for compressed video action
recognition
Yufan Liu (Institute of Automation, Chinese Academy Sciences)*; Jiajiong Cao (Ant Financial Service
Group); Weiming Bai (Chinese Academy of Sciences); Bing Li (National Laboratory of Pattern
Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences); Weiming Hu (Institute of
Automation，Chinese Academy of Sciences)

1157: Decontamination Transformer for Blind Image Inpainting

Chun-Yi Li (National Chiao Tung University)*; Yen-Yu Lin (National Yang Ming Chiao Tung University);
Wei-Chen Chiu (National Chiao Tung University)

1170: PRRD: PIXEL-REGION RELATION DISTILLATION FOR EFFICIENT SEMANTIC

SEGMENTATION
Chen Wang (Chongqing University)*; Jiang Zhong (); Qizhu Dai (Chongqing University); yafei qi (Central
South University); Rongzhen Li (Chongqing University); Qin Lei (Chongqing University); BIN FANG
(Chongqing University); Xue Li (University of Queensland)

1175: HQP-MVS:A HIGH-QUALITY PLANE PRIOR ASSISTED MULTI-VIEW STEREO FOR LOW-
TEXTURED AREA
zefan tian (peking university)*; Rongjie Wang (PCL); Zhenyu Wang (Shenzhen Graduate School, Peking
University); Ronggang Wang (Peking University)

1192: Improving Image Captioning with Control Signal of Sentence Quality

Zhangzi Zhu (University of Electronic Science and Technology of China)*; shuai Wang (University of
Electronic Science and Technology of China); Hong Qu (University of Electronic Science and Technology
of China)

1211: UNCER2NATURAL: UNCERTAINTY-AWARE UNSUPERVISED IMAGE DENOISING

Chenyu Huang (Fudan University); Weimin Tan (Fudan University); Jiaxing Shi (Fudan University); Zhen
Xing (Fudan University); Bo Yan (Fudan University)*

1236: S3I-POINTHOP: SO(3)-INVARIANT POINTHOP FOR 3D POINT CLOUD CLASSIFICATION

Pranav A Kadam (University of Southern California)*; Handrik Prajapati (University of Souther California);
Min Zhang (University of Southern California); Jinjang Xue (University of Southern California); Shan Liu
(Tencent America); C.-C. Jay Kuo (USC)

1242: SANet: Spatial Attention Network with Global Average Contrast Learning for Infrared Small
Target Detection
Jiewen Zhu (UESTC); Shengjia Chen (University of Electronic Science and Technology of China); lexiao li
(UESTC); Luping Ji (UESTC)*

69
1267: Two-stream Decoder Feature Normality Estimating Network for Industrial Anomaly Detection
Chaewon Park (Yonsei University)*; Minhyeok Lee ( Yonsei University); Suhwan Cho (Yonsei University);
Donghyeong Kim (Yonsei University); Sangyoun Lee (Yonsei University)

1279: MODIFY: Model-driven Face Stylization without Style Images

Yuhe Ding ( Institute of Automation, Chinese Academy of Sciences )*; Jian Liang (CASIA); Jie Cao
(Institute of Automation, Chinese Academy of Sciences); Aihua Zheng (Anhui University); Ran He
(Institute of Automation, Chinese Academy of Sciences)

1291: Towards Making a Trojan-horse Attack on Text-to-Image Retrieval

Fan Hu (Renmin University of China); Aozhu Chen (Renmin University of China); Xirong Li (Renmin
University of China)*

1302: Sample-aware Knowledge Distillation for Long-tailed Learning

Shanshan Zheng (Xiamen University); Yachao Zhang (Tsinghua University); Yanyun Qu (XMU)*; hongyi
huang (XMU)

1303: A3S: ADVERSARIAL LEARNING OF SEMANTIC REPRESENTATIONS FOR SCENE-TEXT

SPOTTING
Masato Fujitake (Fast accounting co., ltd.)*

1310: A novel Cross-Component Context Model for End-to-End Wavelet Image Coding
Anna Meyer (Friedrich-Alexander-Universität Erlangen-Nürnberg)*; Andre Kaup (Friedrich-Alexander-
Universität Erlangen-Nürnberg)

1322: Vision Transformer-based Feature Extraction for Generalized Zero-Shot Learning

Jiseob Kim (Seoul National University)*; Kyuhong Shim (Seoul National University); Junhan Kim (Seoul
National University); Byonghyo Shim (Seoul National University)

1335: DivCon: Learning Concept Sequences for Semantically Diverse Image Captioning
Yue Zheng (Tsinghua University)*; Ya-Li Li (Tsinghua University); Shengjin Wang (Tsinghua University)

1380: Solving Jigsaw Puzzle of Large Eroded Gaps Using Puzzlet Discriminant Network
Xingke Song (University of Nottingham Ningbo China); Xiaoying YANG (University of Nottingham Ningbo
China); Jianfeng Ren (University of Nottingham Ningbo China)*; RUIBIN BAI (University of Nottingham );
Xudong Jiang (Nanyang Technological University)

1412: ONE-SHOT NEURAL BAND SELECTION FOR SPECTRAL RECOVERY

Hai-Miao Hu (Beihang Univeristy); Zhenbo Xu (Hangzhou Innovation Institute, Beihang University,
Hangzhou, China); Wenshuai Xu (School of Software, Beihang University)*; You Song (Beihang
University); YiTao Zhang (Hangzhou Innovation Institute, Beihang University, Hangzhou, China); Liu Liu
(Hangzhou ShiFang Technology Inc.); Zhilin Han (shifang); Ajin Meng (ShiFang Technology Inc.)

1431: Kernel estimation and deconvolution for blind image super-resolution

Jiali Gong (East China Normal University)*; Hongfan Gao (East China Normal University); Jiahao Chao
(East China Normal University); Zhou Zhou (East China Normal University); Zhengfeng Yang (East China
Normal University); Zhenbing Zeng (Shanghai University)

1437: DUAL META CALIBRATION MIX FOR IMPROVING GENERALIZATION IN META-LEARNING

Ze-Yu Mi (Nanjing university); Yu-Bin Yang (State Key Laboratory for Novel Software Technology, Nanjing
University)*

70
1446: Infrared and visible image fusion by using multi-scale transformation and fractional-order
gradient information
Shiwei Wu (Nanjing University of Science and Technology); Kang Zhang (Nanjing University of Science
and Technology); Xia Yuan (Nanjing University of Science and Technology)*; ChunXia Zhao (Nanjing
university of science and technology)

1470: SEMI-SUPERVISED REMOTE SENSING IMAGE CHANGE DETECTION USING MEAN

TEACHER MODEL FOR CONSTRUCTING PSEUDO-LABELS
mao zan (ucas)*; xinyu tong (Computer Network Information Center); Ze Luo (Computer Network
Information Center, Chinese Academy of Sciences)

1473: SAR IMAGE DESPECKLING WITH RESIDUAL-IN-RESIDUAL DENSE GENERATIVE

ADVERSARIAL NETWORK
Yunpeng Bai (Aberystwyth University)*; Yayuan Xiao (Northwestern Polytechnical University); Xuan Hou
(aberystwyth university); Ying Li (Northwestern Polytechnical University); Chaangjing Shang (Aberystwyth
University); Qiang Shen (Aberystwyth University )

1478: CLMAE: a liter and faster Masked Autoencoders

Yiran Song (Shanghai Jiao Tong University)*; Lizhuang Ma (Shanghai Jiao Tong University)

1496: ROI-BASED DEEP IMAGE COMPRESSION WITH SWIN TRANSFORMERS

Binglin Li (Simon Fraser University)*; Jie Liang (Simon Fraser University); Haisheng Fu (Xi'an Jiaotong
University); Jingning Han (Google Inc.)

1514: LEARNED VIDEO CODING WITH MOTION COMPENSATION MIXTURE MODEL

Khanh Quoc Dinh (Samsung Research)*; Kwang Pyo Choi (Samsung Electronics)

1528: Visual-Aware Text-to-Speech

Mohan Zhou (Harbin Institute of Technology)*; Yalong Bai (JD AI Research); Wei Zhang (JD AI
Research); Ting Yao (JD AI Research); Tiejun Zhao (Harbin Institute of Technology); Tao Mei (AI
Research of JD.com)

1553: Learning Hybrid Representations of Semantics and Distortion for Blind Image Quality
Assessment
Xiaoqi Wang (Nanjing University of Posts and Telecommunications); Jian Xiong (Nanjing Univeristy of
Posts and Telecommunications)*; Bo Li (Xihua University); Jinli Suo (Tsinghua University); Hao Gao
(Nanjing University of Posts and Telecommunications)

1554: Affinity Learning with Blind-spot Self-Supervision for Image Denoising

Yuhongze Zhou (McGill University)*; Liguang Zhou (The Chinese University of Hong Kong, Shenzhen);
Issam Hadj Laradji (ServiceNow); Tin Lun Lam (The Chinese University of Hong Kong, Shenzhen);
Yangsheng Xu (Shenzhen Institute of Artificial Intelligence and Robotics for Society)

1555: A Comprehensive Comparison of Projections in Omnidirectional Super-Resolution

Huicheng Pi (Beijing Jiaotong University); Ming Lu (Intel Labs China)*; Senmao Tian (Beijing Jiaotong
University); Jiaming Liu (Peking University); Yandong Guo (OPPO Research Institute); Shunli Zhang
(Beijing Jiaotong University)

1561: Efficient Online Convolutional Dictionary Learning Using Approximate Sparse Components
Farshad G Veshki (Aalto university)*; Sergiy A. Vorobyov (Aalto University)

71
1562: Laryngeal Leukoplakia Classification via Dense Multiscale Feature Extraction in White Light
Endoscopy Images
Zhenzhen You (Xi'an University of Technology)*; Yan Yan (Second Affiliated Hospital of Medical College,
Xi'an Jiaotong University); Zhenghao Shi (.School of Computer Science and Engineering，Xi’an
University of Technology); Minghua Zhao (Xi'an University of Technology); Jing Yan (Second Affiliated
Hospital of Medical College, Xi'an Jiaotong University); Haiqin Liu (Second Affiliated Hospital of Medical
College, Xi'an Jiaotong University); Xinhong Hei (Xi'an University of Technology); Xiaoyong Ren (Second
Affiliated Hospital of Medical College, Xi'an Jiaotong University)

1568: Contrastive Domain Adaptation via Delimitation Discriminator

Xing Wei (Hefei University of Technology); bin wen (Hefei University of Technology)*; Lei Chen (Institute
of Intelligent Machines, HFIPS, Chinese Academy of Sciences); Yujie Liu (Hefei University of
Technology); Chong Zhao (HeFei University of Technology); Yang Lu (Hefei University of Technology)

1575: MODULATION-BASED CENTER ALIGNMENT AND MOTION MINING FOR SPATIAL

TEMPORAL ACTION DETECTION
Weiji Zhao (Shanghai Jiao Tong University)*; KeFeng Huang (Shanghai Jianke Engineering Consulting
Co.,Ltd); Chongyang Zhang (Shanghai Jiao Tong University)

1580: MHSCNet: A Multimodal Hierarchical Shot-aware Convolutional Network for Video

Summarization
Wujiang Xu (Xi'an Jiaotong University); Runzhong Wang (Shanghai Jiao Tong University); xiaobo guo
(antgroup)*; Shaoshuai Li (Ant Group); Qiongxu Ma (Ant Group); Yunan Zhao (Ant Group); Sheng Guo
(Ant Group); Zhenfeng Zhu (bjtu); Junchi Yan (Shanghai Jiao Tong University)

1584: Two-Stage Video De-raining with Spatio-Temporal Fusion and Illumination-Invariant Detail
Preservation
Yufeng Tan (South China University of Technology)*; Youjun Xiang ( South China University of
Technology); Lei Cai (South China University of Technology); Pengcheng Wang (South China University
of Technology); Ying Zhang (South China University of Technology); Yuli Fu (South China University of
Technology)

1585: AugTarget Data Augmentation for Infrared Small Target Detection

Shengjia Chen (University of Electronic Science and Technology of China); Jiewen Zhu (UESTC); Luping
Ji (UESTC)*; Hongjun Pan (Sichuan University); Yuhao Xu (Sichuan University)

1591: DQFORMER: DYNAMIC QUERY TRANSFORMER FOR LANE DETECTION

Hao Yang (Xiamen University); Shuyuan Lin (Jinan University); Runqing Jiang (Xiamen University); Yang
Lu (Xiamen University); Hanzi Wang (Xiamen University)*

1599: Lightweight Portrait Segmentation via Edge-optimized Attention

Xinyue Zhang (Qingdao university); Guodong Wang (Qingdao University)*; Lijuan Yang (Hisense Visual
Technology Co., Ltd); Chenglizhao Chen (China University of Petroleum (East China))

1627: GOP-based Latent Refinement for Learned Video Coding

Mohsen Abdoli (IRT b-com)*; Gordon Clare (IRT b-com); Felix E Henry (Orange)

1646: GAITCOTR: improved spatial-temporal representation for gait recognition with a hybrid
convolution-transformer framework
Jingqi Li (Fudan University); Yuzhen Zhang (Fudan University); Hongming Shan (Fudan University);
Junping Zhang (Fudan University)*

1651: Mutual Information based Reweighting for Precipitation Nowcasting

Yuan Cao (Fudan University)*; Danchen Zhang (Pittsburgh University); Xin Zheng (Fudan University);
Hongming Shan (Fudan University); Junping Zhang (Fudan University)

72
1670: Line segment matching based on intersection-enhanced point correspondences
Zhiyu Liu (School of Computer Science and Technology, Soochow University); Baojiang Zhong (School of
Computer Science and Technology, Soochow University)*

1675: Deep learning-based stereo camera multi-video synchronization

Nicolas Boizard (University Of Mons)*; Kevin El Haddad (University of Mons/The Big Projects); Thierry
Ravet (UMONS); Francois Cresson (UMONS); Thierry Dutoit (University of Mons)

1680: Instance-Aware Hierarchical Structured Policy for Prompt learning in Vision-Language

Models
Xun Wu (school of software, tsinghua university); Guolong Wang (University of International Business and
Economics); Zhaoyuan Liu (Qilu University of Technology (Shandong Academy of Sciences)); Xuan Dang
(Tsinghua University); Zheng Qin (Tsinghua University)*

1721: Facial Texure Perceiver: Towards High-Fidelity Facial Texture Recovery with Input-Level
Inductive Biased Perceiver IO
Seungeun Lee (UNIST)*

1729: Exploring instance relation for decentralized multi-source domain adaptation

Yikang Wei (Tianjin University)*; Yahong Han (Tianjin University)

1759: DEWARPING DOCUMENTS USING C2 CONTINUOUS BOUNDARY ESTIMATION

Prasenjit Mondal (Adobe)*; Ayush Pant (Adobe); Sachin Soni (Adobe)

1764: IAST: Instance Association Relying on Spatio-temporal Features for Video Instance
Segmentation
Junhao Chen (Zhejiang University of Technology); Sheng Liu (Zhejiang University of Technology)*;
ruixiang chen (Zhejiang University of Technology); BIngnan Guo (Zhejiang University of Technology);
Feng Zhang (Zhejiang University of Technology)

1769: Streaming Stroke Classification of Online Handwriting

Jingyu Liu (Institute of Automation of Chinese Academy of Sciences)*; Yanming Zhang (Institute of
Automation of Chinese Academy of Sciences); Fei yin (Institute of Automation of Chinese Academy of
Sciences); Cheng-Lin Liu (Institute of Automation of Chinese Academy of Sciences)

1780: CANet: Curved Guide Line Network with Adaptive Decoder for Lane Detection
Zhongyu Yang (University of Electronic Science and Technology of China)*; Chen Shen (Didi chuxing);
Wei Shao (Didi Chuxing); Tengfei Xing (Didi chuxing); Runbo Hu (DiDi Chuxing); Pengfei Xu (Didi
Chuxing); Hua Chai (Didi Chuxing); Ruini Xue (University of Electronic Science and Technology of China)

1791: SFEMGN: IMAGE DENOISING WITH SHALLOW FEATURE ENHANCEMENT NETWORK AND
MULTI-SCALE CONVGRU
Qidong Wang (China University of Mining and Technology); Lili Guo (China University of Mining and
Technology)*; Shifei Ding (China University of Mining and Technology); Jian Zhang (china university of
mining and technology); xiao xu (China University of Mining and Technology)

1794: FAPM: Fast Adaptive Patch Memory for Real-time Industrial Anomaly Detection
Donghyeong Kim (Yonsei University)*; Chaewon Park (Yonsei University); Suhwan Cho (Yonsei
University); Sangyoun Lee (Yonsei University)

1800: CRFAST: CLIP-BASED REFERENCE-GUIDED FACIAL IMAGE SEMANTIC TRANSFER

Ailin Li (College of Computer Science and Technology, Zhejiang University)*; Lei Zhao (Zhejiang
University); Zhizhong Wang (Zhejiang University); Zhiwen Zuo (Zhejiang University); Wei Xing (Zhejiang
University); Dongming Lu (Zhejiang University)

73
1834: Continuous interaction with a smart speaker via low-dimensional embeddings of dynamic
hand pose
songpei xu (University of Glasgow)*; Chaitanya Kaul (University of Glasgow); Xuri Ge (University of
Glasgow); Roderick Murray-Smith (University of Glasgow)

1854: SHADOW REMOVAL OF TEXT DOCUMENT IMAGES USING BACKGROUND ESTIMATION

and ADAPTIVE TEXT ENHANCEMENT
Wenjie Liu (Northwestern Polytechnical University); Bingshu Wang (Northwestern Polytechnical
University)*; Jiangbin Zheng (Northwestern Polytechnical University); Wenmin Wang (Macau University of
Science and Technology)

1887: CANDY: CAtegory-kerNelized DYnamic Convolution for Instance Segmentation

Yao Lu (Xiamen University)*; Zhiyi Chen (XiaMen University); Zehui Chen (University of Science and
Technology of China); Jie Hu (Xiamen University); Liujuan Cao (Xiamen University); ShengChuan Zhang
(Xiamen University)

1892: Thermal Infrared Image Inpainting via Edge-Aware Guidance

Zeyu Wang (Zhejiang University)*; Haibin Shen (Zhejiang University); Changyou Men (Hangzhou Vango
Technologies, Inc. ); Quan Sun (Hangzhou Vango Technologies, Inc. ); Kejie Huang (Zhejiang University)

1900: LONG-SHORT ATTENTION NETWORK FOR THE SPECTRAL SUPER-RESOLUTION OF

MULTISPECTRAL IMAGES
Kai Zhang (Shandong Normal University)*; Tian Jin (Shandong Normal University); Feng Zhang
(Shandong Normal University); Jiande Sun (Shandong Normal University)

1901: TAMFormer: Multi-Modal Transformer with Learned Attention Mask for Early Intent
Prediction
Nada Osman (University of Padova); Guglielmo Camporese (University of Padova); Lamberto Ballan
(University of Padova)*

1904: Long-tailed Recognition with Causal Invariant Transformation

Yahong zhang (lenovo )*; Sheng Shi (Lenovo Research); Chenchen Fan (Lenovo Research); Yixin Wang
(Lenovo Research); Wenli Ouyang (Lenovo AI lab); Wei Fan (Lenovo); Jianping Fan (Lenovo)

1945: Semantic-Aware Gated Fusion Network for Interactive Colorization

Jie Zhang (Hunan University)*; yi xiao (Hunan University); yan zheng (Hunan University); Zhenni Wang
(City University of Hong Kong); Chi Sing Leung (City University of Hong Kong)

1946: CDHD: CONTRASTIVE DREAMER FOR HINT DISTILLATION

yu le (Tsinghua University)*; Hua TongYan (Guangdong Bright Dream Robotics Co., Ltd.); Wenming Yang
(Tsinghua University); Ye Peng (Guangdong Bright Dream Robotics Co., Ltd.); Qingmin Liao (Tsinghua
Univeristy)

1959: Decaying Contrast for Fine-grained Video Representation Learning

Heng Zhang (Gaoling School of Artificial Intelligence,Renmin University of China); Bing Su (Renmin
University of China)*

1966: D2Q-DETR: Decoupling and Dynamic Queries for Oriented Object Detection with
Transformers
Qiang Zhou (Alibaba Group)*; Chaohui Yu (Alibaba Group); Zhibin Wang (Alibaba Group); Fan Wang
(Alibaba Group)

1967: Cross-head supervision for crowd counting with noisy annotations

Mingliang Dai (Fudan University)*; Zhizhong Huang (Fudan University); Jiaqi Gao (Fudan University);
Hongming Shan (Fudan University); Junping Zhang (Fudan University)

74
1974: N2MVSNet: Non-local Neighbors Aware Multi-View Stereo Network
Zhe Zhang (Peking University); Huachen Gao (Peking University); Yuxi Hu (The Chinese University of
Hong Kong, Shenzhen); Ronggang Wang (Peking University)*

1983: Look and Think: Intrinsic Unification of Self-attention and Convolution for Spatial-Channel
Specificity
Xiang Gao (South China University of Technology)*; Honghui Lin (South China University of Technology);
Yu Li (South China University of Technology); Ruiyan Fang (South China University of Technology); Xin
Zhang (South China University of Technology)

1984: SANDFORMER: CNN and Transformer under Gated Fusion for Sand Dust Image Restoration
Shi Jun (XinJiang University)*; Bingcai Wei (Shandong University of Technology); Gang Zhou (Xinjiang
University); Liye Zhang (Shandong university of technology)

2028: Diffusion Motion: Generate Text-Guided 3D Human Motion by Diffusion Model

Zhiyuan Ren (Michigan State University )*; Zhihong Pan (Baidu Research (USA)); Xin Zhou (Baidu USA);
Le Kang (Baidu Research)

2055: Trust Your Partner's Friends: Hierarchical Cross-modal Contrastive Pre-training for Video-
Text Retrieval
Yuhan Xiang (Xiamen University)*; Kaijian Liu (SenseTime Group Limited); Shixiang Tang (The University
of Sydney); Lei Bai (Shanghai AI Laboratory); Feng Zhu (University of Science and Technology of China);
Rui Zhao (SenseTime Group Limited); Xianming Lin (Xiamen University)

2059: BiSVP: Building Footprint Extraction via Bidirectional Serialized Vertex Prediction
Mingming Zhang (Beihang University); Ye Du (Beihang University); Zhenghui Hu (Hangzhou Innovation
Institute, Beihang University); Qingjie Liu (State Key Laboratory of Virtual Reality Technology and System,
Beihang University, Beijing 100191, China)*; Yunhong Wang (State Key Laboratory of Virtual Reality
Technology and System, Beihang University, Beijing 100191, China)

2071: Semantic Preserving Learning for Task-oriented Point Cloud Downsampling

Jianyu Xiong (Tsinghua University)*; Tao Dai (Shenzhen University); Yaohua Zha (Tsinghua University);
Xin Wang (Tsinghua University); Shu-Tao Xia (Tsinghua University)

2088: A NOVEL MODE SELECTION-BASED FAST INTRA PREDICTION ALGORITHM FOR SPATIAL
SHVC
Dayong Wang (Institute of Bioinformatics, Chongqing University of Posts & Telecommunications,
Chongqing, China)*; Yu Sun (University of Central Arkansas); Weisheng Li (Chongqing University of
Posts and Telecommunications); Lele Xie (Chongqing University of Posts & Telecommunications); Xin Lu
(De Montfort University ); Frederic Dufaux (CNRS); Ce Zhu (University of Electronic Science &
Technology of China)

2125: Ultimate Negative Sampling For Contrastive Learning

Huijie Guo (Beihang University)*; Lei Shi (Beihang University)

2126: Designing a 3D-Aware StyleNeRF Encoder for Face Editing

Songlin Yang (Institute of Automation, Chinese Academy of Sciences)*; Wei Wang (Center for Research
on Intelligent Perception and Computing, National Laboratory of Pattern Recognition, Institute of
Automation, Chinese Academy of Sciences); Bo Peng (Institute of Automation, Chinese Academy of
Sciences); Jing Dong (Chinese Academy of Sciences)

2133: ShaDocNet: Learning Spatial-Aware Tokens in Transformer for Document Shadow Removal
Xuhang Chen (University of Macau)*; Xiaodong Cun (Tencent AI Lab); Chi-Man Pun (University of
Macau); Shuqiang Wang (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences)

75
2134: Fine-grained Blind Face Inpainting with 3D Face Component Disentanglement
Yu Bai (Fudan University); Ruian He (Fudan University); Weimin Tan (Fudan University); Bo Yan (Fudan
University)*; Yangle Lin (Fudan University)

2139: Sample-Adapt Fusion Network for RGB-D Hand Detection in the Wild
Xingyu Liu (Beijing University of Posts and Telecommunications)*; Pengfei Ren (Beijing University of
Posts and Telecommunications); Yuchen Chen (Beijing University of Posts and Telecommunications);
Cong Liu (China Mobile); Jing Wang (Beijing University of Posts and Telecommunications); Haifeng Sun
(Beijing university of posts and telecommunications); Qi Qi (Beijing University of Posts and
Telecommunications); Jingyu Wang (Beijing University of Posts and Telecommunications)

2155: A fusion-based and multi-layer method for low light image enhancement
Xueyan Zhou (Nankai University)*; Jiacen Guo (Nankai University); Hao Liu (Nankai University); Chao
Wang (Nankai University)

2160: SFR: Semantic-aware Feature Rendering of Point Cloud

Yaohua Zha (Tsinghua University)*; Rongsheng Li (Tsinghua University); Tao Dai (Shenzhen University);
Jianyu Xiong (Tsinghua University); Xin Wang ( Tsinghua University); Shu-Tao Xia (Tsinghua University)

2198: TRANSFORMER-BASED DEEP HASHING METHOD FOR MULTI-SCALE FEATURE FUSION

Chao He (Inner Mongolia University); Hongxi Wei (Inner Mongolia University)*

2199: StackMaps: A Visualization Technique for Diabetic Retinopathy Grading

Ismail M El-Yamany (Alexandria University)*; Abdelrahman Wael (Faculty of Engineering, University of
Alexandria); Noha Adly (MCIT); Marwan Torki (Alexandria University)

2203: Associative Learning Network for Coherent Visual Storytelling

Xin Li ( School of Computer Science & Technology, Soochow University); Chunping Liu (School of
Computer Science and Technology, Soochow University); Yi Ji (School of Computer Science and
Techonology, Soochow University)*

2221: SPATIAL SIMILARITY GUIDANCE FOR FEW-SHOT SEGMENTATION

Xiaoliu Luo (Chongqing University)*; Zhao Duan (Chongqing University); Taiping Zhang (Chongqing
University)

2226: SELF-DISTILLATION HASHING FOR EFFICIENT HAMMING SPACE RETRIEVAL

Hongjia HJ Zhai (Zhejiang University); Hai Li (Zhejiang University); hanzhi zhang (Zhejiang University);
Hujun Bao (Zhejiang University); Guofeng Zhang (Zhejiang University)*

2268: DUAL-HEAD FUSION NETWORK FOR IMAGE ENHANCEMENT

Yuhong Zhang (Shanghai Jiao Tong University); Hengsheng Zhang (Shanghai Jiao Tong University); Li
Song (Shanghai Jiao Tong University)*; Rong Xie (Shanghai Jiao Tong University); Wenjun Zhang
(Shanghai Jiao Tong University)

2270: Spatial-Temporal Graph Convolutional Network boosted Flow-Frame Prediction for Video
Anomaly Detection
Kai Cheng (Fudan University)*; Xinhua Zeng (Fudan University); Yang Liu (Fudan University); Mengyang
Zhao (FUDAN University); pang chengxin (Shanghai University of Electric Power); Xing Hu (university of
shanghai for science and technology)

2273: Nasty-SFDA: Source Free Domain Adaptation from A Nasty Model

Jiajiong Cao (Ant Financial Service Group); Yufan Liu (Institute of Automation, Chinese Academy
Sciences)*; Weiming Bai (Chinese Academy of Sciences); Jingting Ding (Ant Financial); Liang Li (Ant
Financial Service Group)

76
2303: IMAGE FUSION VIA SLICE_BASED CONVOLUTIONAL SPARSE REPRESENTATION
Jingchen Xu (Yanshan University); Yali Zhang (Yanshan University); Ze Li (YanShan University); Jinjia
Wang (Yanshan University)*

2310: CAENet: Using Collaborative Attention Transformer and Add-Boost Strategy for Single
Image Deraining
Shengdi Qin (Beijing Jiaotong University); Shunli Zhang (Beijing Jiaotong University)*; Yu Zhang
(Beihang University); Haoyu Gao (Beijing Jiaotong University)

2318: GEOGCN: GEOMETRIC DUAL-DOMAIN GRAPH CONVOLUTION NETWORK FOR POINT

CLOUD DENOISING
ZhaoWei Chen (Nanjing University of Aeronautics and Astronautics)*; Peng Li (Nanjing University of
Aeronautics and Astronautics); Zeyong Wei (Nanjing University of Aeronautics and Astronautics);
Honghua Chen (Nanyang Technological University); Haoran Xie (Lingnan University); Mingqiang
Wei ( Nanjing University of Aeronautics and Astronautics); Fu Lee Wang (Hong Kong
Metropolitan University)

2325: Deep Double Self-expressive Subspace Clustering

zhao ling (Southwest University); Ma Yunpeng (Southwest University); Shanxiong Chen (southwest
university); Jun Zhou (Southwest University)*

2360: Learning Task-aligned Mask Query for Instance Segmentation

Bin Fu (School of Electronic and Computer Engineering, Peking University Shenzhen Graduate School)*;
Hongliang He (School of Electronic and Computer Engineering, Peking University); Pengxu Wei (Sun Yat-
sen University); Jie Chen (Peking University)

2361: PI-Trans: Parallel-ConvMLP and Implicit-Transformation Based GAN for Cross-View Image
Translation
Bin Ren (University of Trento)*; Hao Tang (ETH Zurich); Yiming Wang (Fondazione Bruno Kessler); Xia Li
(ETH Zurich); Wei Wang (EPFL); Nicu Sebe (University of Trento)

2363: Multi-level fusion for burst super-resolution with deep permutation-invariant conditioning
Martina Cilia (Politecnico di Torino); Diego Valsesia (Politecnico di Torino)*; Giulia Fracastoro (Polito);
Enrico Magli (POLITO)

2436: VLKP:VIDEO INSTANCE SEGMENTATION WITH VISUAL-LINGUISTIC KNOWLEDGE

ruixiang chen (Zhejiang University of Technology); Sheng Liu (Zhejiang University of Technology)*;
Junhao Chen (Zhejiang University of Technology); BIngnan Guo (Zhejiang University of Technology);
Feng Zhang (Zhejiang University of Technology)

2442: Volumetric 3D Reconstruction with Window-wise Global Feature Aggregation

Shihao Ren (Tsinghua University)*; Yikang Ding (Tsinghua University); Jinli Liao (Tsinghua University);
Xinghui Li (Tsinghua University); Jia Guo (None); Wensen Feng (the Shenzhen Graduate School,
Tsinghua University, Shenzhen 518071, China); Xueqian Wang (Tsinghua University)

2446: LOW-RANK CONSTRAINED MEMORY AUTOENCODER FOR HYPERSPECTRAL ANOMALY

DETECTION
yuyun lian (China University of Geosciences); Yongshan Zhang (China University of Geosciences)*;
Xuxiang Feng (Chinese Academy of Sciences); Xinwei Jiang (China University of Geosciences); Zhihua
Cai (China University of Geosciences)

2453: Human Pose Estimation from Ambiguous Pressure Recordings with Spatio-temporal
Masked Transformers
Vandad Davoodnia (Queen's University)*; Ali Etemad (Queen's University)

77
2455: TrOMR:Transformer-based Polyphonic Optical Music Recognition
Yixuan Li (Hangzhou Netease cloud Music Technology Co., Ltd)*; Huaping Liu ( Hangzhou Netease
cloud Music Technology Co., Ltd); Qiang Jin (Hangzhou Netease cloud Music Technology Co., Ltd);
Miaomiao Cai (Hangzhou Netease cloud Music Technology Co., Ltd); Peng Li (NetEase Cloud Music)

2465: MSFormer: Multi-Scale Transformer with Neighborhood Consensus for Feature Matching
Dongyue Li (Southeast University); Yaping Yan (Southeast University); Dong Liang (Nanjing University of
Aeronautics and Astronautics); Songlin Du (Southeast University)*

2467: VOLUMETRIC ATTRIBUTE COMPRESSION FOR 3D POINT CLOUDS USING FEEDFORWARD

NETWORK WITH GEOMETRIC ATTENTION
Tam Thuc V.H Do (York University); Philip A Chou (Google); Gene Cheung (York University)*

2469: Continual Cell Instance Segmentation of Microscopy Images

Tzu-Ting Chuang (National Sun Yat-sen University); Ting-Yun Wei (National Taiwan University); Yu-Hsing
Hsieh (National Taiwan University); Chu-Song Chen (National Taiwan University); Huei-Fang Yang
(National Sun Yat-sen University)*

2476: HIGH-FREQUENCY TRANSFORMER NETWORK BASED ON WINDOW CROSS-ATTENTION

FOR PANSHARPENING
Chengjie Ke (WuHan University); Hao Liang (WuHan University); Duidui Li (China Centre for Resources
Satellite Data and Application); Xin Tian (Wuhan University)*

2489: MULTIPLE DOMAIN-ADVERSARIAL ENSEMBLE LEARNING FOR DOMAIN GENERALIZATION

Ze-Yu Mi (Nanjing university); Kun Long (State Key Laboratory for Novel Software Technology, Nanjing
University); Yu-Bin Yang (State Key Laboratory for Novel Software Technology, Nanjing University)*

2500: SEMANTICS-DISENTANGLED CONTRASTIVE EMBEDDING FOR GENERALIZED ZERO-SHOT

LEARNING
Jian Ni (University of Science and Technology of China)*; Yong Liao (University of Sciences and
Technology of China)

2502: MMCOSINE: MULTI-MODAL COSINE LOSS TOWARDS BALANCED AUDIO-VISUAL FINE-

GRAINED LEARNING
Ruize Xu (Renmin University of China); Ruoxuan Feng (Renmin University of China); Shixiong Zhang
(Tencent); Di Hu (Renmin University of China)*

2505: LOCAL FEATURE ENHANCED ADVERSARIAL NETWORK FOR THE BLIND IMAGE QUALITY
ASSESSMENT
Xiaomei Shi (Northwest University); Min Zhang (Northwest University)*; Shou Hai Xia (Northwest
University); Ru Xue Zhang (Northwest University); Jun Feng (Northwest University)

2521: SPATIAL CORRELATION FUSION NETWORK FOR FEW-SHOT SEGMENTATION

Xueliang Wang (Tsinghua University)*; Wenqi Huang (China southern power grid); Wenming Yang
(Tsinghua University); Qingmin Liao (Tsinghua Univeristy)

2531: FREQUENCY-AWARE ATTENTIONAL FEATURE FUSION FOR DEEPFAKE DETECTION

Cheng Tian (Xiamen University)*; Zhiming Luo (Xiamen University); Guimin Shi (Wuyi University); Shaozi
Li (Xiamen University, China)

2538: 2DSBG: A 2D SEMI BI-GAUSSIAN FILTER ADAPTED FOR ADJACENT AND MULTI-SCALE
LINE FEATURE DETECTION
Baptiste Magnier (IMT Mines Ales CERIS)*; Ghulam Sakhi Shokouh (IMT Mines Ales); Louis Berthier
(IMT Mines Ales CERIS); Marcel Pie-Tapia (IMT Mines Ales CERIS); Adrien Ruggiero (IMT Mines Ales
CERIS)

78
2553: RATE-DISTORTION OPTIMIZED VARIABLE-NODE-SIZE TRISOUP FOR POINT CLOUD
CODING
Kyohei Unno (KDDI Research)*; Kohei Matsuzaki (KDDI Research); Satoshi Komorita (KDDI Research,
Inc.); Kei Kawamura (KDDI Research)

2562: TENSOR DECOMPOSITION BASED LATENT FEATURE CLUSTERING FOR

HYPERSPECTRAL BAND SELECTION
Jianwen Qi (China University of Geosciences); jie zhang (University of Macau); Yongshan Zhang (China
University of Geosciences)*; Xinwei Jiang (China University of Geosciences); Zhihua Cai (China
University of Geosciences)

2569: ERBNet: An Effective Representation Based Network for Unbiased Scene Graph Generation
Wenxi Ma (Xiamen University); Tianxiang Hou (Xiamen University); Qianji Di (Xiamen University);
Zhongang Qi (Tencent); Ying Shan (Tencent); Hanzi Wang (Xiamen University)*

2636: Customized Automatic Face Beautification

Wang Chen (FuZhou University); Peizhen Chen ( Fuzhou University); Weijie Chen (Zhejiang University);
Luojun Lin (Fuzhou University)*

2680: Deep3DSketch: 3D modeling from Free-hand Sketches with View- and Structural-Aware
Adversarial Training
Tianrun Chen (Zhejiang University)*; Chenglong Fu (Huzhou University); Lanyun Zhu (Singapore
University of Technology and Design); Mao Papa (Moxin (Huzhou) Technology Co., LTD); Ying Zang
(Huzhou University); Jia Zhang (Yangzhou Polytechnic College); Lingyun Sun (Zhejiang University)

2684: Frequency Reciprocal Action and Fusion for Single Image Super-Resolution
Shuting Dong (Tsinghua University)*; Feng Lu (Tsinghua University); Chun Yuan (Graduate school at
ShenZhen，Tsinghua university)

2692: DL-NET: DILATION LOCATION NETWORK FOR TEMPORAL ACTION DETECTION

Dianlong You (yanshan university); Houlin Wang (yanshan university)*; Bingxin Liu (yanshan university);
Yang Yu (yanshan university); Zhiming Li (yanshan university)

2710: iSmallNet: Densely Nested Network with Label Decoupling for Infrared Small Target
Detection
Zhiheng Hu (Nanjing University of Aeronautics and Astronautics); Yongzhen Wang (Nanjing University of
Aeronautics and Astronautics); Peng Li (Nanjing University of Aeronautics and Astronautics); Jie Qin
(Nanjing University of Aeronautics and Astronautics)*; Haoran Xie (Lingnan University); Mingqiang Wei
(Nanjing University of Aeronautics and Astronautics)

2713: UAV REMOTE SENSING IMAGE DEHAZING BASED ON MULTI-DIMENSIONAL SALIENCY

AWARENESS UNEQUAL NETWORK
Ruohui Zheng (Beijing Normal University); Libao Zhang (Beijing Normal University)*

2714: A Two-branch Network for Video Anomaly Detection with Spatio-temporal Feature Learning
Guoqiu Li (Tsinghua Shenzhen International Graduate School, Tsinghua University)*; Shengjie Chen
(Tsinghua University); Yujiu Yang (Tsinghua University); Zhenhua Guo (Tianyi Traffic Technology)

2757: BILATERAL COARSE-TO-FINE NETWORK FOR POINT CLOUD COMPLETION

Tran Thanh Phong Nguyen (University of Wollongong)*; Son Lam Phung (University of Wollongong,
VinAI); Vinod Gopaldasani (University of Wollonong); Jane L Whitelaw (University of Wollongong)

2762: A Dual-branch Adaptive Distribution Fusion Framework for Real-world Facial Expression
Recognition
Shu Liu (Central South University)*; Yan Xu (Central South University); Tongming Wan (Central South
University); Xiaoyan Kui (Central South University)

79
2765: Face Recognition on Point Cloud with cGAN-TOP for Denoising
Junyu Liu (University of Nottingham Ningbo China); Jianfeng Ren (University of Nottingham Ningbo
China)*; Hong-liang Sun (UNNC); Xudong Jiang (Nanyang Technological University)

2767: Self-paced Partial Domain-Aware Learning for Face Anti-spoofing

Zhiyi Chen (XiaMen University)*; Yao Lu (Xiamen University); Xinzhe Deng (Tencent); Jia Meng
(Tencent); ShengChuan Zhang (Xiamen University); Liujuan Cao (Xiamen University)

2770: SQA: STRONG GUIDANCE QUERY WITH SELF-SELECTED ATTENTION FOR HUMAN-
OBJECT INTERACTION DETECTION
Feng Zhang (Zhejiang University of Technology); Sheng Liu (Zhejiang University of Technology)*;
BIngnan Guo (Zhejiang University of Technology); ruixiang chen (Zhejiang University of Technology);
Junhao Chen (Zhejiang University of Technology)

2777: FCIR: RETHINK AERIAL IMAGE SUPER RESOLUTION WITH FOURIER ANALYSIS
Yan Zhang (Chongqing University of Posts and Telecommunications); Pengcheng Zheng (Chongqing
University of Posts and Telecommunications); Jianan Jiang (Chongqing University Of Posts And
Telecommunications); Xiao PU (Chongqing University of Posts and Telecommunications); Xinbo Gao
(Chongqing University of Posts and Telecommunications)*

2799: Knowledge Distillation with Active Exploration and Self-attention based Inter-Class Variation
Transfer For Image Segmentation
Yifan Zhang (Shenzhen University); Shaojie Li (Shenzhen University); Xuan Yang (Shenzhen University)*

2824: Structure-Aware Multi-Feature Co-Learning for Dual Branch Face Super Resolution
Kangli Zeng (School of Computer Science, Wuhan University)*; Zhongyuan Wang (Wuhan University);
Tao Lu (Wuhan Institute of Technology); Jianyu Chen (Wuhan University)

2847: End-to-End Unsupervised Sketch to Image Generation

Xingming Lv (Shandong University)*; Lei Wu (Shandong University); Zhenwei Cheng (Shandong
University); Xiangxu Meng (Shandong University)

2858: IFUNET++: ITERATIVE FEEDBACK UNET++ FOR INFRARED SMALL TARGET DETECTION
Zhangying Weng (Nanjing University of Aeronautics and Astronautics)*; Peng Li (Nanjing University of
Aeronautics and Astronautics); Xin Zhuang
(BeijingAerospaceIntelligentManufacturingTechnologyDevelopmentCo.,Ltd); Xuefeng Yan (Nanjing
University of Aeronautics and Astronautics); Lina Gong (Nanjing University of Aeronautics and
Astronautics); Haoran Xie (Lingnan University); Mingqiang Wei (Nanjing University of Aeronautics and
Astronautics)

2873: SEMI-SUPERVISED CONTRASTIVE LEARNING WITH SOFT MASK ATTENTION FOR FACIAL
ACTION UNIT DETECTION
Zhongling Liu (Fujitsu Research and Development Center); Rujie Liu (Fujitsu Research & Development
Center Co., Ltd.); Ziqiang Shi (Fujitsu Research & Development Center)*; Liu Liu (Fujitsu Research &
Development Center); Xiaoyu Mi (Fujitsu Laboratories Ltd.); Kentaro Murase (Fujitsu Laboratories Ltd.)

2898: $\psi$-Net: Point Structural Information Network for No-reference Point Cloud Quality
Assessment
Jian Xiong (Nanjing Univeristy of Posts and Telecommunications)*; Sifan Wu (Nanjing Univeristy of Posts
and Telecommunications); Wang Luo (Nanjing Univeristy of Posts and Telecommunications); Jinli Suo
(Tsinghua University); Hao Gao (Nanjing University of Posts and Telecommunications)

2904: Gender-Cartoon: Image cartoonization method based on gender classification

Long Feng (Northwest University)*; Guohua Geng (Northwest University); Chen Guo (Shaanxi Normal
University); longquan yan (Northwest University); Xingrui Ma (Northwest University); Zhan Li (Northwest
University); Kang Li (Northwest University)

80
2917: JNDMix: JND-Based Data Augmentation for No-reference Image Quality Assessment
Jiamu Sheng (Fudan University); Jiayuan Fan (Fudan University)*; peng ye (fudan university); Jianjian
Cao (Fudan University)

2927: RDO CANDIDATE SELECTION FOR MAXIMIZING CODING EFFICIENCY IN A PRACTICAL

HEVC ENCODER
Joose Sainio (Tampere University); Alexandre MERCAT (Tampere University)*; Jarno Vanne (Tampere
University)

2929: Residual Hybrid Attention Network for Compression Artifact Reduction

bingchun luo (Harbin Institute of Technology); Wei Yu (Harbin Institute of Technology)*

2940: SL-MOE: A TWO-STAGE MIXTURE-OF-EXPERTS SEQUENCE LEARNING FRAMEWORK FOR

FORECASTING RAPID INTENSIFICATION OF TROPICAL CYCLONE
Jian Xu (Beijing University of Posts and Telecommunications); Yang Lei (Beijing University of Posts and
Telecommunications); Guangqi Zhu (Beijing University of Posts and Telecommunications); Yunling Feng
(Beijing University of Posts and Telecommunications); Bo Xiao (Beijing University of Posts and
Telecommunications); Qifeng Qian (National Meteorological Center of China); Yajing Xu (Beijing
University of Posts and Telecommunications)*

2962: A content-based multi-scale network for single image super-resolution

Jiahuan Ji (College of Electronic and Information Engineering, Nanjing University of Aeronautics and
Astronautics); Baojiang Zhong (School of Computer Science and Technology, Soochow University)*; Kai-
Kuang Ma (Nanyang Technological University, Singapore)

2972: Prior-Enhanced Temporal Action Localization using Subject-aware Spatial Attention

Yifan Liu (Tsinghua University)*; Youbao Tang (PAII Inc.); Ning Zhang (PAII Inc); Ruei-Sung Lin (PAII Inc);
Haoqian Wang (Tsinghua Shenzhen International Graduate School, Tsinghua University)

2993: A2SConv: Asymmetric Spetral-Spatial Neural Architecture Search for Hyperspectral Image
Classification
Zhan Lin (School of Information Science and Technology, Fudan); Jiayuan Fan (Fudan University)*; peng
ye (fudan university); Cao Jianjian (Fudan University)

3014: SCOREFORMER: SCORE FUSION-BASED TRANSFORMERS FOR WEAKLY-SUPERVISED

VIOLENCE DETECTION
Yang Xiao (Xinjiang University)*; Liejun Wang (Xinjiang University); Tongguan Wang (Xinjiang University);
Huicheng Lai (Xinjiang University)

3021: RETHINK LONG-TAILED RECOGNITION WITH VISION TRANSFORMS

Zhengzhuo Xu (Tsinghua University)*; Shuo Yang (Tsinghua university); Xingjun Wang (Tsinghua
University); Chun Yuan (Graduate school at ShenZhen，Tsinghua university)

3031: DISTORTION-AWARE CONVOLUTIONAL NEURAL NETWORK-BASED INTERPOLATION

FILTER FOR AVS3
Ying Zhang (Samsung Electronics); liang wen (Samsung Research China-Beijing (SRC-B))*; Lizhong
Wang (Samsung); Yinji Piao (Samsung Electronics); Weijing Shi (Samsung Electronics); Kwang Pyo Choi
(Samsung Electronics)

3032: YOLO-Based Lightweight Object Detection with Structure Simplification and Attention
Enhancement
Shuqi Sun (University of Jinan)*; Xiaohui Yang (University of Jinan); Jingliang Peng (University of Jinan)

81
3053: LEARNING TO EXPLAIN: A GRADIENT-BASED ATTRIBUTION METHOD FOR INTERPRETING
SUPER-RESOLUTION NETWORKS
Anni Yu (State Key Laboratory for Novel Software Technology, Nanjing University); Yu-Bin Yang (State
Key Laboratory for Novel Software Technology, Nanjing University)*

3073: Matrix Recovery using Deep Generative Priors with Low-Rank Deviations
Pengbin Yu (Southwest University)*; Jianjun Wang (Southwest University); Chen Xu (University of
Ottawa)

3094: Optimising Different Feature Types for Inpainting-based Image Representations

Ferdinand Jost (Saarland University)*; Vassillen Chizhov (Saarland University); Joachim Weickert
(Saarland University)

3108: Boosting No-Reference Super-Resolution Image Quality Assessment with Knowledge

Distillation and Extension
Haiyu Zhang (Northwestern Polytechnical University)*; Shaolin Su (Northwestern Polytechnical
University); Yu Zhu (Northwestern Polytechnical University); Jinqiu Sun (Northwestern Polytechnical
University); Yanning Zhang (Northwestern Polytechnical University)

3115: MSNet: A Deep Architecture using Multi-Sentiment Semantics for Sentiment-Aware Image
Style Transfer
Shikun Sun (Tsinghua University)*; Jia Jia (Tsinghua University); Haozhe Wu (Tsinghua University); Zijie
Ye (Tsinghua University); Junliang Xing (Tsinghua University)

3140: CNN Filter for RPR-Based SR in VVC with Wavelet Decomposition

Hui Lan (Xidian University); Cheolkon Jung (Xidian University)*; Yang Liu (OPPO Mobile); Ming Li
(OPPO)

3145: Sketch Less Face Image Retrieval: A New Challenge

Dawei Dai (Chongqing Key Laboratory of Computational Intelligence, College of Computer Science and
Technology, Chongqing University of Posts and Telecommunications)*; YuTang Li (Chongqing Key
Laboratory of Computational Intelligence, College of Computer Science and Technology, Chongqing
University of Posts and Telecommunications); liang wang (Chongqing Key Laboratory of Computational
Intelligence, College of Computer Science and Technology, Chongqing University of Posts and
Telecommunications); shiyu fu (Chongqing Key Laboratory of Computational Intelligence, College of
Computer Science and Technology, Chongqing University of Posts and Telecommunications); Shuyin Xia
(Chongqing University of Posts and Telecommunications); Guoyin Wang (Chongqing Key Laboratory of
Computational Intelligence; Chongqing University of Posts and Telecommunications)

3167: Extracting the Brain-like Representation by an Improved Self-Organizing Map for Image
Classification
Jiahong Zhang (Communication University of China)*; Lihong Cao (Communication University of China);
Moning Zhang (Communication University of China ); Wenlong Fu (Communication University of China)

3183: Dynamic Multi-View Scene Reconstruction Using Neural Implicit Surface

Decai Chen (Fraunhofer Heinrich Hertz Institute )*; Haofei Lu (The Fraunhofer Institute for
Telecommunications, Heinrich Hertz Institute); Ingo Feldmann (Fraunhofer HHI); Oliver Schreer
(Fraunhofer Heinrich-Hertz-Institute); Peter Eisert (Fraunhofer HHI / Humboldt University Berlin)

3192: IMPLICITLY ROTATION EQUIVARIANT NEURAL NETWORKS

Naman Khetan (IIT (ISM) Dhanbad); Tushar Arora (IIT (ISM) Dhanbad); Samee Ur Rehman (Transmute
AI); Deepak K Gupta (UiT The Arctic University of Norway)*

82
3206: LP-IOANET: EFFICIENT HIGH RESOLUTION DOCUMENT SHADOW REMOVAL
Kostas Georgiadis (CERTH/ITI); Mehmet Kerim Yücel (Samsung R&D UK )*; Evangelos Skartados
(Centre for Research and Technology, Hellas, Information Technologies Institute); Valia Dimaridou
(CERTH-ITI); Anastasios Drosou (CERTH-ITI); Albert Saà-Garriga (Samsung R&D UK); Bruno Manganelli
(Samsung Research UK)

3216: Non-convex approaches for low-rank tensor completion under tubal sampling
Zheng Tan (University of California, Los Angeles); Longxiu Huang (Michigan State University); HanQin
Cai (University of Central Florida ); Yifei Lou (University of Texas at Dallas)*

3262: LSTM-based Video Quality Prediction Accounting for Temporal Distortions in

Videoconferencing Calls
Gabriel Mittag (Microsoft Corporation)*; Babak Naderi (Technical University of Berlin); Vishak Gopal
(Microsoft Corporation); Ross Cutler ( Microsoft Corporation)

3268: PAIR DETR: TOWARD FASTER CONVERGENT DETR

Seyed mehdi Iranmanesh (Amazon); Sherry X Chen (University of California, Santa Barbara); Kuo-Chin
Lien (Appen)*

3287: Lit the Darkness: Three-stage zero-shot learning for low-light enhancement with multi-
neighbor enhancement factors
Mariam Saeed (Alexandria University); Marwan Torki (Alexandria University)*

3296: Efficient Siamese Network for UAV Tracking

Xiaohan Zhang (Dalian University of Technology)*; Dong Wang (Dalian University of Technology);
Xiaohong Ma (Dalian University of Technology)

3306: Exploring vision transformer layer choosing for semantic segmentation

Fangjian Lin (alibaba-inc)*; Yizhe Ma (Xinjiang University); Shengwei Tian (Xinjiang University)

3311: Data Augmentation based on Invariant Shape Blending for Deep Learning Classification
Emna Ghorbel (National School of Computer Science (ENSI))*; Mahmoud Ghorbel (National School of
Computer Science (ENSI)); Slim Mhiri (ENSI)

3318: Multi-rate adaptive transform coding for video compression

Lyndon Duong (New York University)*; Bohan Li (Google LLC); Cheng Chen (Google Inc.); Jingning Han
(Google Inc.)

3327: Efficiently fusing sparse LiDAR for enhanced Self-supervised Monocular Depth Estimation
Yue Wang (University College London); Mingrong Gong (Shenzhen Institute of Advanced Technology,
Chinese Academy of Sciences); Lei Xia (Shenzhen Institute of Advanced Technology, Chinese Academy
of Sciences); Qieshi Zhang (Shenzhen Institute of Advanced Technology, Chinese Academy of
Sciences)*; Jun Cheng (Shenzhen Institutes of Advanced Technology, Chinese Academy of Sciences)

3350: Temporal Contrastive Learning with Curriculum

Shuvendu Roy (Queen's University)*; Ali Etemad (Queen's University)

3366: Bayesian Methods for Optical Flow Estimation Using a Variational Approximation, With
Applications to Ultrasound
Jan Dorazil (TU Wien)*; Bernard H. Fleury (TU Wien); Franz Hlawatsch (TU Wien)

3432: GLOBAL MATCHING-OPTIMIZATION NETWORK FOR STEREO DEPTH ESTIMATION

Yidi Zhang (Tsinghua University)*; Wenqi Huang (China southern power grid); Wenming Yang (Tsinghua
University)

83
3444: RD-NAS: Enhancing One-shot Supernet Ranking Ability via Ranking Distillation from Zero-
cost Proxies
Peijie Dong (School of Computer Science, National University of Defense Technology); Xin Niu (NUDT)*;
Lujun Li (Chinese Academy of Sciences); ZHILIANG TIAN (National University of Defense Technology);
Xiaodong Wang (National University of Defense Technology); Zimian Wei (School of Computer Science,
National University of Defense Technology); Hengyue Pan (National University of Defense Technology);
Dongsheng Li (School of Computer Science, National University of Defense Technology)

3451: Progressive Meta-Pooling Learning for Lightweight Image Classification Model

Peijie Dong (School of Computer Science, National University of Defense Technology); Xin Niu (NUDT)*;
ZHILIANG TIAN (National University of Defense Technology); Lujun Li (Chinese Academy of Sciences);
Xiaodong Wang (National University of Defense Technology); Zimian Wei (School of Computer Science,
National University of Defense Technology); Hengyue Pan (National University of Defense Technology);
Dongsheng Li (School of Computer Science, National University of Defense Technology)

3470: A NOVEL STATE CONNECTION STRATEGY FOR QUANTUM COMPUTING TO REPRESENT

AND COMPRESS DIGITAL IMAGES
MD ERSHADUL HAQUE (Charles Sturt University )*; Manoranjan Paul (Charles Sturt University,
Australia); Anwaar Ulhaq (Charles Sturt University); Tanmoy Debnath (Charles Sturt University, Australia)

3473: Robust Video Object Segmentation With Restricted Attention

Huaizheng Zhang (Fudan University); Pinxue Guo (Fudan University); Zhongwen Le (Fudan University );
Wenqiang Zhang (Fudan University)*

3475: MULTI-STREAM FACIAL ADAPTIVE NETWORK FOR EXPRESSION RECOGNITION FROM A

SINGLE IMAGE
Baichuan Zhang (Sun Yat-sen University); Fanyang Meng (Peng Cheng Laboratory); Runwei Ding
(Peking University Shenzhen Graduate School); Mengyuan Liu (Peking University, Shenzhen Graduate
School)*

3477: TINYCOD: TINY AND EFFECTIVE MODEL FOR CAMOUFLAGED OBJECT DETECTION
Haozhe Xing (Fudan University); Shuyong Gao (Fudan University); Hao Tang (ETH Zurich); Tsui Qin Mok
(Fudan University); Yanlan Kang (Fudan University); Wenqiang Zhang (Fudan University)*

3490: Privacy Preserving Face Recognition with Lensless Camera

Chris Henry (University of Missouri-Kansas City)*; M. Salman Asif (University of California, Riverside);
Zhu Li (university of missouri-kansas city)

3498: Decoupled Visual Causality for Robust Detection

Ping Jiang (Central South University); Xiaoheng Deng (Central South University)*; Shichao Zhang
(Central South University)

3501: STACKING-BASED ATTENTION TEMPORAL CONVOLUTIONAL NETWORK FOR ACTION

SEGMENTATION
Liu Yang (School of Computer Science and Engineering, Central South University); Yu Jiang (School of
Computer Science and Engineering, Central South University); Junkun Hong (School of Computer
Science and Engineering, Central South University); Zhenjie Wu ( School of Computer Science
and Engineering, Central South University); Zhan Yang (Big Data Institute, Central South University); Jun
Long (Central South University)*

3503: Lightweight Fisher Vector Transfer Learning for Video Deduplication

Chris Henry (University of Missouri-Kansas City)*; Rijun Liao (University of Missouri-Kansas City);
Ruiyuan Lin (InnoPeak Technology (Oppo US Research Center)); Zhebin Zhang (OPPO); Hongyu Sun
(Oppo); Zhu Li (university of missouri-kansas city)

84
3532: BAUENet: Boundary-Aware Uncertainty Enhanced Network for Infrared Small Target
Detection
Tianxiang Chen (University of Science and Technology of China); Qi Chu (University of Science and
Technology of China)*; Zhentao Tan (Alibaba DAMO Academy); Bin Liu (University of Science and
Technology of China); Nenghai Yu (University of Science and Technology of China)

3537: BAGGING R-CNN: ENSEMBLE FOR OBJECT DETECTION IN COMPLEX TRAFFIC SCENES
Pengteng Li (Shenzhen University); Ying He (Shenzhen University); Dongfu Yin (Guangdong Laboratory
of Artificial Intelligence and Digital Economy (SZ)); F Richard Yu (Shenzhen University)*; Pinhao Song
(KU Leuven)

3551: RCDPT: Radar-Camera fusion Dense Prediction Transformer

Lo Chen-Chou (KU Leuven)*; Vandewalle Patrick (KU Leuven)

3555: LOCAL TO GLOBAL PRIOR LEARNING FOR BLIND UNSUPERVISED IMAGE SUPER
RESOLUTION
Kazuhiro Yamawaki (Yamaguchi University)*; Xian-Hua Han (Yamaguchi University)

3583: LiNuIQA: Lightweight No-Reference Image Quality Assessment based on Non-Uniform

Weighting
Wook-Hyung Kim (Samsung Electronics Co. Ltd)*; Cheul-Hee Hahm (Samsung Electronics Co. Ltd);
Anant Baijal (Samsung Electronics Co. Ltd); Namuk Kim (Samsung Electronics Co. Ltd); Ilhyun Cho
(Samsung Electronics Co. Ltd); Jayoon Koo (Samsung Electronics Co. Ltd)

3588: MFAT: A Multi-level Feature Aggregated Transformer for person re-identification

Bowen Tan (University of Electronic Science and Technology of China)*; Linfeng Xu (University of
Electronic Science and Technology of China); Zihuan Qiu (University of Electronic Science and
Technology of China); Qingbo Wu (University of Electronic Science and Technology of China); Fanman
Meng (University of Electronic Science and Technology of China)

3589: Single-Particle Tracking by Graph Transformer

Satoshi Kamiya (Meijo university)*; Kazuhiro Hotta (Meijo University); Taka Aki Tsunoyama (OIST);
Akihiro Kusumi (Okinawa Institute of Science and Technology Graduate University)

3597: MTFD : Multi-teacher Fusion Distillation For Compressed Video Action Recognition
Jinxin Guo (Inner Mongolia University)*; Jiaqiang Zhang (Inner Mongolia University); Shaojie Li (Inner
Mongolia University); Xiaojing Zhang (Inner Mongolia University); Ming Ma (Inner Mongolia University)

3602: Mask Guided Selective Context Decoding for Handwritten Chinese Text Recognition
tao li (University of Science and Technology of China)*; shilian wu (University of Science and Technology
of China); Zengfu Wang ( Institute of Intelligent Machines, Chinese Academy of Sciences)

3649: MaskDUL: Data Uncertainty Learning in Masked Face Recognition

Libo Zhang (Southwest University)*; Weiming Xiong (Southwest University); Ku Zhao (SWU); Kehan
Chen (Southwest University); Mingyang Zhong (Southwest University)

3696: Learning 3D Human Pose and Shape Estimation Using Uncertainty-Aware Body Part
Segmentation
Ziming Wang (Fudan University)*; Han Yu (Fudan University); Xiaoguang Zhu (Shanghai Jiao Tong
University); Zengwen Li (Chongqing Changan Automobile Co., Ltd.); Changxue Chen (Chongqing
Changan Automobile Co., Ltd.); Liang Song (Fudan University)

3701: Underwater Image Restoration With Light-Aware Progressive Network

Jian Yang (Northwestern Polytechnical University)*; Chen Li (Northwestern Polytechnical University);
Xuelong Li (Northwestern Polytechnical University)

85
3711: A Simulation-Based Framework for Urban Road Accident Detection
Haohan Luo (East China Normal University); Feng Wang (East China Normal University)*

3730: DUAL-UNCERTAINTY GUIDED CURRICULUM LEARNING AND PART-AWARE FEATURE

REFINEMENT FOR DOMAIN ADAPTIVE PERSON RE-IDENTIFICATION
Zhangping Liu (University of Science and Technology of China); Bin Liu (University of Science and
Technology of China)*; Zhiwei Zhao (University of Science and Technology of China); Qi Chu (University
of Science and Technology of China); Nenghai Yu (University of Science and Technology of China)

3745: TransWnet: Integrating Transformers into CNNs via Row and Column Attention for
Abdominal Multi-organ Segmentation
Yazhen Xie (Xiangtan University); Yanglin Huang (Xiangtan University); Yuan Zhang (Xiangtan
University); Xuanya Li (Baidu); Xiongjun Ye (Xiangtan University); Kai Hu (Xiangtan University)*

3793: LABANet: Lead-Assisting Backbone Attention Network for oral multi-pathology

segmentation
Huabao Chen (Hohai University); Xiaolong Huang (Chongqing University of Technology); Qiankun Li
(USTC); Jianqing Wang (Shanghai International Studies University); bo fang (Northeastern University);
Junxin Chen (Dalian University of Technology)*

3838: Long-tailed Image Recognition with Dynamic Re-weighting

Xinyuan LI (Ritsumeikan University); Yu Wang (Hitotsubashi University)*; Jien Kato (Ritsumeikan
University)

3841: Monocular 3D Human Pose Estimation Based on Global Temporal-Attentive and Joints-
Attention in Video
ruhan He (Wuhan Textile University); shanshan xiang (Wuhan Textile University)*; Tao Peng (Wuhan
Textile University); Yongsheng Yu (武汉理工大学)

3857: A Dynamic Cross-scale Transformer with Dual-compound Representation for 3D Medical

Image Segmentation
Ruixia Zhang (Northeastern University); Zhiqiong Wang (Northeastern University); Zhongyang Wang
(Northeastern University); Junchang Xin (Northeastern University)*

3874: Masked-AP: Attention Pyramid Convolutional Neural Network with mask for Cervical Cell
Classification
yu jin (Institute of Artificial Intelligence, School of Computer Science, Wuhan University); Juan Liu
(Institute of Artificial Intelligence, School of Computer Science, Wuhan University)*; Hua Chen (Institute of
Artificial Intelligence, School of Computer Science, Wuhan University); Wensi Duan (Institute of Artificial
Intelligence, School of Computer Science, Wuhan University); Dehua Cao (Landing Artificial Intelligence
Center for Pathological Diagnosis); Baochuan Pang (Landing Artificial Intelligence Center for Pathological
Diagnosis )

3888: DDN: Dynamic Aggregation Enhanced Dual-stream Network for Medical Image Classification
Lang Wang (Institute of Artificial Intelligence, School of Computer Science, Wuhan University); Juan Liu
(Institute of Artificial Intelligence, School of Computer Science, Wuhan University)*; Peng Jiang (Institute
of Artificial Intelligence, School of Computer Science, Wuhan University); Dehua Cao (Landing Artificial
Intelligence Center for Pathological Diagnosis); Baochuan Pang (Landing Artificial Intelligence Center for
Pathological Diagnosis )

3890: CFFMixer: Multi-dimensional Feature Fusion For Object Detection

Hao Xie (Southeast University); weizhe yuan (Southeast University); Bin Kang (Nanjing University of
Posts and Telecommunication); Songlin Du (Southeast University)*

86
3929: Image Inpainting with Semantic-aware Transformer
Shiyu Chen (Southwest University of Science and Technology); Wenxin Yu (Southwest University of
Science and Technology)*; Qi Wang (Southwest University of Science and Technology); Jun Gong
(Beijing Institute of Technology); Peng Chen (Chengdu Hongchengyun Technology Co., Ltd)

3936: An application of quantum mechanics to attention methods in computer vision

Juntao Zhang (Institute of System Engineering, AMS)*; Yihao Luo (Yichang Testing Technique R&D
Institute); Peng Cheng (Coolanyp LLC); Zehan Li (University of Electronic Science and Technology of
China); Hao Wu (Institute of System Engineering, AMS); Kun Yu ( Institute of System Engineering, AMS );
Wenbo An (Institute of System Engineering, AMS ); Jun Zhou (Institute of System Engineering, AMS)

3941: JOINT TRAINING OF HIERARCHICAL GANS AND SEMANTIC SEGMENTATION FOR

EXPRESSION TRANSLATION
Rumeysa Bodur (Imperial College London)*; Binod Bhattarai (University of Aberdeen); Tae-Kyun Kim
(Imperial College London)

3945: Deep Feature Aggregation for Lightweight Single Image Super-Resolution

Yanchun Li (Xiangtan university); Xinan He (Xiangtan University); Shujuan Tian (Xiangtan University)*;
Zhetao Li (湘潭大学); Saiqin Long (Jinan University)

3959: LOGO-Former: Local-Global Spatio-Temporal Transformer for Dynamic Facial Expression

Recognition
Fuyan Ma (Hunan University); Bin Sun (Hunan University)*; Shutao Li (Hunan University)

3972: Hierarchical Spatiotemporal Feature Fusion Network for Video Saliency Prediction
Yunzuo Zhang (Shijiazhuang Tiedao University)*; Tian Zhang (Shijiazhuang Tiedao University); Cunyu
Wu (Shijiazhuang Tiedao University); Yuxin Zheng (Shijiazhaung Tiedao University)

3983: BODY PRIOR GUIDED GRAPH CONVOLUTIONAL NEURAL NETWORK FOR SKELETON-
BASED ACTION RECOGNITION
Qianshuo Hu (Chongqing university of technology); Hong Liu (Peking University Shenzhen Graduate
School); Hua-qiu Wang ( Chongqing University of Technology); Mengyuan Liu (Peking University,
Shenzhen Graduate School)*

3986: A highly Interpretable Deep equilibrium network for hyperspectral image deconvolution
Alexandros Gkillas (University of Patras)*; Dimitris Ampeliotis (Digital Media and Communication
Department, Ionian University, Greece); Kostas Berberidis (University of Patras)

3993: MPE4G : Multimodal Pretrained Encoder for Co-Speech Gesture Generation

Gwantae Kim (Korea University)*; Seonghyeok Noh (Korea University); Insung Ham (Korea University);
Hanseok Ko (Korea University)

4008: STEREOSCOPIC VIDEO RETARGETING BASED ON CAMERA MOTION CLASSIFICATION

Linghui Cai (Guangxi University); Zhenhua Tang (Guangxi University)*

4028: Unsupervised Feature Selection with Self-Weighted and L2,0-norm Constraint

Yongjin Yuan (Northwestern Polytechnical University)*; Zheng Wang (Xi'an Jiaotong University); Feiping
Nie (Northwestern Polytechnical University); Xuelong Li (Northwestern Polytechnical University)

4036: D-3DLD: Depth-aware Voxel Space Mapping for Monocular 3D Lane Detection with
Uncertainty
Nayeon Kim (Samsung Electronics)*; Moonsub Byeon (Samsung Electronics); Daehyun Ji (Samsung
Electronics); Dokwan Oh (Samsung Electronics)

87
4037: Recurrent Fine-Grained Self-Attention Network for Video Crowd Counting
Jifan Zhang (School of Electronic and Computer Engineering, Peking University); Zhe Wu (Peng Cheng
Laboratory); xinfeng zhang (University of Chinese Academy of Sciences); Guoli Song (Peng Cheng
Laboratory); Yaowei Wang (PengCheng Laboratory); Jie Chen (Peking University)*

4046: LOCAL-GLOBAL SIAMESE NETWORK WITH EFFICIENT INTER-SCALE FEATURE LEARNING

FOR CHANGE DETECTION IN VHR REMOTE SENSING IMAGES
Yue Zhang (Shaanxi University of Science and Technology); Tao Lei (Shaanxi University of Science and
Technology)*; Shaoxiong Han (Norinco Group Testing And Research institute); Yetong Xu (Shaanxi
University of Science and Technology); Asoke K Nandi (Brunel University London)

4057: WavSyncSwap: End-to-End Portrait-Customized Audio-Driven Talking Face Generation

Weihong Bao (Tsinghua University)*; Liyang Chen (Tsinghua University); Chaoyong Zhou (Ping An
Technology); Sicheng Yang (Tsinghua University); Zhiyong Wu (Tsinghua University)

4090: Gated Enhanced RPN and Hybrid-View for Few-Shot Object Detection
Xujun Wei (Fudan University); Zechu Zhou (Academy of Engineering and Technology, Fudan University);
Pinxue Guo (Fudan University); Wenqiang Zhang (Fudan University)*

4113: Vehicle View Synthesis by Generative Adversarial Network

Chan-Shuo Hu (National Chung-Cheng University); Sung-Wei Tseng (National Chung Cheng University);
Xin-Yun Fan (National Chung Cheng University); Chen-Kuo Chiang (National Chung Cheng University)*

4168: DO-FAM: Disentangled Non-Linear Latent Navigation for Facial Attribute Manipulation
Yifan Yuan (Fudan University)*; Siteng Ma (Fudan University); Hongming Shan (Fudan University);
Junping Zhang (Fudan University)

4175: Stochastic super-resolution for Gaussian textures

Emile Pierret (Institut Denis Poisson)*; Bruno Galerne (University of Orléans)

4199: Efficient Practices for Profile-to-Frontal Face Synthesis and Recognition

Huijiao Wang (Wuhan University)*; Xulei Yang (Institute for Infocomm Research (I2R), A*STAR)

4208: LEARNING CAUSAL REPRESENTATIONS FOR GENERALIZABLE FACE ANTI SPOOFING

Guanghao Zheng (Shanghai Jiao Tong University)*; Yuchen Liu (Shanghai Jiao Tong university); Wenrui
Dai (Shanghai Jiao Tong University); Chenglin Li (Shanghai Jiao Tong University); Junni Zou (Shanghai
Jiao Tong University); Hongkai Xiong (Shanghai Jiao Tong University)

4235: HIERARCHICAL INTERACTIVE RECONSTRUCTION NETWORK FOR VIDEO COMPRESSIVE

SENSING
Tong Zhang (Harbin Institute of Technology)*; Wenxue Cui (Harbin Institute of Technology); Chen Hui
(Harbin Institute of Technology); Feng Jiang (Harbin Institute of Technology, Harbin)

4237: Time-Frequency Awareness Network for Human Mesh Recovery from Videos
Boyang Zhang (Ningxia University); Suping Wu (Ningxia University)*; Meining Jia (NingXia University)

4254: QUATERNION ORTHOGONAL TRANSFORMER FOR FACIAL EXPRESSION RECOGNITION IN

THE WILD
Yu Zhou (Huazhong University Of Science And Technology)*; Liyuan Guo (Huazhong University of
Science and Technology); Lianghai Jin (Huazhong University of Science and Technology)

88
4263: COLOR GUIDED DEPTH MAP SUPER-RESOLUTION WITH NONLOCLA AUTOREGRESSIVE
MODELING
Wei Xu (Faculty of Information Technology, Beijing University of Technology)*; Na Qi (Beijing University of
Technology); Qing Zhu (Beijing University of Technology); Jingzhong Qi (Beijing University of
Technology); Longlu Huang (Beijing University of Technology); Kun Cao (Beijing University of
Technology); Yuxin Bao (Beijing University of Technology); Qianwen Wang (Beijing university of
technology)

4291: Ontology-Aware Network for Zero-Shot Sketch-based Image Retrieval

Haoxiang Zhang (School of Information and Control, China University of Mining and Technology)*; He
Jiang (School of Information and Control, China University of Mining and Technology); Ziqiang Wang
(School of Information and Control, China University of Mining and Technology); Deqiang Cheng (School
of Information and Control, China University of Mining and Technology)

4300: An Auto-Encoder Based Method for Camera Fingerprint Compression

Kaixuan Zhang (Shanghai Jiao Tong University)*; Zihan Liu (Shanghai Jiao Tong University); Jiashang Hu
(Shanghai Jiao Tong University); shilin wang (SEIEE, Shanghai Jiaotong University)

4301: COMBINING LOSS REWEIGHTING AND SAMPLE RESAMPLING FOR LONG-TAILED

INSTANCE SEGMENTATION
Yaochi Zhao (Hainan University); Sen Chen (Hainan University); Qiong Chen (Hainan University); Zhuhua
Hu (Hainan University)*

4310: Could the BubbleView metaphor be used to infer visual attention on 3D graphical content ?
Alexandre Bruckert (Nantes Université)*; Mona Abid (Nantes université); Matthieu Perreira Da Silva
(Université de Nantes); Patrick Le Callet ("Universite de Nantes, France")

4314: Multi-dimensional Signal Recovery using Low-rank Deconvolution

David Reixach (Universitat Politècnica de Catalunya, BarcelonaTech)*

4359: Test your samples jointly: Pseudo-reference for image quality evaluation
Marcelin Tworski (Telecom Paris)*; Stéphane Lathuilière (Telecom-Paris)

4370: SEMANTIC CENTRALIZED CONTRASTIVE LEARNING FOR UNSUPERVISED HASHING

Fengming Liang (Beijing University of Posts and Telecommunications); Changlin Fan (Beijing University
of Posts and Telecommunications); Bo Xiao (Beijing University of Posts and Telecommunications)*;
Kongming Liang (Beijing University of Posts and Telecommunications)

4380: EVOPOSE: A RECURSIVE TRANSFORMER FOR 3D HUMAN POSE ESTIMATION WITH

KINEMATIC STRUCTURE PRIORS
Yaqi Zhang (University of Science and Technology of China); Yan Lu (University of Sydney); Bin Liu
(University of Science and Technology of China)*; Zhiwei Zhao (University of Science and Technology of
China); Qi Chu (University of Science and Technology of China); Nenghai Yu (University of Science and
Technology of China)

4414: DENSITYTOKEN: WEAKLY-SUPERVISED CROWD COUNTING WITH DENSITY

CLASSIFICATION
Zaiyi Hu (Northwestern Polytechnical University); Binglu Wang (Northwestern Polytechnical University)*;
Xuelong Li (Northwestern Polytechnical University)

4420: Towards Realizing the Value of Labeled Target Samples: a Two-Stage Approach for Semi-
Supervised Domain Adaptation
Mengqun Jin (Tsinghua University); Kai Li (NEC LABORATORIES AMERICA, INC); SHUYAN LI
(University of Cambridge); Chunming He (Tsinghua University); Xiu Li (Tsinghua University)*

89
4440: Learning how to learn domain-invariant parameters for domain generalization
Feng Hou (University of Chinese Academy of Sciences)*; Yao Zhang (Shanghai AI Lab); Yang Liu
(Institute of Computing Technology, University of Chinese Academy of Sciences, Lenovo AI Lab); Jin
Yuan (Southeast University); Cheng Zhong (Lenovo Research, AI Lab); Yang Zhang (Lenovo Ltd);
zhongchao shi (lenovo company); Jianping Fan (Lenovo); Zhiqiang He (Lenovo Ltd.)

4464: LEARNING ON ENTROPY CODED IMAGES WITH CNN

Rémi Piau (INRIA)*; Thomas Maugey (INRIA); Aline Roumy (INRIA)

4544: Synthetic Pseudo Anomalies for Unsupervised Video Anomaly Detection: A Simple yet
Efficient Framework based on Masked Autoencoder
Xiangyu Huang (School of informatics Xiamen University)*; Caidan Zhao (School of Informatics Xiamen
University); Chenxing Gao (xiamen university); Chen Lvdong (xiamen university); Zhiqiang Wu (Wright
State University)

4549: Weakly-Supervised Scene-Specific Crowd Counting Using Real-Synthetic Hybrid Data

Yaowu Fan (Northwestern Polytechnical University); Jia Wan (University of California, San Diego); Yuan
Yuan (Northwestern Polytechnical University); Qi Wang (Northwestern Polytechnical University)*

4553: Semi-Supervised Domain Generalization with Graph-based Classifier

Minxiang Ye (Zhejianglab); Yifei Zhang (Zhejiang lab)*; Shiqiang Zhu (Zhejiang Lab); Anhuan Xie
(ZhejiangLab, Zhejiang University); Senwei Xiang (ZhejiangLab)

4590: IMAGE SEGMENTATION FOR IMPROVED LOSSLESS SCREEN CONTENT COMPRESSION

Shabhrish Reddy Reddy Uddehal (Coburg University)*; Tilo Strutz (Coburg University); Hannah Och
(Friedrich-Alexander University Erlangen-Nürnberg); Andre Kaup (Friedrich-Alexander-Universität
Erlangen-Nürnberg)

4607: A Video Anomaly Detection Framework based on Appearance-Motion Semantics

Representation Consistency
Xiangyu Huang (School of informatics Xiamen University)*; Caidan Zhao (School of Informatics Xiamen
University); Zhiqiang Wu (Wright State University)

4667: GATOR: GRAPH-AWARE TRANSFORMER WITH MOTION-DISENTANGLED REGRESSION

FOR HUMAN MESH RECOVERY FROM A 2D POSE
Yingxuan You (Peking University); Hong Liu (Peking University Shenzhen Graduate School)*; Xia Li (ETH
Zurich); Wenhao Li (Peking University); Ti Wang (Peking University Shenzhen Graduate School); Runwei
Ding (Peking University Shenzhen Graduate School)

4690: Collaborative Audio-Visual Event Localization based on Sequential Decision and Cross-
modal Consistency
Yuqian Kuang (Harbin Institute of Technology)*; Xiaopeng Fan (Harbin Institute of Technology)

4692: REPETITION COUNTING FROM COMPRESSED VIDEOS USING SPARSE RESIDUAL

SIMILARITY
Rishabh Khurana (Samsung Research, Bangalore)*; Jayesh Rajkumar Vachhani (Samsung R&D Institute
Bengaluru); Sourabh Vasant Gothe (SAMSUNG R&D INSTITUTE BANGALORE, KARNATAKA, INDIA);
Pranay Kashyap (Samsung Research Institute Bangalore)

4693: Clean Sample Guided Self-Knowledge Distillation For Image Classification

Jiyue Wang (South China University of Technology); Yanxiong Li (South China University of Technology);
Qianhua He (SOUTH CHINA UNIVERSITY OF TECHNOLOGY)*; Wei Xie (South China University of
Technology)

90
4696: LGViT: Local-Global Vision Transformer for Breast Cancer Histopathological Image
Classification
Lang Wang (Institute of Artificial Intelligence, School of Computer Science, Wuhan University); Juan Liu
(Institute of Artificial Intelligence, School of Computer Science, Wuhan University)*; Peng Jiang (Institute
of Artificial Intelligence, School of Computer Science, Wuhan University); Dehua Cao (Landing Artificial
Intelligence Center for Pathological Diagnosis); Baochuan Pang (Landing Artificial Intelligence Center for
Pathological Diagnosis)

4708: ENABLING LARGE-SCALE IMAGE SEARCH WITH CO-ATTENTION MECHANISM

Zechao Hu (University of York)*; Adrian Bors (University of York)

4719: FEW BUT INFORMATIVE LOCAL HASH CODE MATCHING FOR IMAGE RETRIEVAL
Zechao Hu (University of York)*; Adrian Bors (University of York)

4730: Dynamic Scalable Self-Attention Ensemble for Task-Free Continual Learning

Fei Ye (University of york)*; Adrian Bors (University of York)

4748: Compressing Cross-Domain Representation via Lifelong Knowledge Distillation

Fei Ye (University of york)*; Adrian Bors (University of York)

4755: SELF-SIMILARITY IS ALL YOU NEED FOR FAST AND LIGHT-WEIGHT GENERIC EVENT
BOUNDARY DETECTION
Sourabh Vasant Gothe (SAMSUNG R&D INSTITUTE BANGALORE, KARNATAKA, INDIA)*; Jayesh
Rajkumar Vachhani (Samsung R&D Institute Bengaluru); Rishabh Khurana (Samsung Research,
Bangalore); Pranay Kashyap (Samsung Research Institute Bangalore)

4803: Efficient Feature Extraction for Non-Maximum Suppression in Visual Person Detection
Charalampos Symeonidis (AUTH)*; Ioannis Mademlis (Department of Informatics, Aristotle University of
Thessaloniki); Ioannis Pitas (Aristotle University of Thessaloniki); Nikolaos Nikolaidis (Aristotle University
of Thessaloniki)

4814: Cov loss: Covariance-based Loss for Deep Face Recognition

Ibrahim Alkanhal (Carnegie Mellon University)*; Abdullah Almansour (National Center for Artificial
Intelligence); Lamia Alsalloom (National Center for Artificial Intelligence); Raied Aljadaany (National
Center for Artificial Intelligence); Marios Savvides (Carnegie Mellon University)

4836: Motion Matters: A Novel Motion Modeling For Cross-View Gait Feature Learning
Jingqi Li (Fudan University); Jiaqi Gao (Fudan University); Yuzhen Zhang (Fudan University); Hongming
Shan (Fudan University); Junping Zhang (Fudan University)*

4867: Automatic Error Detection in Integrated Circuits Image Segmentation: A Data-driven

Approach
Zhikang Zhang (Arizona State University)*; Bruno Trindade (TechInsights Inc.); Michael Green
(TechInsights Inc.); Zifan Yu (Arizona State University); Christopher Pawlowicz (TechInsights Inc.);
Fengbo Ren (Arizona State University)

4890: Comprehensive Complexity Assessment of Emerging Learned Image Compression on CPU

And GPU
Farhad Pakdaman (Tampere University)*; Moncef Gabbouj (Tampere University)

4893: Detail-aware Uncalibrated Photometric Stereo

Antonio Agudo (Institut de Robotica i Informatica Industrial, CSIC-UPC)*

4951: Multimodal Facial Action Unit Detection with Physiological Signals

Zhihua Li (Binghamton University)*; Lijun Yin (State University of New York at Binghamton)

91
4957: Soft 2D-to-3D Delivery Using Deep Graph Neural Networks for Holographic-Type
Communication
Takuya Fujihashi (Osaka University)*; Toshiaki Koike-Akino (Mitsubishi Electric Research Laboratories);
Takashi Watanabe (Osaka University)

5095: GRAPH WAVELET-BASED POINT CLOUD GEOMETRIC DENOISING WITH SURFACE-

CONSISTENT NON-NEGATIVE KERNEL REGRESSION
Ryosuke Watanabe (KDDI Research, Inc.)*; Keisuke Nonaka (KDDI Research Inc.); Eduardo Pavez
(University of Southern California); Tatsuya Kobayashi (KDDI Research Inc.); Antonio Ortega (University
of Southern California)

5121: Efficient and Effective Multi-Camera Pose Estimation with Weighted M-Estimate Sample
Consensus
Xinyu Lin (University of Electronic Science and Technology of China)*; Yingjie Zhou (Sichuan University);
Xun Zhang (Institut superieur d’electronique de Paris - ISEP); Yipeng Liu (University of Electronic Science
and Technology of China); Ce Zhu (University of Electronic Science & Technology of China)

5144: Level-line Guided Edge Drawing for Robust Line Segment Detection
Xinyu Lin (University of Electronic Science and Technology of China)*; Yingjie Zhou (Sichuan University);
Yipeng Liu (University of Electronic Science and Technology of China); Ce Zhu (University of Electronic
Science & Technology of China)

5157: TENSOR LOWRANK COLUMN-WISE COMPRESSIVE SENSING FOR DYNAMIC IMAGING

Silpa Babu (IOWA STATE UNIVERSITY)*; Selin Aviyente (Michigan State University); Namrata Vaswani
(Iowa State University)

5185: Multi-Modal Approach to Food Classification Diet Tracking System with spoken and visual
inputs
Shivani Gowda Kallappanahalli (Loyola Marymount University); Yifan Hu (Loyola Marymount University);
Mandy B Korpusik (Loyola Marymount University)*

5194: CROSS-MODAL MATCHING AND ADAPTIVE GRAPH ATTENTION NETWORK FOR RGB-D
SCENE RECOGNITION
Yuhui Guo (Renmin University of China)*; Xun Liang (Renmin University of China); james kwok (The
Hong Kong University of Science and Technology); Xiangping Zheng (Renmin University of China); Bo
Wu (Renmin University of China); Yuefeng Ma (Qufu Normal University)

5200: Exploring Progressive Hybrid-degraded Image Processing for Homography Estimation

Yijun Lin (University of Chinese Academy of Sciences)*; Xingzhe Su (Institute of Software Chinese
Academy of Sciences); Fengge Wu (Institute of Software Chinese Academy of Sciences); Junsuo Zhao
(Science and Technology on Integrated Information System Laboratory Institute of Software Chinese
Academy of Sciences)

5267: GRAPH-BASED POINT CLOUD COLOR DENOISING WITH 3-DIMENSIONAL PATCH-BASED

SIMILARITY
Ryosuke Watanabe (KDDI Research, Inc.)*; Keisuke Nonaka (KDDI Research Inc.); Eduardo Pavez
(University of Southern California); Tatsuya Kobayashi (KDDI Research Inc.); Antonio Ortega (University
of Southern California)

5280: Boundary Cue Guidance and Contextual Feature Mining for Glass Segmentation
Qiquan Xiao (Xiangtan University); Yuan Zhang (Xiangtan University); Xuanya Li (Baidu); Kai Hu
(Xiangtan University)*

92
5283: Dynamic Local and Global Context Exploration For Small Object Detection
Ziji Zhang (Beijing University of Posts and Telecommunications)*; Ping Gong (Beijing University of Posts
and Telecommunications); Haotian Sun (Beijing University of Posts and Telecommunications); Pingping
Wu (Beijing University of Posts and Telecommunications); Xuanyuan Yang (Beijing University of Posts
and Telecommunications)

5286: 3D Point Cloud Completion based on Multi-Scale Degradation

long jianing (Institute of Software, Chinese Academy of Sciences); Hao He (Institute of Software, Chinese
Academy of Sciences)*; Qingmeng Zhu (Institute of Software, Chinese Academy of Sciences); Zhipeng
Yu (Institute of Software, Chinese Academy of Sciences); Qilin Zhang (Institute of Software, Chinese
Academy of Sciences); Zhihong Zhang (Kunming University of Science and Technology)

5304: MOTION-AWARE VIDEO PARAGRAPH CAPTIONING VIA EXPLORING OBJECT-CENTERED

INTERNAL KNOWLEDGE
hu yimin (Fudan University); Guorui Yu (Fudan University); Yuejie Zhang (Fudan University)*; Rui Feng
(Fudan University); Tao Zhang (Shanghai University of Finance and Economics); Xuequan Lu (Deakin
University); Shang Gao (Deakin University)

5309: RECURSIVE JOINT ATTENTION FOR AUDIO-VISUAL FUSION IN REGRESSION BASED

EMOTION RECOGNITION
Gnana Praveen Rajasekhar (Ecole Technologie Superieure)*; Eric Granger (ETS Montreal ); Patrick
Cardinal (École de technologie supérieure)

5313: Toward Auto-evaluation with Confidence-based Category Relation-aware Regression

Jiexin Wang (Renmin University of China); Jiahao Chen (Renmin University of China); Bing Su (Renmin
University of China)*

5432: ON DESIGNING LIGHT-WEIGHT OBJECT TRACKERS THROUGH NETWORK PRUNING: USE

CNNS OR TRANSFORMERS?
Saksham Aggarwal (IIT (ISM) Dhanbad)*; Taneesh Gupta (Indian Institute of Technology,Dhanbad);
Pawan Kumar Sahu (IIT Dhanbad); Arnav Santosh Chavan (Indian Institute of Technology - Dhanbad);
Rishabh Tiwari (Google Research, India); Dilip K Prasad (UiT The Arctic University of Norway); Deepak K
Gupta (UiT The Arctic University of Norway)

5479: A PROGRESSIVE IMAGE DEHAZING FRAMEWORK WITH INTER AND INTRA CONTRASTIVE
LEARNING
honglei xu (Harbin Institute of Technology); Shaohui Liu (Harbin Institute of Technology)*; Yan Shu (State
Key Laboratory of Communication Content Cognition, People`s Daily Online, Beijing, China; Harbin
Institute of Technology; Institute of Information Engineering, CAS ); Feng Jiang (Harbin Institute of
Technology, Harbin)

5489: DMFormer: Closing the Gap between CNN and Vision Transformers
Zimian Wei (School of Computer Science, National University of Defense Technology); Hengyue Pan
(National University of Defense Technology)*; Lujun Li (Chinese Academy of Sciences); MengLong Lu
(National University of Defense Technology); Xin Niu (NUDT); Peijie Dong (School of Computer Science,
National University of Defense Technology); Dongsheng Li (School of Computer Science, National
University of Defense Technology)

5538: real-time Human reconstruction based on human pose prior and epipolar refinement
Kuncheng Luo (Tsinghua University)*; Zhiheng Li (Tsinghua University)

5567: INFORMATION EXTRACTION FROM PILL BOTTLE IMAGES VIA TEXT STITCHING
Rahul Kumar Gupta (Walmart Global Tech)*; Shilka Roy (Walmart); Sujit Jos (Walmart Global Tech); Unni
V.S. (Walmart Global Tech); Lauren Lavoie (Walmart Global Tech); Frederic Medous (Walmart Global
Tech); Walter Smith (Walmart Global Tech)

93
5569: No reference quality assessment for screen content images based on entire and high-
influence regions
Zhuoran Xu (Anhui University); Yang Yang (Anhui University)*; Zhixiang Zhang (Hefei High-Dimensional
Data Technology Co.,Ltd); Weiming Zhang (University of Science and Technology of China)

5574: Enhanced DCF Tracker Regularized by Reliable Sample Construction

Kun Hu (National University of Defense Technology)*; Mingyu Cao (NUDT); Mengzhu Wang (NUDT); long
lan (NUDT); Wenjing Yang (National University of Defense Technology); Huibin Tan (NUDT)

5583: LEARNING A WEIGHT MAP FOR WEAKLY-SUPERVISED LOCALIZATION

Tal Shaharbany (Tel Aviv University)*; Lior Wolf (Tel Aviv University, Israel)

5586: Pyramid Spatial Feature Transform And Shared-Offsets Deformable Alignment Based
Convolutional Network for HDR Imaging
Junda Liao (Nanjing University; Waseda University); Qin Liu (Nanjing University)*; Takeshi Ikenaga
(Waseda University)

5663: EI2SR: LEARNING AN ENHANCED INTRA-INSTANCE SEMANTIC RELATIONSHIP FOR

ARBITRARY-SHAPED SCENE TEXT DETECTION
Yan Shu (State Key Laboratory of Communication Content Cognition, People`s Daily Online, Beijing,
China; Harbin Institute of Technology; Institute of Information Engineering, CAS ); Shaohui Liu (Harbin
Institute of Technology)*; Yu Zhou (Institute of Information Engineering, CAS; Also with University of
Chinese Academy of Sciences); honglei xu (Harbin Institute of Technology); Feng Jiang (Harbin Institute
of Technology, Harbin)

5668: AMPose: Alternately Mixed Global-Local Attention Model for 3D Human Pose Estimation
Hong-Xin Lin (National Taiwan University)*; Yun-Wei Chiu (National Taiwan University); Pei-Yuan Wu
(National Taiwan University)

5674: Boosting Face Recognition Performance with Synthetic Data and Limited Real Data
Wenqing Wang (University of Macau)*; Lingqing Zhang (University of Macau); Chi-Man Pun (University of
Macau); Jiucheng Xie (Nanjing University of Posts and Telecommunications)

5684: A Deep Fusion Rule for Infrared and Visible Image Fusion: Feature Communication for
Importance Assessment
Xuran Lv (Qilu University of Technology(Shandong Academy of Sciences)); Jinyong Cheng (Qilu
University of Technology(Shandong Academy of Sciences) )*; Guohua Lv (Qilu Universityof
Technology (Shandong Academy of Sciences)); Zhonghe Wei (Qilu University of Technology (Shandong
Academy of Sciences))

5685: Optimal Kernel for Real-Time Arbitrary-Shaped Text Detection

Haozhao Ma (Northwestern Polytechnical University); Chuang Yang (Northwestern Polytechnical
University); Yuan Yuan (Northwestern Polytechnical University); Qi Wang (Northwestern Polytechnical
University)*

5694: RATE-DISTORTION OPTIMIZATION WITH ALTERNATIVE REFERENCES FOR UGC VIDEO

COMPRESSION
Xin Xiong (University of Southern California)*; Eduardo Pavez (University of Southern California); Antonio
Ortega (University of Southern California); Balu Adsumilli (YouTube/Google)

5696: MDR-MFI:Multi-Branch Decoupled Regression and Multi-Scale Feature Interaction for

Partial-to-Partial Cloud Registration
Weidong Dai (Hikvision Research Institute)*; Xuejun Yan (Hikvision Research Institue); Jingjing Wang
(Hikvision Research Institute); Di Xie (Hikvision Research Institute); Shiliang Pu (Hikvision Research
Institute)

94
5699: STATIC-SCENE CONSTRAINED OPTIMIZATION FOR MATRIX/TENSOR-DECOMPOSITION-
FREE FOREGROUND-BACKGROUND SEPARATION
Kazuki Naganuma (Tokyo Institute of Technology)*; Shunsuke Ono (Tokyo Institute of Technology)

5708: KEPS-NET: Robust Parking Slot Detection based Keypoint Estimation for High Localization
Accuracy
Jaewoo Lee ( Samsung Electronics)*; Kapje Sung (Samsung Electronics); Daeul Park (Samsung
Electronics); Younghan Jeon (Seoul National University)

5712: SDRNet: Shape Decoupled Regression Network for 3D Face Reconstruction

Shikun Zhang (Nanjing Normal University)*; Fengyi Song (Nanjing Normal University); GE SONG
(Nanjing Normal University); Ming Yang (Nanjing Normal University)

5713: Low in Resolution, High in Precision: UAV Detection with Super-Resolution and Motion
Information Extraction
Hanzhuo Wang (Zhejiang University)*; Xingjian Wang (Zhejiang University); Chengwei Zhou (Zhejiang
University); Wenchao Meng (Zhejiang University); Zhiguo Shi (Zhejiang University)

5735: Unsupervised Action Segmentation of Untrimmed Egocentric Videos

Sam Perochon (Ecole Normale Supérieure Paris-Saclay)*; Laurent Oudre (ENS Paris-Saclay)

5750: FLOWPOSE: CONDITIONAL NORMALIZING FLOWS FOR 3D HUMAN POSE AND SHAPE
ESTIMATION FROM MONOCULAR VIDEOS
Yaoyao Du (Tsinghua University)*; Zixiao Zhang (Huawei); Zhihao Li (Huawei Noah's Ark Lab); Peng Wei
(Huawei Device BG); Qingmin Liao (Tsinghua Univeristy); Wenming Yang (Tsinghua University)

5753: Random Projector: Efficient Deep Image Prior

Taihui Li (University of Minnesota)*; Zhong Zhuang (University of Minnesota); Hengkang Wang (University
of Minnesota); Ju Sun (University of Minnesota)

5755: Background-Weakening Consistency Regularization for Semi-Supervised Video Action

Detection
Xian Zhong (Wuhan University of Technology); Aoyu Yi (Wuhan University of Technology); Wenxuan Liu
(Wuhan University of Technology)*; Wenxin Huang (Hubei University); Chengming Zou (Wuhan University
of Technology); Zheng Wang (Wuhan University)

5771: OPTIMIZED QUALITY FEATURE LEARNING FOR VIDEO QUALITY ASSESSMENT

Ngai-Wing Kwong (The Hong Kong Polytechnic University)*; Yui-Lam Chan ( The Hong Kong Polytechnic
University ); Sik-Ho Tsang (Centre for Advances in Reliability and Safety (CAiRS)); Daniel P.K. Lun (The
Hong Kong Polytechnic University)

5794: EXPLOITING 3D HUMAN RECOVERY FOR ACTION RECOGNITION WITH SPATIO-TEMPORAL

BIFURCATION FUSION
Na Jiang (Information Engineering College, Capital Normal University); Wei Quan (Capital Normal
University); Qichuan Geng (Capital Normal University); Zhiping Shi (Capital Normal University); Peng Xu
(Capital Normal University)*

5802: JOINT COMPRESSION AND DEMOSAICKING FOR SATELLITE IMAGES

Pascal Bacchus (INRIA)*; Renaud Fraisse (Airbus); Aline Roumy (INRIA); Christine Guillemot (INRIA)

5827: Background Disturbance Mitigation for Video Captioning via Entity-Action Relocation
Zipeng Li (Wuhan University of Technology); Xian Zhong (Wuhan University of Technology); Shuqin Chen
(Hubei University of Education)*; Wenxuan Liu (Wuhan University of Technology); Wenxin Huang (Hubei
University); Lin Li (Wuhan University of Technology)

95
5841: Joint Multi-Level Feature Network for Lightweight Person Re-Identification
Yunzuo Zhang (Shijiazhuang Tiedao University)*; Weili Kang (Shijiazhuang Tiedao University); Yameng
Liu (Shijiazhuang Tiedao University); Pengfei Zhu (Shijiazhuang Tiedao University)

5844: ACTIVE PERCEPTION SYSTEM FOR ENHANCED VISUAL SIGNAL RECOVERY USING DEEP
REINFORCEMENT LEARNING
Gaurav Chaudhary (Indian Institute of Technology Kanpur, India)*; Prof Laxmidhar Behera (IIT Kanpur);
Tushar Sandhan (Indian Institute of Technology Kanpur)

5876: Classifying Pathological Images Based on Multi-Instance Learning and End-to-End Attention
Pooling
Yuqi Chen (Institute of Artificial Intelligence, School of Computer Science, Wuhan University); Juan Liu
(Institute of Artificial Intelligence, School of Computer Science, Wuhan University)*; Zhiqun Zuo (Institute
of Artificial Intelligence, School of Computer Science, Wuhan University); Peng Jiang (Institute of Artificial
Intelligence, School of Computer Science, Wuhan University); Yu Jin (Institute of Artificial Intelligence,
School of Computer Science, Wuhan University); Guangsheng Wu (School of Mathematics and Computer
Science, Xinyu University)

5941: Robust Autoencoders for Collective Corruption Removal

Taihui Li (University of Minnesota)*; Hengkang Wang (University of Minnesota); Le Peng (University of
Minnesota); XianE Tang (University of Minnesota Duluth); Ju Sun (University of Minnesota)

5955: YOLOX-B: A BETTER YOLOX MODEL FOR REAL-TIME DRIVER BEHAVIOR DETECTION
Xu Guo (Inner Mongolia University)*; Ming Ma (Inner Mongolia University); Jiaqiang Zhang (Inner
Mongolia University); Shaojie Li (Inner Mongolia University)

5974: Rain2Avoid: Self-supervised Single Image Deraining

Yan-Tsung Peng (National Chengchi University)*; Wei Hua Li (National Chengchi University)

6013: ROBUST CONTENT-VARIANT REFERENCE IMAGE QUALITY ASSESSMENT VIA SIMILAR

PATCH MATCHING
Wenbo Shi (Tsinghua University)*; Wenming Yang (Tsinghua University); Qingmin Liao (Tsinghua
Univeristy)

6015: Neighborhood Information-Based Label Refinement for Person Re-Identification with Label
Noise
Xian Zhong (Wuhan University of Technology); Shuaipeng Su (Wuhan University of Technology);
Wenxuan Liu (Wuhan University of Technology)*; Xuemei Jia (Wuhan University); Wenxin Huang (Hubei
University); Mengdie Wang (Wuhan University Of Technology)

6029: End-to-End Non-Autoregressive Image Captioning

Hong Yu (Dalian University of Technology); Yuanqiu Liu (Dalian University of Technology); BaoKun Qi
(Dalian University of Technology); Zhaolong Hu (Dalian University of Technology); Han Liu (Dalian
University of Technology)*

6050: Animal Re-identification Algorithm for Posture Diversity

zhimin he (Ningbo University); Jiangbo Qian (Ningbo University)*; Yan Diqun (Ningbo University); Chong
Wang (Ningbo University); Yu Xin (Ningbo University)

6056: PCQA-GRAPHPOINT: EFFICIENT DEEP-BASED GRAPH METRIC FOR POINT CLOUD

QUALITY ASSESSMENT
Marouane Tliba (University of Orleans)*; Aladine Chetouani (Université d'Orléans, France); Giuseppe
Valenzise (CNRS); Frederic Dufaux (CNRS)

96
6067: Classification-based Dynamic Network for Efficient Super-Resolution
Qi Wang (Beijing Jiaotong University); Weiwei Fang (Beijing Jiaotong University)*; Meng Wang (Beijing
Jiaotong University); Yusong Cheng (Beijing Jiaotong University)

6106: Decomposition, Interaction, Reconstruction Meets Global Context Learning in Visual

Tracking
Huibin Tan (NUDT); Kun Hu (National University of Defense Technology)*; Mingyu Cao (NUDT); Mengzhu
Wang (NUDT); liyang xu (National University of Defense Technology); Wenjing Yang (National University
of Defense Technology)

6147: ADAPTIVE SEMANTIC FUSION FRAMEWORK FOR UNSUPERVISED MONOCULAR DEPTH

ESTIMATION
Ruoqi Li (University of Electronic Science and Technology of China)*; huimin yu (uestc); du kaiyang
(uestc); Zhuoling Xiao (University of Electronic Science and Technology of China); Bo Yan (University of
Electronic Science and Technology of China); zhengxi yuan (university of electronic science and
technology of china)

6158: SigVIC: Spatial Importance Guided Variable-Rate Image Compression

Jiaming Liang (Beijing Jiaotong University); Meiqin Liu (Beijing Jiaotong University)*; Chao Yao
(University of Science and Technology, Beijing); Chunyu Lin (Beijing Jiaotong University); Yao Zhao
(Beijing Jiaotong University)

6198: AV-TAD: AUDIO-VISUAL TEMPORAL ACTION DETECTION WITH TRANSFORMER

Yangcheng Li (Shanghai Jiao Tong University)*; Zefang Yu (Shanghai Jiao Tong University); Suncheng
Xiang (Shanghai Jiao Tong University); Ting Liu (Shanghai Jiao Tong University); Yuzhuo Fu (sjtu)

6215: Pondering about Task Spatial Misalignment: Classification-Localization Equilibrated Object

Detection
Yudong Zhang (University of Science and Technology of China); Wei Lu (University of Science and
Technology of China); Xu Wang (University of Science and Technology of China); Pengkun Wang
(University of Science and Technology of China); Yang Wang (University of Science and Technology of
China)*

6223: Free-view Expressive Talking Head Video Editing

Yuantian Huang (University of Tsukuba)*; Satoshi Iizuka (University of Tsukuba); Kazuhiro Fukui
(University of Tsukuba)

6235: Towards Privacy and Utility in Tourette Tic Detection Through Pretraining Based on Publicly
Available Video Data of Healthy Subjects
Nele Sophie Brügge (Universität zu Lübeck)*; Esfandiar Mohammadi (Universität zu Lübeck); Alexander
Münchau (Universität zu Lübeck); Tobias Bäumer (Universität zu Lübeck); Christian Frings (Universität
Trier); Christian Beste (Technische Universität Dresden); Veit Roessner (Technische Universität Dresden);
Heinz Handels (University of Lübeck)

6284: MEMORY-AUGMENTED CONTRASTIVE LEARNING FOR TALKING HEAD GENERATION

Jianrong Wang (School of Computer Science and Technology, Tianjin University, Tianjin, China); Yaxin
Zhao (Tianjin International Engineering Institute, Tianjin University, Tianjin, China); Hongkai Fan (School
of Computer Science and Technology, Tianjin University, Tianjin, China); Tianyi Xu (Tianjin University); Qi
Li (School of Electrical and Information Engineering, Tianjin University, Tianjin, China); Sen Li (School of
Computer Science and Technology, Tianjin University, Tianjin, China); Li Liu (Shenzhen Research
Institute of Big Data, the chinese university of hong kong shenzhen)*

97
6322: RETRIEVAL-BASED NATURAL 3D HUMAN MOTION GENERATION
Zehan Tan (Fudan University)*; Weidong Yang (Fudan University); Shuai Wu (Fudan University)

6357: PROGRESSIVE REFINEMENT LEARNING BASED ON FEATURE CROSS PERCEPTION FOR

RESIDENTIAL AREAS SEMANTIC SEGMENTATION
Xinran Lyu (Beijing Normal University); Libao Zhang (Beijing Normal University)*

6383: SSGD: A smartphone screen glass dataset for defect detection

Haonan Han (Tsinghua University); Rui Yang (Tsinghua University); SHUYAN LI (University of
Cambridge); Runze Hu (Beijing Institute of Technology); Xiu Li (Tsinghua University)*

6387: In-Sensor & Neuromorphic Computing are all you need for Efficient Computer Vision
Gourav Datta (University of Southern California)*; Zeyu Liu (University of Southern California); Md
Abdullah-Al Kaiser (University of Southern California); Souvik Kundu (Intel Labs); Joe Mathai (Information
Sciences Institute); Zihan Yin (USC); Ajey Jacob (USC); Akhilesh Jaiswal (USC); Peter A. Beerel
(University of Southern California)

6396: SVMV: SPATIOTEMPORAL VARIANCE-SUPERVISED MOTION VOLUME FOR VIDEO FRAME

INTERPOLATION
Yao Luo (Nanjing University of Science and Technology)*; Jinshan Pan (Nanjing University of Science
and Technology); Jinhui Tang (Nanjing University of Science and Technology)

6496: DisCoHead: Audio-and-Video-Driven Talking Head Generation by Disentangled Control of

Head Pose and Facial Expressions
Geumbyeol Hwang (DeepBrain AI Inc.); Sunwon Hong (DeepBrain AI Inc.); Seunghyun Lee (DeepBrain
AI Inc.); Sungwoo Park (DeepBrain AI Inc.); Gyeongsu Chae (DeepBrain AI Inc.)*

6536: Learning Supervised Covariation Projection Through General Covariance

Xiangze Bao (Yangzhou University); Yunhao Yuan (Yangzhou University)*; Yun Li (Yangzhou University);
Jipeng Qiang (Yangzhou University); Yi Zhu (Yangzhou University)

98
 Information Forensics and Security

121: FedPrompt: Communication-Efficient and Privacy-Preserving Prompt Tuning in Federated

Learning
Haodong Zhao (Shanghai Jiao Tong University)*; Wei Du (Shanghai Jiao Tong University); Fangqi Li
(SEIEE, Shanghai Jiao Tong University); Peixuan Li (Shanghai Jiao Tong University); Gongshen Liu
(Shanghai Jiao Tong University)

223: QTrojan: A Circuit Backdoor Against Quantum Neural Networks

Cheng Chu (Indiana University Bloomington); Lei Jiang (Indiana University)*; Martin Swany (Indiana
University); Fan Chen (Indiana University Bloomington)

276: SC-NET: SALIENT POINT AND CURVATURE BASED ADVERSARIAL POINT CLOUD
GENERATION NETWORK
Zihao Zhang (The University of Electronic Science and Technology of China); Nan Sang (UESTC);
Xupeng Wang (University of Electronic Science and Technology of China)*; Mumuxin Cai (University of
Electronic Science and Technology of China)

290: Audio Cross Verification Using Dual Alignment Likelihood Ratio Test
Heidi Lei (MIT); Arm Wonghirundacha (Pomona College); Irmak Bukey (Pomona College); Timothy Tsai
(Harvey Mudd College)*

297: ENHANCING ROBUSTNESS AND IMPERCEPTIBILITY OF BLIND WATERMARKING WITH

IMPROVED MESSAGE PROCESSOR
Yufeng Wu (Nanjing University of Information Science and Technology)*; Baowei Wang (Nanjing
University of Information Science and Technology); Changyu Dai (Nanjing University of Information
Science and Technology); Yi Yuan (Nanjing University of Information Science and Technology); Bin Li
(Nanjing University of Information Science and Technology); Weiqian Zheng (Nanjing University of
Information Science and Technology); Hao Wu (Nanjing University of Information Science and
Technology)

300: NCL: Textual Backdoor Defense Using Noise-augmented Contrastive Learning

Shengfang Zhai (Peking University)*; Qingni Shen (Peking University); Xiaoyi Chen (Peking University);
Weilong Wang (Peking University); Cong Li (Peking University); Yuejian Fang (Peking University);
Zhonghai Wu (Peking University)

344: GAPter: Gray-box Data Protector for Deep Learning Inference Services at User Side
Hao Wu (Nanjing University); Bo Yang (Nanjing University); Xiaopeng Ke (Nanjing University); Siyi He
(Nanjing University); Fengyuan Xu (Nanjing University)*; Sheng Zhong (Nanjing University)

376: Measure and Countermeasure of the Capsulation Attack against Backdoor-based Deep
Neural Network Watermarks
Fangqi Li (SEIEE, Shanghai Jiao Tong University)*; shilin wang (SEIEE, Shanghai Jiaotong University);
Yun Zhu (Shanghai Jiaotong University)

494: Enhance Transferability of Adversarial Examples with Model Architecture

Mingyuan Fan (Fuzhou University)*; Wenzhong Guo (Fuzhou University); Zuobin Ying (Anhui University);
Ximeng Liu (Fuzhou University)

606: Classification of Synthetic Facial Attributes by Means of Hybrid Classification/Localization

Patch-based Analysis
Jun Wang (University of Siena)*; Benedetta Tondi (University of Siena); Mauro Barni (University of Siena)

99
874: A Multi-modal Approach for Context-aware Network Traffic Classification
Bo Pang (哈尔滨工业大学); Yongquan Fu (National University of Defense Technology)*; Siyuan Ren
(Department of Computer Science and Technology, Harbin Institute of Technology(Shenzhen)); Siqi Shen
(Xiamen University); Ye Wang (National University of Defense Technology); Qing Liao (Harbin Institute of
Technology (Shenzhen)); Yan Jia (National University of Defense Technology)

906: A study on the invariance in security whatever the dimension of images for the steganalysis
by deep-learning
Kévin Planolles (LIRMM (Montpellier)); Marc Chaumont (LIRMM (Montpellier), UNimes)*; Frédéric Comby
(LIRMM)

1149: Image Sharing Chain Detection via Sequence-to-Sequence Model

Jiaxiang You (Shenzhen University); Yuanman Li (Shenzhen University)*; Rongqin Liang (Shenzhen
University); Yuxuan Tan (Shenzhen University); Jiantao Zhou (University of Macau); Xia Li (Shenzhen
University)

1285: Adversarial Network Pruning By Filter Robustness Estimation

Xinlu Zhuang (Wuhan University)*; Yunjie Ge (Wuhan University); Baolin Zheng (Alibaba Group); Qian
Wang (Wuhan University)

1299: CONTENT-INSENSITIVE DYNAMIC LIP FEATURE EXTRACTION FOR VISUAL SPEAKER

AUTHENTICATION AGAINST DEEPFAKE ATTACKS
Zihao Guo (Shanghai Jiao Tong University)*; shilin wang (SEIEE, Shanghai Jiaotong University)

1428: BadRes: Reveal the Backdoors through Residual Connection

Mingrui He (Beihang University)*; Tianyu Chen (Beihang University); Haoyi Zhou (Beihang University);
Shanghang Zhang (Peking University); Jianxin Li (Beihang University)

1556: APGP: ACCURACY-PRESERVING GENERATIVE PERTURBATION FOR DEFENDING

AGAINST MODEL CLONING ATTACKS
Anda Cheng (CASIA)*; jian cheng (casia)

1560: Liveness Score-Based Regression Neural Networks for Face Anti-Spoofing

Youngjun Kwak (Kakaobank)*; Minyoung Jung (KETI); Hunjae Yoo (Kakaobank); Jinho Shin
(Kakaobank); Changick Kim (KAIST)

1665: Benchmarking Cross-Domain Face Recognition with Avatars, Caricatures and Sketches
Ahmad Foroughi (Hochschule Darmstadt); Christian Rathgeb (Hochschule Darmstadt)*; Mathias Ibsen
(Hochschule Darmstadt); Christoph Busch (Hochschule Darmstadt)

1917: EXPLOITING PRNU AND LINEAR PATTERNS IN FORENSIC CAMERA ATTRIBUTION UNDER
COMPLEX LENS DISTORTION CORRECTION
Andrea AM Montibeller (University of Trento)*; Fernando Perez-Gonzalez (Universidad de Vigo)

1950: WHICH COUNTRY IS THIS PICTURE FROM? NEW DATA AND METHODS FOR DNN-BASED
COUNTRY RECOGNITION
Omran Alamayreh (University of Siena )*; Giovanna Dimitri (University of Siena ); Jun Wang (University
of Siena); Benedetta Tondi (University of Siena); Mauro Barni (University of Siena)

2183: CPA: Compressed Private Aggregation for Scalable Federated Learning over Massive
Networks
Natalie Lang ( Ben-Gurion University of the Negev)*; Elad Sofer (Ben-Gurion University of the Negev); Nir
Shlezinger (Ben-Gurion University); Rafael D'Oliveira (Clemson University); Salim El Rouayheb (Rutgers
University)

100
2322: A Graph Neural Network Multi-task Learning-Based Approach for Detection and Localization
of Cyberattacks in Smart Grids
Abdulrahman Takiddin (Texas A&M University)*; Rachad Atat (Texas A&M University at Qatar);
Muhammad Ismail (Tennessee Tech University); Katherine Davis (Texas A&M University); Erchin
Serpedin ()

2345: UNTAG: Learning Generic Features for Unsupervised Type-Agnostic Deepfake Detection
Nesryne Mejri (Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of
Luxembourg)*; Enjie Ghorbel (SnT, University of Luxembourg); Djamila Aouada (SnT, University of
Luxembourg)

2407: Defense against black-box adversarial attacks via heterogeneous fusion features
Jiahuan Zhang (Hokkaido University)*; Keisuke Maeda (Hokkaido University); Takahiro Ogawa (Hokkaido
University); Miki Haseyama (Hokkaido University)

2449: Effect of Lossy Compression Algorithms on Face Image Quality and Recognition
Torsten Schlett (Hochschule Darmstadt)*; Sebastian Schachner (Hochschule Darmstadt); Christian
Rathgeb (Hochschule Darmstadt); Juan Tapia (hda); Christoph Busch (Hochschule Darmstadt)

2479: A 3D-ASSISTED FRAMEWORK TO EVALUATE THE QUALITY OF HEAD MOTION

REPLICATION BY REENACTMENT DEEPFAKE GENERATORS
Sahar Husseini (Eurecom)*; Jean-Luc DUGELAY (Eurecom); Fabien Aili (Docaposte); Emmanuel Nars
(Docaposte)

2535: SORA: Scalable Black-box Reachability Analyser on Neural Networks

Peipei Xu (University of Liverpool)*; Fu Wang (University of Exeter); Wenjie Ruan (University of Exeter);
Chi Zhang (University of Exeter); Xiaowei Huang (Liverpool University)

2570: HE-GAN: Differentially Private GAN using Hamiltonian Monte Carlo based Exponential
Mechanism
Usman Hassan (University of Kentucky); Dongjie Chen (University of California, Davis)*; Sen-ching S
Cheung (University of Kentucky); Chen-Nee Chuah (University of California Davis)

2597: TRUSTERA: A LIVE CONVERSATION REDACTION SYSTEM

Evandro Gouvea (Interaction); Ali Dadgar (Interactions LLC); Shahab Jalalvand (Interactions LLC)*; Rathi
Chengalvarayan (Interactions LLC); Badrinath Jayakumar (Interactions LLC); Ryan Price (Interactions);
Nicholas Ruiz (Interactions); Jennifer McGovern (Interactions LLC); Srinivas Bangalore (Interactions
LLC); Ben Stern (Interactions LLC)

2761: Light Projection-based Physical-world Vanishing Attack against Car Detection

Huixiang Wen (Donghua University); Shan Chang (Donghua University)*; Luo Zhou (Donghua University)

2780: MULTI-LAYER FEATURE DIVISION TRANSFERABLE ADVERSARIAL ATTACK

Zikang Jin (Nanjing University of Aeronautics and Astronautics)*; Changchun Yin (Nanjing University of
Aeronautics and Astronautics); Piji Li (Nanjing University of Aeronautics and Astronautics); Lu Zhou
(Nanjing University of aeronautics and astronautics); Liming Fang (Nanjing University of Aeronautics and
Astronautics); Xiangmao Chang (Nanjing University of Aeronautics and Astronautics); Zhe Liu (Nanjing
University of Aeronautics and Astronautics)

3110: Backdoor Attack Against Automatic Speaker Verification Models in Federated Learning
Dan Meng (OPPO Research Institute); Xue Wang (Wuhan University); Jun Wang (OPPO Research
Institute)*

3221: Model Fingerprinting with Benign Inputs

Thibault Maho (Inria)*; Teddy Furon (Inria); Erwan Le Merrer (Inria)

101
3529: Sparse Black-box Inversion Attack With Limited Information
Yixiao Xu (Institute of Computer Application, China Academy of Engineering Physics); Xiaolei Liu
(Institute of Computer Application, China Academy of Engineering Physics)*; Teng Hu (Institute of
Computer Application, China Academy of Engineering Physics); Bangzhou Xin (Institute of Computer
Application, China Academy of Engineering Physics); Run Yang (Institute of computer application,
Chinese Academy of Engineering Physics)

3540: Image Adversarial Steganography Based on Joint Distortion

Zexin Fan (University of Science and Technology of China); Kejiang Chen (University of Science and
Technology of China)*; Chuan Qin (University of Science and Technology of China); Kai Zeng (University
of Science and Technology of China); Weiming Zhang (University of Science and Technology of China);
Nenghai Yu (University of Science and Technology of China)

3608: Towards Practical Edge Inference Attacks against Graph Neural Networks
Kailai Li (Shanghai Jiao Tong University)*; Jiawei Sun (Shanghai Jiao Tong University); Ruoxin Chen
(Shanghai Jiao Tong University); Wei Ding (Shanghai Jiao Tong University); Kexue Yu (Shanghai Jiao
Tong University); Jie Li (Shanghai Jiao Tong University); Chentao Wu (Shanghai Jiao Tong University)

3662: Single Domain Dynamic Generalization for Iris Presentation Attack Detection
Yachun Li (Hikvision Research Institute)*; Jingjing Wang (Hikvision Research Institute); yuhui chen
(HIKVISION); Di Xie (Hikvision Research Institute); Shiliang Pu (Hikvision Research Institute)

3684: Learning Expressive and Generalizable Motion Features for Face Forgery Detection
Jingyi Zhang (Hikvision Research Institute)*; Peng Zhang (Hikvision Research Institute); Jingjing Wang
(Hikvision Research Institute); Di Xie (Hikvision Research Institute); Shiliang Pu (Hikvision Research
Institute)

3899: DOUBLE COMPRESSION DETECTION BASED ON THE DE-BLOCKING FILTERING OF HEVC

VIDEOS
Xiangui Kang (Sun Yat-Sen University); pengcheng su (Sun Yat-sen University); Zisheng Huang (Sun Yat-
sen University); Yifang Chen (Guangdong Polytechnic Normal University); Jie Wang (Sun Yat-sen
University)*

3940: AN EMPIRICAL STUDY OF BACKDOOR ATTACKS ON MASKED AUTOENCODERS

Shuli Zhuang (University of Science and Technology of China)*; Pengfei Xia (University of Science and
Technology of China); Bin Li (University of Science and Technology of China)

4031: Electric Network Frequency Detection Using Least Absolute Deviations

Christos Korgialas (Aristotle University of Thessaloniki); Constantine Kotropoulos (Aristotle University of
Thessaloniki)*

4062: FINE-GRAINED PRIVATE KNOWLEDGE DISTILLATION

Yuntong Li (Guangzhou University)*; Shaowei Wang (Guangzhou University); Yingying Wang
(Guangzhou University); Jin Li (Guangzhou University); Yuqiu Qian (Tencent Inc.); Bangzhou Xin
(University of Science and Technology of China); Wei Yang (University of Science and Technology of
China)

4121: Efficient Privacy Preserving Graph Neural Network for Node Classification
Xinjun Pei (Central South Univerisity); Xiaoheng Deng (Central South University)*; Shengwei Tian
(Xinjiang University); Kaiping Xue (University of Science and Technology of China)

4204: DISTANCE-BASED ONLINE LABEL INFERENCE ATTACKS AGAINST SPLIT LEARNING

Junlin Liu (Beijing University of Posts and Telecommunications)*; Xinchen Lyu (Beijing University of Posts
and Telecommunications)

102
4206: Towards Adversarially Robust Continual Learning
Tao Bai (Nanyang Technological University)*; Chen Chen (Sony AI); Lingjuan Lyu (Sony AI); Jun Zhao
(Nanyang Technological University); Bihan Wen (Nanyang Technological University)

4324: ICStega: Image Captioning-based Semantically Controllable Linguistic Steganography

Xilong Wang (University of Science and Technology of China)*; Yaofei Wang (Hefei University of
Technology); Kejiang Chen (University of Science and Technology of China); Jinyang Ding (University of
Science and Technology of China); Weiming Zhang (University of Science and Technology of China);
Nenghai Yu (University of Science and Technology of China)

4399: ROBUST WATERMARKING SCHEME IN ENCRYPTED DOMAIN BASED ON INTEGER LIFTING

WAVELET TRANSFORM AND COMPRESSED SENSING
Di Xiao (Chongqing University)*; Qin Tang (Chongqing University); Aozhu Zhao (Chongqing University);
Min Li (Chongqing University)

4473: RUMOR DETECTION VIA ASSESSING THE SPREADING PROPENSITY OF USERS

Peng Zheng (National University of Defense Technology)*; Zhen Huang (National Laboratory for Parallel
and Distributed Processing, National University of Defense Technology,Changsha,Hunan); Yong Dou
(National University of Defense Technology); Yeqing Yan (National University of Defense Technology)

4490: Hearing and Seeing Abnormality: Self-supervised Audio-Visual Mutual Learning for
Deepfake Detection
ChangSung Sung (National Taiwan University)*; Jun-Cheng Chen (Academia Sinica); Chu-Song Chen
(National Taiwan University)

4506: Mixer: DNN Watermarking using Image Mixup

Kassem Kallas (National Institute for Research in Digital Science and Technology (INRIA))*; Teddy Furon
(Inria)

4514: Two-branch multi-scale deep neural network for generalized document recapture attack
detection
Li Jiaxing (City University of Hong Kong); Chenqi KONG (City Unversity of Hong Kong); Shiqi Wang (City
University of Hong Kong); Haoliang Li (CityU)*

4630: Reliability Estimation for Synthetic Speech Detection

Davide Salvi (Politecnico di Milano)*; Paolo Bestagini (Politecnico di Milano); Stefano Tubaro (Politecnico
di Milano, Italy)

4632: LINK: Linguistic Steganalysis Framework with External Knowledge

Jinshuai Yang (Tsinghua University)*; zhongliang yang (tsinghua university); Xinrui Ge (Beijing University
of Posts and Telecommunications); Jiajun Zou (Tsinghua University); yue gao (tsinghua); Yongfeng
Huang (Tsinghua University)

4877: CSM in Motion Vector Steganalysis: The Effect of Coders on Motion Vectors in H.264 Video
Encoding
Verena Lachner (ZITiS)*; Katharina Schaar (ZITiS); Ralf Zimmermann (ZITiS)

4888: ROW CONDITIONAL-TGAN FOR GENERATING SYNTHETIC RELATIONAL DATABASES

Mohamed Gueye (CROESUS); Yazid Attabi (CROESUS)*; Maxime Dumas (CROESUS)

4920: Prosody is Not Identity: A Speaker Anonymization Approach Using Prosody Cloning
Sarina Meyer (University of Stuttgart)*; Florian Lux (University of Stuttgart); Julia Koch (University of
Stuttgart); Pavel Denisov (University of Stuttgart); Pascal Tilli (University of Stuttgart); Ngoc Thang Vu
(University of Stuttgart)

103
5189: A Role Engineering Approach based on Spectral Clustering Analysis for RESTful
Permissions in Cloud
Yutang Xia (Peking University)*; Yang Luo (Peking University); Wu Luo (Peking University); Qingni Shen
(Peking University); Yahui Yang (Peking University); Zhonghai Wu (Peking University)

5386: A Speech Representation Anonymization Framework via Selective Noise Perturbation

Minh Tran (University of Southern California)*; Mohammad Soleymani (University of Southern California)

5628: Styx: Adaptive Poisoning Attacks against Byzantine-Robust defenses in Federated Learning
Yuxin Wen (University of Maryland)*; Jonas A. Geiping (University of Maryland, College Park); Micah
Goldblum (University of Maryland); Tom Goldstein (University of Maryland, College Park)

5689: LEARNING TO LOCATE THE TEXT FORGERY IN SMARTPHONE SCREENSHOTS

Zeqin Yu (shenzhen university); Bin Li (Shenzhen University)*; Yuzhen Lin (Shenzhen University); Jinhua
Zeng (Academy of Forensic Science); Jishen Zeng (Alibaba Group)

5769: Detecting Malicious Migration on Edge to Prevent Running Data Leakage

Yuchen Wong (软件工程中心)*; Qingni Shen (Peking University); Cong Li (Peking University); Cunzhan
Liu (Peking University); Tianxiang Ai (Peking University)

5839: Going in Style: Audio Backdoors through Stylistic Transformations

Stefanos Koffas (Technical University of Delft)*; luca pajola (University of Padova); Stjepan Picek (Delft
University of Technology); Mauro Conti (University of Padua)

5936: LEARNING SPARSE ALIGNMENTS VIA OPTIMAL TRANSPORT FOR CROSS-DOMAIN FAKE
NEWS DETECTION
Wei Tang (Beijing University of Posts and Telecommunications)*; zuyao ma (Beijing University of Posts
and Telecommunications)

5944: MAKE YOUR ENEMY YOUR FRIEND: IMPROVING IMAGE ROTATION ANGLE ESTIMATION
WITH HARMONICS
yu kun (School of Computer Science & Technology Southwest University of Science and Technology
Mianyang, China); Morteza Darvish Morshedi Hosseini (State University of New York at Binghamton);
Anjie Peng (Southwest University of Science and Technology); Hui Zeng (Southwest University of
Science and Technology)*; Miroslav Goljan (State University of New York at Binghamton)

6006: A PRIVACY-PRESERVING TRAJECTORY MINING MODEL

Ziyang Wang (ShenZhen University); Xiaoxiao Wu (Shenzhen University)*; Junjie Zhu (Shenzhen
University); Yingying Zhu (University of Texas Arlington)

6096: Prototype-Based Layered Federated Cross-Modal Hashing

Jiale Liu (Shandong University); Yu-Wei Zhan (Shandong University); Xin Luo (Shandong University)*;
Zhen-Duo Chen (Shandong University); Yongxin Wang (Shandong Jianzhu University); Xin-Shun Xu
(Shandong University)

6121: A LARGE-SCALE PRETRAINED DEEP MODEL FOR PHISHING URL DETECTION

Yanbin Wang (Zhejiang university)*; wei fan zhu (zhejiang university); Haitao Xu (Zhejiang University);
Zhan Qin (Zhejiang University); Kui Ren (Zhejiang University); Wenrui Ma (Zhejiang Gongshang
University)

6296: Improved WordPCFG for Passwords with Maximum Probability Segmentation

Wenting Li (Peking University); JIahong Yang (Peking University); Haibo Cheng (Peking University)*; Ping
Wang (Peking University); Kaitai Liang (Delft University of Technology)

104
6310: On the detection of synthetic images generated by diffusion models
Riccardo Corvi (University Federico II of Naples); Davide Cozzolino (University Federico II of Naples);
Giada Zingarini (University Federico II of Naples); GIovanni Poggi (University Federico II of Naples); Koki
Nagano (NVIDIA); Luisa Verdoliva (University Federico II of Naples)*

105
 Machine Learning for Signal Processing

103: Overcoming the Seesaw in Monocular 3D Object Detection via Language Knowledge
Transferring
Weichen Xu (Peking University)*; Tianhao Fu (Peking University)

140: Learning sparse auto-encoders for green AI image coding

Cyprien Gille (UMONS); Frederic Guyard (Orange Labs); Marc Antonini (Universite Nice Sophia
Antipolis); Michel Barlaud (University of Nice)*

152: Active Learning of Non-semantic Speech Tasks with Pretrained Models

Harlin Lee (University of California Los Angeles)*; Aaqib Saeed (Eindhoven University of Technology);
Andrea L. Bertozzi (UCLA)

156: HDNet: Hierarchical Dynamic Network for Gait Recognition using Millimeter-Wave Radar
Yanyan Huang (Zhejiang University)*; Yong Wang (Zhejiang University); Kun Shi (Zhejiang University );
Chaojie Gu (Zhejiang University); Yu Fu (Zhejiang University); Cheng Zhuo (Zhejiang University); Zhiguo
Shi (Zhejiang University)

162: Gluformer: Transformer-Based Personalized Glucose Forecasting with Uncertainty

Quantification
Renat Sergazinov (Texas A&M University)*; Mohammadreza Armandpour (Texas A&M University); Irina
Gaynanova (Texas A&M University)

167: Energy Regularized RNNs for Solving Non-Stationary Bandit Problems

Michael Rotman (Tel Aviv University)*; Lior Wolf (Tel Aviv University, Israel)

193: A Multi-Stage Triple-Path Method for Speech Separation in Noisy and Reverberant
Environments
Zhaoxi Mu (Xi'an Jiaotong University)*; Xinyu Yang (Xi'an Jiaotong University); Xiangyuan Yang (Xi'an
Jiaotong University); WenJing Zhu (DXM)

204: Explicit and Implicit Knowledge Distillation via Unlabeled Data

Yuzheng Wang (Fudan University)*; zuhao ge (fudan university); Zhaoyu Chen (Fudan University); Xian
Liu (Fudan University); Chuangjia Ma (Fudan University); Yunquan Sun (Fudan University); Lizhe Qi
(Fudan University)

205: Adversarial Contrastive Distillation with Adaptive Denoising

Yuzheng Wang (Fudan University)*; Zhaoyu Chen (Fudan University); Dingkang Yang (Fudan University);
Yang Liu (Fudan University); Siao Liu (Fudan University); Wenqiang Zhang (Fudan University); Lizhe Qi
(Fudan University)

207: Chord-Conditioned Melody Harmonization with Controllable Harmonicity

Shangda Wu (Central Conservatory of Music); Xiaobing Li (Central Conservatory of Music); Maosong Sun
(Tsinghua University)*

226: SD-PINN: Physics informed neural networks for spatially dependent PDEs
Ruixian Liu (University of California, San Diego)*; Peter Gerstoft (University of California San Diego)

238: Centroid Distance Distillation for Effective Rehearsal in Continual Learning

Liu Daofeng (Suzhou University of Science and Technology); Fan Lyu (College of Intelligence and
Computing, Tianjin University)*; Linyan Li (Suzhou Institute of Trade & Commerce); Zhenping Xia
(Suzhou University of Science and Technology); Fuyuan Hu (Suzhou University of Science and
Technology)

106
287: Optimization for Robustness Evaluation beyond Lp Metrics
Hengyue Liang (University of Minnesota)*; Buyun Liang (University of Minnesota); Ying Cui (University of
Minnesota); Tim Mitchell (Queens College / CUNY); Ju Sun (University of Minnesota)

361: HalluAudio: Hallucinate frequency as concepts for few-shot audio classification

Zhongjie Yu (Wyze Labs, Inc.)*; Shuyang Wang (Shiseido Americas); Lin Chen (Wyze Labs Inc.);
Zhongwei Cheng (Wyze Labs, Inc.)

371: ModalDrop: Modality-aware Regularization for Temporal-Spectral Fusion in Human Activity

Recognition
Xin Zeng (Institute of Computing Technology, Chinese Academy of Sciences)*; Yiqiang Chen (Institute of
Computing Technology, Chinese Academy of Sciences); Benfeng Xu (University of Science and
Technology of China); Tengxiang Zhang (institute of computing technology, Chinese academy of
sciences)

386: Preformer: Predictive Transformer with Multi-Scale Segment-wise Correlations for Long-Term
Time Series Forecasting
Dazhao Du (Institute of Software Chinese Academy of Sciences); Bing Su (Renmin University of China)*;
Zhewei Wei (Renmin University of China)

418: Hierarchical Hypergraph Recurrent Attention Network for Temporal Knowledge Graph
Reasoning
Jiayan Guo (Peking University)*; Meiqi Chen (Peking University); Yan Zhang (Peking University);
Jianqiang Huang (Meituan); zhiwei liu (meituan)

423: NRTSI: NON-RECURRENT TIME SERIES IMPUTATION

Siyuan Shan (Department of Computer Science, University of North Carolina at Chapel Hill)*; Yang Li
(Department of Computer Science, University of North Carolina at Chapel Hill); Junier Oliva (UNC-Chapel
Hill)

427: Pseudo-Inverted Bottleneck Convolution for DARTS Search Space

Arash Ahmadian (University of Toronto); Yue Fei (University of Toronto); Louis S.P. Liu (University of
Toronto); Konstantinos N Plataniotis (UofT); Mahdi S Hosseini (Concordia University)*

429: PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under
Adversarial Attack
Junxuan Huang (University at Buffalo)*; Junsong Yuan ("State University of New York at Buffalo, USA");
Chunming Qiao (University at Buffalo); yatong an (xmotors); Cheng Lu (Xiaopeng); Chen Bai (Xpeng
Motors)

461: TinyOOD: Effective Out-of-Distribution Detection for TinyML

Yongchang Li (Soochow University); Juncheng Jia (Soochow University)*; Yan Zuo (Jiangsu New Hope
Technology Co., Ltd); Weipeng Zhu (SOOCHOW UNIVERSITY)

507: Learn Topological Representation with Flexible Manifold Layer

Ziheng Jiao (Northwestern Polytechnical University.); Hongyuan Zhang (Northwestern Polytechnical
University); Xuelong Li (Northwestern Polytechnical University)*

524: On the minimum perimeter criterion for bounded component analysis

Sergio Cruces (Universidad de Sevilla)*

526: ACTIVE LEARNING FOR EFFICIENT FEW-SHOT CLASSIFICATION

Aymane Abdali (IMT Atlantique)*; Vincent Gripon (IMT Atlantique); Lucas Drumetz (IMT Atlantique);
Bartosz Boguslawski (Schneider Electric)

107
560: DepthFormer: Multimodal Positional Encodings and Cross-Input Attention for Transformer-
Based Segmentation Networks
Francesco Barbato (University of Padova)*; Giulia Rizzoli (University of Padova); Pietro Zanuttigh
(University of Padova)

589: CPD-GAN: Cascaded Pyramid Deformation GAN for Pose Transfer

Yuan Huang (Nanjing University); Yuting Tang (Nanjing University); Xiu Zheng (Nanjing University); Jie
Tang (Nanjing University)*

596: Adaptive Scale and Spatial Aggregation for Real-time Object Detection
Wei Chen (College of Computer, National University of Defense Technology); Yulin He (National
University of Defense Technology)*; Zhengfa Liang (Defense Innovation Institute); Yulan Guo (National
University of Defense Technology)

599: JOINT HUMAN ORIENTATION-ACTIVITY RECOGNITION USING WIFI SIGNALS FOR HUMAN-
MACHINE INTERACTION
Hojjat Salehinejad (Mayo Clinic)*; Navid Hasanzadeh (University of Toronto); Radomir Djogo (University
of Toronto); Shahrokh Valaee (University of Toronto)

615: FFedCL: Fair Federated Learning with Contrastive Learning

xiaorong shi (nankai university)*; Liping Yi (Nankai University); Liu Xiaoguang (Nankai Univerisity); Wang
Gang (Nankai Univerisity)

623: Measuring the Transferability of L-infty Attacks by the L-2 Norm

Sizhe Chen (Shanghai Jiao Tong University)*; Qinghua Tao (KU Leuven); Zhixing Ye (Shanghai Jiao Tong
University); Xiaolin Huang (Shanghai Jiao Tong University)

624: Enhanced Low-resolution LiDAR-Camera Calibration Via Depth Interpolation and Supervised
Contrastive Learning
Zhikang Zhang (Arizona State University)*; Zifan Yu (Arizona State University); Suya You (U.S. Army
Research Laboratory); Raghuveer Rao (Army Research Laboratory); Sanjeev Agarwal (U.S. Army
DEVCOM C5ISR Center); Fengbo Ren (Arizona State University)

626: SEQUENCE-BASED DEVICE-FREE GESTURE RECOGNITION FRAMEWORK FOR MULTI-

CHANNEL ACOUSTIC SIGNALS
Zhizheng Yang (Nanjing University)*; Xun Wang (Nanjing University); Dongyu Xia (Nanjing University);
Wei Wang (Nanjing University); Haipeng Dai (Nanjing University)

627: Scalable and Secure Federated XGBoost

Quang M Nguyen (Massachusetts Institute of Technology)*; Nhan Khanh Le (TUM); Lam M Nguyen (IBM
Research, Thomas J. Watson Research Center)

643: Learning to Generate 3D Representations of Building Roofs Using Single-View Aerial Imagery
Maxim Khomiakov (Technical University of Denmark)*; Alejandro Valverde Mahou (Technical University of
Denmark); Alba Reinders Sánchez (Technical University of Denmark ); Jes Frellsen (Technical University
of Denmark); Michael Andersen (Technical University of Denmark)

674: Hybrid Transformers For Music Source Separation

Simon Rouard (Meta AI Research)*; Francisco Massa (Facebook AI Research); Alexandre Défossez
(Meta AI Research)

681: Stochastic Optimization of Vector Quantization Methods in Application to Speech and Image
Processing
Mohammad Hassan Vali (Aalto University)*; Tom Bäckström (Aalto University)

108
684: TENSOR COMPLETION FOR EFFICIENT AND ACCURATE HYPERPARAMETER
OPTIMISATION IN LARGE-SCALE STATISTICAL LEARNING
Aaman Rebello (Imperial College London); Kriton Konstantinidis (Imperial College London)*; Yao Lei Xu
(Imperial College London); Danilo P. Mandic ((Imperial College of London, UK))

687: Transductive Matrix Completion with Calibration for Multi-Task Learning

Hengfang Wang (Fujian Normal University); Yasi Zhang (University of California, Los Angeles); Xiaojun
Mao (Shanghai Jiao Tong University)*; Zhonglei Wang (Xiamen University)

693: Autonomous Soundscape Augmentation with Multimodal Fusion of Visual and Participant-
linked Inputs
Kenneth Ooi (Nanyang Technological University)*; Karn N Watcharasupat (Georgia Institute of
Technology); Bhan Lam (NTU); Zhen-Ting Ong (Nanyang Technological University); Woon Seng Gan
(NTU )

715: Graph-Graph Context Dependency Attention for Graph Edit Distance

Ruiqi Jia (Wangxuan Institute of Computer Technology, Peking University)*; xianbing feng (peking
university); Xiaoqing Lyu (Peking University); Zhi Tang (Peking University)

730: K2NN: Self-supervised Learning with Hierarchical Nearest Neighbors for Remote Sensing
Jianlong Yuan (Alibaba Group)*; Yuanhong Xu (Alibaba Group); Zhibin Wang (Alibaba Group)

740: ADAPTIVE DATA AUGMENTATION FOR CONTRASTIVE LEARNING

Yuhan Zhang (Brainnetome Center and NLPR, Institute of Automation, Chinese Academy of Sciences;
School of Artificial Intelligence, University of Chinese Academy of Sciences(UCAS);)*; He Zhu (
Brainnetome Center and NLPR; School of Future Technology, UCAS; University of Chinese Academy of
Sciences; Institute of Automation, Chinese Academy of Sciences); Shan Yu (Brainnetome Center and
NLPR;University of Chinese Academy of Sciences;CAS Center for Excellence in Brain Science and
Intelligence Technology, Chinese Academy of Sciences;)

743: Bipartite Graph Convolutional Networks with Adversarial Domain Transfer

Dong Wu (Fudan University); Bin Liang (Fudan University); Xiangjun Liu (Fudan University); Xuan Zang
(Fudan University); mingmin Chi (Fudan university)*

794: SEMI-SUPERVISED LOCAL STRUCTURED FEATURE LEARNING WITH DYNAMIC MAXIMUM

ENTROPY GRAPH
Rui Xu (Renmin University of China)*; Xun Liang (Renmin University of China)

796: Neural Architecture of Speech

Subba Reddy Oota (IIIT Hyderabad)*; Khushbu Pahwa (University of California Los Angeles); Mounika
Marreddy (IIIT Hyderabad); Manish Gupta (Microsoft); Raju Surampudi Bapi (International Institute of
Information Technology Hyderabad)

814: Weakly- and Semi-Supervised Object Localization

Zhen-Tang Huang (National Taiwan Normal University); Yan-He Chen (National Taiwan Normal
University); Mei-Chen Yeh (National Taiwan Normal University)*

815: KalmanBOT: KalmanNet and Bollinger Bands based Learned Trader for Pairs Trading
Haoran Deng (ETH Zürich); Guy Revach (ETH Zürich)*; Hai Morgenstern (BeyondMinds); Nir Shlezinger
(Ben-Gurion University)

109
816: COMPLEMENTARY LEARNING SYSTEM BASED INTRINSIC REWARD IN REINFORCEMENT
LEARNING
Zijian Gao (National University of Defense Technology); Kele Xu (National Key Laboratory of Parallel and
Distributed Processing (PDL))*; Hongda Jia (National University of Defense Technology); Tianjiao Wan
(National University of Defense Technology); Ding Bo (National University of Defense Technology); Dawei
Feng (National University of Defense Technology); Xinjun Mao (National University of Defense
Technology); Huaimin Wang (National University of Defense Technology)

818: Filter Pruning via Filters Similarity in Consecutive Layers

Xiaorui Wang (Ping An Technology (Shenzhen) Co., Ltd.); Jun Wang (Ping An Technology (Shenzhen)
Co. Ltd.)*; xin tang (Ping An property&casualty insurance company of China.LTD.); Peng Gao (Ping An
Technology); Rui Fang (Ping An property&casualty insurance company of China.LTD.); Guotong Xie (Ping
An Technology (Shenzhen) Co. Ltd.)

829: IMPROVING ADVERSARIAL ROBUSTNESS WITH HYPERSPHERE EMBEDDING AND

ANGULAR-BASED REGULARIZATIONS
Olukorede J Fakorede (Iowa State University )*; Ashutosh Nirala (Iowa State University); Modeste
Atsague (Iowa State University); Jin Tian (Iowa State University)

841: Hierarchical Multi-Task Learning for Fabric Component Analysis Based on NIR Spectral
Signals
Joseph Kim (Fudan University); Dong Wu (Fudan University); mingmin Chi (Fudan university)*; Gaoqi Xu
(Zhongshan PoolNet Technology Co. Ltd.)

861: BIOLOGICALLY-INSPIRED CONTINUAL LEARNING OF HUMAN MOTION SEQUENCES

Joachim C Ott (ETH Zurich)*; Shih-Chii Liu (Institute of Neuroinformatics)

866: Surrogate Based Post-hoc Calibration for Distributional Shift

Jun Zhang (Tsinghua University; National Innovation Institute of Defense Technology, Chinese Academy
of Military Science)*

885: EXTENDED EXPECTATION MAXIMIZATION FOR UNDER-FITTED MODELS

Aref Miri Rekavandi (University of Western Australia)*; Abd-Krim Seghouane (University of Mebourne);
Farid Boussaid (University of Western Australia); Mohammed Bennamoun (University of Western
Australia)

893: Quantifying Catastrophic Forgetting in Continual Federated Learning

Christophe Dupuy (Amazon)*; Jimit Majmudar (Amazon); Jixuan Wang (Amazon); Tanya G Roosta
(Amazon); Rahul Gupta (Amazon); Clement Chung (Amazon); Jie Ding (Amazon); Salman Avestimehr
(University of Southern California)

896: Controllable music inpainting with mixed-level and disentangled representation

Shiqi Wei (Fudan University)*; Ziyu Wang (NYU Shanghai); Weiguo Gao (Fudan University); Gus Xia
(New York University Shanghai)

903: CO-Net: Classification-oriented Point Cloud Sampling via Informative Feature Learning and
Non-overlapped Local Adjustment
Yanan Lin (Xiamen University)*; Keyu Chen (East China Normal University); Shihao Zhou (Xiamen
University); Yunan Huang (Xiamen University); Yunqi Lei (Xiamen university)

931: Wassertein GAN synthesis for time series with complex temporal dynamics: Frugal
architectures and arbitrary sample-size generation
Thomas Beroud (Ecole Centrale Nantes); Patrice Abry (CNRS, Physics Department, Ecole Normale
Supérieure de Lyon)*; Yannick Malevergne (Univ. Paris1); Marc Senneret (Vivienne Investissement );
Gerald Perrin (Vivienne Investissement); Johan Macq (Vivienne Investissement)

110
944: TransAdapt: A Transformative Framework for Online Test Time Adaptive Semantic
Segmentation
Debasmit Das (Qualcomm AI Research)*; Shubhankar Borse (Qualcomm AI Research ); Hyojin Park
(Qualcomm AI Research); Kambiz Azarian (Qualcomm AI Research); Hong Cai (Qualcomm AI
Research); Risheek Garrepalli (Qualcomm AI Research); Fatih Porikli (Qualcomm AI Research)

982: Higher-order Sparse Convolutions in Graph Neural Networks

Jhony H. Giraldo (Télécom Paris)*; Sajid Javed (Khalifa University of Science and Technology); Arif
Mahmood (Information Technology University); Fragkiskos Malliaros (CentraleSupelec); Thierry
BOUWMANS (Univ. La Rochelle)

987: Backdoor Defense via Suppressing Model Shortcuts

Sheng Yang (Tsinghua University); Yiming Li (Tsinghua University)*; Yong Jiang (Tsinghua University);
Shu-Tao Xia (Tsinghua University)

999: High-resolution neural network processing of LFM radar pulses

Jabran Akhtar (FFI)*

1002: TEST-TIME TRAINING-FREE DOMAIN ADAPTATION

Yongxiang Feng (Huawei Technologies Co., Ltd); Weihua He (Tsinghua University); Kaichao You (Huawei
Technologies Co., Ltd); Bing Liu (Peking University); Ziyang Zhang (HUAWEI TECHNOLOGIES
CO.LTD)*; Yaoyuan Wang (Huawei Technologies Co., Ltd.); Minglei Li (Huawei Technologies Co., Ltd.);
yihang lou (huawei); Jiawei Li (Huawei Technologies Co., Ltd. ); Guoqi Li (Tsinghua University);
Jianxing Liao (HUAWEI TECHNOLOGIES CO.LTD)

1011: IoU-Aware Multi-Expert Cascade Network via Dynamic Ensemble for Long-tailed Object
Detection
Wan-Cyuan Fan (National Taiwan University)*; Cheng-Yao Hong (Academia Sinica); Yen-Chi Hsu
(Academia Sinica); Tyng-Luh Liu (Academia Sinica)

1023: Deep Manifold Graph Auto-Encoder for Attributed Graph Embedding

Bozhen Hu (Zhejiang University & Westlake University)*; Zelin Zang (Zhejiang University & Westlake
University); Jun Xia (Westlake University); Lirong Wu (Westlake University); Cheng Tan (Zhejiang
University & Westlake University); Stan Z. Li (Westlake University)

1036: Exploiting One-class classification optimization objectives for increasing adversarial

robustness
Vasileios Mygdalis (Aristotle University of Thessaloniki)*; Ioannis Pitas (Aristotle University of
Thessaloniki)

1065: Self-Attention based Action Segmentation using Intra-and Inter-segment Representations

Constantin Patsch (Technical University of Munich)*; Eckehard Steinbach (TUM)

1076: Building Blocks for a Complex-Valued Transformer Architecture

Florian Eilers (University of Münster)*; Xiaoyi Jiang (University of Münster)

1083: Mixed Sample Augmentation for Online Distillation

Yiqing Shen ( Johns Hopkins University)*

1125: Uncertainty-Aware Few-Shot Class-Incremental Learning

Zhu Jiancai (East China Normal University); Jiabao Zhao (East China Normal University)*; Jiayi Zhou
(East China Normal University); Liang He (ECNU); Jing Yang (ECNU); Zhi Zhang (Shanghai Educational
Technology Center)

111
1126: FlowReg: Latent Space Regularization using Normalizing Flow for Limited Samples Learning
Chi Wang (Queen's University Belfast)*; Jian Gao (Queen's University Belfast); Yang Hua (Queen's
University Belfast); Hui Wang (Queen's University Belfast)

1130: Promoting Cooperation in Multi-Agent Reinforcement Learning via Mutual Help

Yunbo Qiu (Tsinghua University)*; Yue Jin (University of Warwick); Lebin Yu (Tsinghua University); Jian
Wang (Tsinghua university); Xudong Zhang (Tsinghua university)

1135: Conditional LS-GAN based Skylight Polarization Image Restoration and Application in
Meridian Localization
Tian Yang (Hefei University of Technology); Hongbo Bo (University of Bristol); Xinyu Yang (Lancaster
University); Jun Gao (Hefei University of Technology); Zijian Shi (University of Bristol)*

1137: Towards Trustworthy Multi-label Sewer Defect Classification via Evidential Deep Learning
Chenyang Zhao (School of Software, Southeast University); Chuanfei Hu (University of Shanghai for
Science and Technology)*; Hang Shao (University of Shanghai for Science and Technology); Zhe Wang
(University of Shanghai for Science and Technology); Yongxiong Wang (University of Shanghai for
Science and Technology)

1152: Input-dependent Dynamical Channel Association for Knowledge Distillation

Qiankun Tang (Zhejiang Lab)*; Yuan Zhang (China Telecom); Xiaogang Xu (Zhejiang Gongshang
University); Jun Wang (Zhejiang Lab); Yimin Guo (China Telecom Research Institute)

1155: An Adaptive Plug-and-Play Network for Few-Shot Learning

Hao Li (Beihang University)*; Li Li (Beihang university); Yunmeng Huang (Beihang University); Ning Li
(Beihang University); Yongtao Zhang (Nanjing University of Aeronautics and Astronautics)

1189: NC-WAMKD: Neighborhood Correction Weight-Adaptive Multi-teacher Knowledge

Distillation For Graph-based Semi-supervised Node Classification
Jiahao Liu ( Xi’an Jiaotong University)*; pengcheng guo (Xi'an Jiaotong University); Yonghong Song
(Xi’an Jiaotong University)

1190: Toward Asymptotic Optimality: Sequential Unsupervised Regression of Density Ratio for
Early Classification
Akinori F Ebihara (NEC Corporation)*; Taiki Miyagawa (NEC Corporation); Kazuyuki Sakurai (NEC
Biometrics Research Laboratories); Hitoshi Imaoka (NEC Corporation)

1234: HIERARCHICAL SPATIAL-TEMPORAL TRANSFORMER WITH MOTION TRAJECTORY FOR

INDIVIDUAL ACTION AND GROUP ACTIVITY RECOGNITION
Xiaolin Zhu (Xiangtan University); Dongli Wang (Xiangtan University); Yan ZHOU (Xiangtan University)*

1254: Memory-Augmented U-Transformer for Multivariate Time Series Anomaly Detection

Shuxin Qin (Purple Mountain Laboratories)*; Yongcan Luo (Purple Mountain Laboratories); Gaofeng Tao
(Purple Mountain Laboratories)

1261: Grad-StyleSpeech: Any-speaker Adaptive Text-to-Speech Synthesis with Diffusion Models

Minki Kang (AITRICS, KAIST)*; Dongchan Min (KAIST); Sung Ju Hwang (KAIST, AITRICS)

1262: CLASSIFICATION VIA SUBSPACE LEARNING MACHINE (SLM): METHODOLOGY AND

PERFORMANCE EVALUATION
Hongyu Fu (University of Southern California)*; Yijing Yang (University of Southern California); Vinod
Mishra (Army Research Lab); C.-C. Jay Kuo (USC)

112
1266: T5-SR: A Unified Seq-to-Seq Decoding Strategy for Semantic Parsing
Yuntao Li (Peking University)*; Zhenpeng Su (University of Chinese Academy of Sciences); yutian li
(Meituan Group); Zhang Hanchu (meituan); Sirui Wang (Meituan); Wei Wu (Meituan-Dianping Group);
Yan Zhang (Peking University)

1268: TRIAAN-VC: TRIPLE ADAPTIVE ATTENTION NORMALIZATION FOR ANY-TO-ANY VOICE

CONVERSION
Hyun Joon Park (Korea University)*; Seok Woo Yang (Korea University); Jin Sob Kim (Korea University);
Wooseok Shin (Korea University); Sung Won Han (Korea University)

1269: AD-YOLO: YOU LOOK ONLY ONCE IN TRAINING MULTIPLE SOUND EVENT LOCALIZATION
AND DETECTION
Jin Sob Kim (Korea University)*; Hyun Joon Park (Korea University); Wooseok Shin (Korea University);
Sung Won Han (Korea University)

1271: Bag of Tricks with Quantized Convolutional Neural Networks for image classification
Jie Hu (Institute of Software Chinese Academy of Sciences)*; Mengze Zeng (Momenta); Enhua Wu
(SKLCS, Institute of Software, Chinese Academy of Sciences, Beijing, China；Faculty of Science and
Technology, University of Macau, Macao, China )

1282: PRECOGNITION IN CONTEXTUAL SPOKEN LANGUAGE UNDERSTANDING VIA

KNOWLEDGE DISTILLATION
Nan Su (Ant Group)*; Bingzhu Du (Ant Group); Yuchi Zhang (Ant Financial Services Group); Chao Liu
(Ant Group); Yongliang Wang (Ant Group); Hong Chen (Ant Group ); xin lu (ant group)

1312: MULTI-HEAD UNCERTAINTY INFERENCE FOR ADVERSARIAL ATTACK DETECTION

Yuqi Yang (Beijing University of Posts and Telecommunications); Songyun Yang (Beijing University of
Posts and Telecommunications); Jiyang Xie (Beijing University of Posts and Telecommunications);
Zhongwei Si (Beijing University of Posts and Telecommunications)*; Kai Guo (BUPT); Ke Zhang (North
China Electric Power University); Kongming Liang (Beijing University of Posts and Telecommunications)

1354: Untargeted Backdoor Attack against Object Detection

Chengxiao Luo (Tsinghua University); Yiming Li (Tsinghua University)*; Yong Jiang (Tsinghua University);
Shu-Tao Xia (Tsinghua University)

1374: Augmentation Robust Self-Supervised Learning for Human Activity Recognition

Cong Xu (Amazon Inc.)*; Yuhang Li (Yale University); Dae Lee (Amazon); Dae Hoon Park (Amazon);
Hongda Mao (Amazon Inc.); Huyen Do (Amazon Inc.); Jonathan Chung (Amazon); Dinesh Nair (Amazon
Inc.)

1375: SPADE: SELF-SUPERVISED PRETRAINING FOR ACOUSTIC DISENTANGLEMENT

John Harvill (University of Illinois at Urbana-Champaign); Jarred Barber (Google); Arun A Nair (Amazon
Inc.); Ramin Pishehvar (Amazon)*

1379: Anomalous Sound Detection using Audio Representation with Machine ID based
Contrastive Learning Pretraining
Jian Guan (Harbin Engineering University)*; Feiyang Xiao (Harbin Engineering University); Youde Liu (
Harbin Institute of Technology); Qiaoxi Zhu (University of Technology Sydney); Wenwu Wang (University
of Surrey)

1397: Rethinking Implicit Neural Representations for Vision Learners

Yiran Song (Shanghai Jiao Tong University)*; Qianyu Zhou (Shanghai Jiao Tong University); Lizhuang Ma
(Shanghai Jiao Tong University)

113
1400: Bias Identification with RankPix Saliency
salamata konate (QUT)*; Leo Lebrat (CSIRO); Rodrigo Santa Cruz (CSIRO); Clinton Fookes
(Queensland University of Technology); Andrew Bradley (Queensland University of Technology); Olivier
Salvado (CSIRO)

1401: Efficient Multi-Scale Attention Module with Cross-Spatial Learning

Daliang Ouyang (AEROSPACE SCIENCE & INDUSTRY SHENZHEN(GROUP)CO.,LTD.)*; Su He
(AEROSPACE SCIENCE & INDUSTRY SHENZHEN(GROUP)CO.,LTD.); Guozhong Zhang
(AEROSPACE SCIENCE & INDUSTRY SHENZHEN(GROUP)CO.,LTD.); Mingzhu Luo (AEROSPACE
SCIENCE & INDUSTRY SHENZHEN(GROUP)CO.,LTD.); Huaiyong Guo (AEROSPACE SCIENCE &
INDUSTRY SHENZHEN(GROUP)CO.,LTD.); Jian Zhan (AEROSPACE SCIENCE & INDUSTRY
SHENZHEN(GROUP)CO.,LTD.); Zhijie Huang (AEROSPACE SCIENCE & INDUSTRY
SHENZHEN(GROUP)CO.,LTD.)

1411: PSEUDO-QUERY GENERATION FOR SEMI-SUPERVISED VISUAL GROUNDING WITH

KNOWLEDGE DISTILLATION
Jianglin Jin (East China Normal University)*; Jiabo Ye (East China Normal University); Xin Lin (ECNU);
Liang He (ECNU)

1421: Designing Transformer networks for sparse recovery of sequential data using deep
unfolding
Brent De Weerdt (Vrije Universiteit Brussel )*; Yonina Eldar (); Nikos Deligiannis (Vrije Universiteit Brussel
- imec)

1429: Framewise multiple sound source localization and counting using binaural spatial audio
signals
Lei Wang (Shanghai Jiao Tong University)*; Zhibin Jiao (Huawei Technologies Co., Ltd.); Qiyong Zhao
(Huawei Technologies Co., Ltd.); jie zhu (Shanghai Jiao Tong University); Yang Fu (Huawei Technologies
Co., Ltd.)

1438: Tensorized LSSVMs for Multitask Regression

Jiani Liu (University of Electronic Science and Technology of China); Qinghua Tao (KU Leuven); Ce Zhu
(University of Electronic Science & Technology of China)*; Yipeng Liu (University of Electronic Science
and Technology of China); Johan Suykens (KU Leuven)

1442: An improved optimal transport kernel embedding method with gating mechanism for
singing voice separation and speaker identification
Weitao Yuan (Tiangong University)*; Yuren Bian (Tiangong University); Shengbei Wang (Tiangong
University); Masashi Unoki (JAIST); Wenwu Wang (University of Surrey)

1461: BHE-DARTS: Bilevel Optimization based on Hypergradient Estimation for Differentiable

Architecture Search
Zicheng Cai (Guangdong University of Technology); Lei Chen (Guangdong University of Technology)*;
Hai-Lin Liu (Guangdong University of Technology)

1463: Not All Classes are Equal: Adaptively Focus-Aware Confidence for Semi-Supervised Object
Detection
Hui Zhu (Institute of Computing Technology, Chinese Academy of Sciences)*; Yongchun Lu (Mashang
Consumer Finance Co., Ltd.); hongyu zhao (Mashang Consumer Finance Company Ltd.); Guoqing Zhao
(Mashang Consumer Finance Co., Ltd); Xiaofang Zhao (Institute of Computing Technology, Chinese
Academy of Sciences; Institute of Intelligent Computing Technology, Suzhou, CAS)

1474: Int-GNN: a User Intention Aware Graph Neural Network for Session-Based Recommendation
Guangning Xu (Harbin Institute of Technology, Shenzhen ▲)*; Jinyang Yang (Harbin Institute of
Technology, Shenzhen); Jinjin Guo (JD Intelligent Cities Research); Zhichao Huang (JD Intelligent Cities
Research); Bowen Zhang (Shenzhen Technology University)

114
1497: Interpretability in the Context of Sequential Cost-Sensitive Feature Acquisition
Yasitha Warahena Liyanage (Microsoft); Daphney-Stavroula Zois (University at Albany)*

1515: HEiMDaL: Highly Efficient Method for Detection and Localization of wake-words
Arnav Kundu (Apple)*; Mohammad Samragh (Apple); Minsik Cho (Apple ); Priyanka Padmanabhan
(Apple); Devang Naik (Apple)

1517: SEQUENTIAL DATUM–WISE JOINT FEATURE SELECTION AND CLASSIFICATION IN THE

PRESENCE OF EXTERNAL CLASSIFIER
Sachini Piyoni Ekanayake (University at Albany SUNY)*; Daphney-Stavroula Zois (University at Albany);
Charalampos Chelmis (University at Albany)

1523: A Magnetic Framelet-Based Convolutional Neural Network for Directed Graphs

Lequan Lin (The University of Sydney)*; Junbin Gao (University of Sydney, Australia)

1538: Output-Dependent Gaussian Process State-Space Model

Zhidi Lin (The Chinese University of Hong Kong, Shenzhen); Lei Cheng (Zhejiang University); Feng Yin
(The Chinese University of Hong Kong, Shenzhen)*; Lexi Xu (China United Network Communications
Corporation); Shuguang Cui (The Chinese University of Hong Kong, Shenzhen )

1565: STRING-BASED MOLECULE GENERATION VIA MULTI-DECODER VAE

Kisoo Kwon (Samsung Advanced Institute of Technology, Samsung Electronics)*; Kuhwan Jeong
(Samsung Advanced Institute of Technology); Junghyun Park (samsung electronics); HWIDONG NA
(Samsung Electronics.); Jinwoo Shin (KAIST)

1571: TOWARDS ROBUST AUDIO-BASED VEHICLE DETECTION VIA IMPORTANCE-AWARE

AUDIO-VISUAL LEARNING
Jung Uk Kim (Kyung Hee University)*; Seong Tae Kim (Kyung Hee University)

1581: DEFENDING AGAINST UNIVERSAL PATCH ATTACKS BY RESTRICTING TOKEN ATTENTION

IN VISION TRANSFORMERS
Hongwei Yu (University of Science and Technology Beijing); Jiansheng Chen (University of Science and
Technology Beijing)*; Huimin Ma (University of Science and Technology Beijing); Cheng Yu (Tsinghua
University); Xinlong Ding (University of Science and Technology Beijing)

1597: Focusing On Targets For Improving Weakly Supervised Visual Grounding

Viet-Quoc Pham (Toshiba Research and Development Center)*; Nao Mishima (Toshiba Research and
Development Center)

1600: LEVERAGING SPARSITY WITH SPIKING RECURRENT NEURAL NETWORKS FOR ENERGY-
EFFICIENT KEYWORD SPOTTING
Manon Dampfhoffer (SPINTEC University Grenoble Alpes)*; Thomas Mesquida (CEA LIST); Emmanuel
Hardy (CEA-Leti); Alexandre Valentian (CEA-List); Lorena Anghel (SPINTEC University Grenoble Alpes)

1615: On Out-of-Distribution Detection for Audio with Deep Nearest Neighbors

Zaharah Bukhsh (Eindhoven University of Technology); Aaqib Saeed (Eindhoven University of
Technology)*

1622: Efficient Compressed Video Action Recognition via Late Fusion with a Single Network
Hayato Terao (Hokkaido University)*; Wataru Noguchi (Hokkaido University); Hiroyuki Iizuka (Hokkaido
University); Masahito Yamamoto (Hokkaido University)

1629: On minimal variations for unsupervised representation learning

Vivien A Cabannnes (FAIR)*; Alberto Bietti (Inria); Randall Balestriero (Facebook AI Research)

115
1649: Amicable Aid: Perturbing Images to Improve Classification Performance
Juyeop Kim (Yonsei University); Jun-Ho Choi (Yonsei University); Soobeom Jang (Yonsei University);
Jong-Seok Lee ("Yonsei University, Korea")*

1658: Channel-driven decentralized Bayesian federated learning for trustworthy decision making
in D2D networks
Luca Barbieri (Politecnico di Milano)*; Osvaldo Simeone (King's College London); Monica Nicoli
(Politecnico di Milano University)

1662: Cross-device Federated Learning for Mobile Health Diagnostics: A First Study on COVID-19
Detection
Tong Xia (University of Cambridge)*; Jing Han (); Abhirup Ghosh (University of Cambridge); Cecilia
Mascolo (University of Cambridge)

1668: Projected Hierarchical ALS for generalized Boolean matrix factorization

Rodrigo Cabral Farias (Université Côte d'Azur, CNRS, I3S Laboratory)*; Sebastian Miron (University of
Lorraine)

1679: PROVABLE COMPUTATIONAL AND STATISTICAL GUARANTEES FOR EFFICIENT

LEARNING OF CONTINUOUS-ACTION GRAPHICAL GAMES
Adarsh Barik (Purdue University)*; Jean Honorio (Purdue)

1691: A UNIFIED UNCERTAINTY-AWARE EXPLORATION: COMBINING EPISTEMIC AND ALEATORY

UNCERTAINTY
Parvin Malekzadeh (university of Toronto)*; Ming Hou (Department of National Defence’s Innovation for
Defence Excellence and Security (IDEaS) program, Canada); Konstantinos N Plataniotis (UofT)

1692: Independent Vector Analysis with multivariate Gaussian model: a scalable method by
multilinear regression
Ben Gabrielson (University of Maryland, Baltimore County)*; Mingyu Sun (University of Maryland,
Baltimore County); Mohammad Akhonda (UMBC); Vince Calhoun (TReNDS); Tulay Adali (University of
Maryland, Baltimore County)

1698: Towards Diverse and Coherent Augmentation for Time-Series Forecasting

Xiyuan Zhang (University of California, San Diego)*; Ranak Roy Chowdhury (University of California, San
Diego); Jingbo Shang (University of California, San Diego); Rajesh Gupta (UC San Diego); Dezhi Hong
(UC San Diego)

1701: Sparse Mixture Once-for-all Adversarial Training for Efficient In-Situ Trade-Off Between
Accuracy and Robustness of DNNs
Souvik Kundu (University of Southern California)*; Sairam Sundaresan (Intel AI Lab); Sharath Nittur
Sridhar (Intel AI Lab); SHUNLIN LU (The Chinese University of Hong Kong); han Tang (University of
Southern California); Peter A. Beerel (University of Southern California)

1706: Cross Modality Knowledge Distillation for Robust Pedestrian Detection in Low Light and
Adverse Weather Conditions
Mazin Hnewa (Michigan State University)*; Alireza Rahimpour (Ford Motor Company- Palo Alto); Justin
Miller (Ford); Devesh Upadhyay (Ford Motor Co.); Hayder Radha (Michigan State University)

1735: OPEN-SET AUTOMATIC TARGET RECOGNITION

Bardia Safaei (Johns Hopkins University)*; Vibashan VS (Johns Hopkins University); Celso M. de Melo
(DEVCOM Army Research Laboratory); Shuowen Hu (US Army Research Laboratory); Vishal Patel
(Johns Hopkins University)

116
1738: Training Robust Spiking Neural Networks on Neuromorphic Data with Spatiotemporal
Fragments
Haibo Shen (Huazhong University of Science and Technology)*; Yihao Luo (Yichang Testing Technique
R&D Institute); Xiang Cao (School of Computer Science and Technology, Huazhong University of Science
and Technology); Liangqi Zhang (Huazhong University of Science and Technology); Juyu Xiao (Huazhong
University of Science and Technology); Tianjiang Wang (School of Computer Science and Technology,
Huazhong University of Science and Technology)

1802: Introducing topography in convolutional neural networks

Maxime Poli (École Normale Supérieure)*; Emmanuel Dupoux (EHESS, ENS, PSL University, CNRS,
INRIA, META); Rachid Riad (CoML/NPI/ENS/CNRS/EHESS/INRIA/PSL/INSERM/UPEC)

1810: Aleatoric Uncertainty Estimation of Overnight Sleep Statistics through Posterior Sampling
using Conditional Normalizing Flows
Hans van Gorp (Eindhoven University of Technology)*; Merel M. van Gilst (Eindhoven University of
Technology); Pedro Fonseca (Philips Research); Sebastiaan Overeem (Eindhoven University of
Technology); Ruud J. G. van Sloun (Technical university of Eindhoven)

1828: Training set cleansing of backdoor poisoning by self-supervised representation learning

Hang Wang (The Pennsylvania State University)*; Sahar Karimi (Meta); Ousmane A Dia (Meta); Hippolyt
Ritter (Meta); Ehsan Emamjomeh-Zadeh (Meta); Jiahui Chen (Meta); Zhen Xiang (University of Illinois
Urbana-Champaign); David Miller (Pennsylvania State University); George Kesidis (Penn State
University)

1832: HiFi++: a Unified Framework for Bandwidth Extension and Speech Enhancement
Pavel Andreev (Samsung AI Center Moscow)*; Aibek Alanov (Artificial Intelligence Research Institute);
Oleg Ivanov (Samsung AI Center Moscow); Dmitry P Vetrov (Higher School of Economics)

1833: SUVR: A Search-based Approach to Unsupervised Visual Representation Learning

Yizhan Xu (National Cheng Kung University); Chih-Yao Chen (Academia Sinica)*; Cheng-Te Li (National
Cheng Kung University)

1837: Refined Pseudo Labeling for Source-free Domain Adaptive Object Detection
Siqi Zhang (Institute of Automation，Chinese Academy of Sciences)*; Lu Zhang (CASIA); Zhiyong Liu
(State Key Lab of Management and Control for Complex Systems, Institute of Automation, Chinese
Academy of Sciences)

1864: A Perturbation-based Policy Distillation Framework with Generative Adversarial Nets

LiHua Zhang (School of Computer Science and Technology, Soochow University)*; Quan Liu (School of
Computer Science and Technology, Soochow University); Zhang Xiongzhen (School of Computer
Science and Technology, Soochow University, Suzhou, China); Yapeng Xu (School of Computer Science
and Technology, Soochow University)

1868: Class-incremental learning on multivariate time series via shape-aligned temporal

distillation
Zhongzheng Qiao (Nanyang Technological University)*; Minghui Hu (Nanyang Technological University);
Xudong Jiang (Nanyang Technological University); Ponnuthurai Suganthan (Nanyang Technological
University); Ramasamy Savitha (I2R A*STAR)

1872: A geometric surrogate for simulation calibration

Lincon Souza (National Institute of Advanced Industrial Science and Technology (AIST))*; Bojan Batalo
(University of Tsukuba); Keisuke Yamazaki (National Institute of Advanced Industrial Science and
Technology)

117
1878: Jazznet: A Dataset of Fundamental Piano Patterns for Music Audio Machine Learning
Research
Tosiron Adegbija (University of Arizona)*

1961: The MBSTOI Binaural Intelligibility Metric Using a Close-Talking Microphone Reference
Pierre Guiraud (Imperial College London)*; Alastair H Moore (Imperial College London); Rebecca Vos
(Imperial College London); Patrick A. Naylor (Imperial College London); Mike Brookes (Imperial College
London)

1977: Batch Normalization damages Federated Learning on Non-IID data: Analysis and Remedy
Yanmeng Wang (The Chinese University of Hong Kong, Shenzhen)*; Qingjiang Shi (Tongji University);
Tsung-Hui Chang ("The Chinese University of Hong Kong,")

1991: HIPI: A Hierarchical Performer Identification model based on Symbolic Representation of

Music.
Syed RM Rafee (QUEEN MARY UNIVERSITY OF LONDON)*; George Fazekas (QMUL); Geraint A.
Wiggins (Vrije Universiteit Brussel)

1995: Adversarial Permutation Invariant Training for Universal Sound Separation

Emilian Postolache (Sapienza University of Rome)*; Jordi Pons (Dolby Laboratories); Santiago Pascual
(Dolby Laboratories); Joan Serrà (Dolby Laboratories)

2019: Accelerating matrix trace estimation by Aitken's $\Delta^2$ process

Vasileios Kalantzis (IBM Research)*; Georgios Kollias (IBM Research); Shashanka Ubaru (IBM
Research); Theodoros Salonidis (IBM T.J. Watson Research Center)

2024: Wav2Seq: Pre-training Speech-to-Text Encoder-Decoder Models Using Pseudo Languages

Felix Wu (ASAPP)*; Kwangyoun Kim (ASAPP); Shinji Watanabe (Carnegie Mellon University); Kyu Jeong
Han (ASAPP); Ryan Mcdonald (ASAPP); Kilian Weinberger (Cornell University); Yoav Artzi (Cornell
University)

2041: SIMILARITY RELATION PRESERVING CROSS-MODAL LEARNING FOR MULTISPECTRAL

PEDESTRIAN DETECTION AGAINST ADVERSARIAL ATTACKS
Jung Uk Kim (Kyung Hee University)*; Yong Man Ro (KAIST)

2051: Interpretable Multi-scale Neural Network for Granger Causality Discovery

Chenchen Fan (Lenovo Research)*; Yixin Wang (Lenovo Research); Yahong zhang (lenovo ); Wenli
Ouyang (Lenovo AI lab)

2054: Reliable Cluster-based Framework for Open Set Domain Adaptation

Xiu Zheng (Nanjing University)*; Yuan Huang (Nanjing University); Jie Tang (Nanjing University)

2065: TriCL: Triplet Continual Learning

Xianchao Zhang (Dalian University of Technology); Guanglu Wang (Dalian University of Technology);
Xiaotong Zhang (School of Software, Dalian University of Technology)*; Han Liu (Dalian University of
Technology); Zhengxi Yin (Huawei Technologies Co. Ltd); Wentao Yang (Dalian University of Technology)

2070: Multilayer Subspace Learning with Self-sparse Robustness for Two-dimensional Feature
Extraction
Han Zhang (Xidian University)*; Maoguo Gong (Xidian University); Feiping Nie (Northwestern
Polytechnical University); Xuelong Li (Northwestern Polytechnical University)

2091: Deep Survival Analysis and Counterfactual Inference Using Balanced Representations
Muskan Gupta (Tata Consultancy Services - Research); Gokul Kannan (NITT); Ranjitha Prasad (IIIT
Delhi)*; Garima Gupta (TCS Innovation Labs, Delhi)

118
2117: Batch-Ensemble Stochastic Neural Networks for Out-of-Distribution Detection
Xiongjie Chen (University of Surrey)*; Yunpeng Li (University of Surrey); Yongxin Yang (Queen Mary
University of London)

2119: Is Multi-Task Learning an Upper Bound for Continual Learning?

Zihao Wu (Vanderbilt University); Huy Tran (Vanderbilt University); Hamed Pirsiavash (University of
California Davis); Soheil Kolouri (Vanderbilt University)*

2131: SUPER-RESOLUTION INFORMATION ENHANCEMENT FOR CROWD COUNTING

Jiahao Xie (Beijing University of Posts and Telecommunications); Wei Xu (Beijing University of Posts and
Telecommunications); Dingkang Liang (Huazhong University of Science and Technology); Zhanyu Ma
(Beijing University of Posts and Telecommunications); Kongming Liang (Beijing University of Posts and
Telecommunications)*; Weidong Liu (China Mobile Research Institute); Rui Wang (China Mobile
Research Institute); Ling Jin (China Mobile Research Institute)

2149: Dynamic Vehicle Graph Interaction for Trajectory Prediction based on Video Signals
Jian Chen (Sun Yat-sen University); Wei Wang (Shenzhen MSU-BIT University)*; Junxin Chen (Dalian
University of Technology); Ming Cai (School of Engineering, Sun Yat-sen University)

2154: Cross-Domain Learning with Normalizing Flow

Chi Wang (Queen's University Belfast)*; Jian Gao (Queen's University Belfast); Yang Hua (Queen's
University Belfast); Hui Wang (Queen's University Belfast)

2161: LQGNet: Hybrid Model-Based and Data-Driven Linear Quadratic Stochastic Control
Solomon Goldgraber Casspi (Ben-Gurion University of the Negev); Oliver Husser (ETH Zurich); Guy
Revach (ETH Zürich); Nir Shlezinger (Ben-Gurion University)*

2164: Self-supervised Guided Hypergraph Feature Propagation for Semi-supervised Classification

with Missing Node Features
chengxiang lei (Huazhong University of Science and Technology); Sichao Fu (Huazhong University of
Science and Technology)*; Yuetian Wang (Huazhong University of Science and Technology); Wenhao
Qiu (Huazhong University of Science and Technology); Yachen Hu (Huazhong University of Science and
Technology); Qinmu Peng (Huazhong University of Science and Technology); Xinge YOU (Huazhong
University of Science and Technology)

2180: Ternary Weight Networks

Bin Liu (Shanghai Jiao Tong University); Fengfu Li (UCAS); Xiaoxing Wang (Shanghai Jiao Tong
University); Bo Zhang (Institute of Applied Mathematics, AMSS, Chinese Academy of Sciences); Junchi
Yan (Shanghai Jiao Tong University)*

2184: BATT: Backdoor Attack with Transformation-based Triggers

Tong Xu (Tsinghua University); Yiming Li (Tsinghua University)*; Yong Jiang (Tsinghua University); Shu-
Tao Xia (Tsinghua University)

2193: AMC-Net: An Effective Network for Automatic Modulation Classification

JiaWei Zhang (Xidian University); Tiantian Wang (Xidian University); Zhixi Feng (Xidian university)*;
Shuyuan Yang (Xidian University)

2195: WHC: Weighted Hybrid Criterion for Filter Pruning on Convolutional Neural Networks
Shaowu Chen (Shenzhen University)*; Weize Sun (Shenzhen University); Lei Huang (Shenzhen
University)

2230: Deep Root MUSIC Algorithm for Data-Driven DoA Estimation

Dor Haim Shmuel (Ben-Gurion University of the Negev); Julian P. Merkofer (TU Eindhoven); Guy Revach
(ETH Zürich); Ruud J. G. van Sloun (Technical university of Eindhoven); Nir Shlezinger (Ben-Gurion
University)*

119
2231: SDG-L: A Semiparametric Deep Gaussian Process based Framework for Battery Capacity
Prediction
Hanbing Liu (Tsinghua University); Yanru Wu (Tsinghua University); Yang Li (Tsinghua-Berkeley
Shenzhen Institute, Tsinghua University); Ercan E Kuruoglu (Tsinghua-Berkeley Shenzhen Institute)*;
Xuan Zhang (Tsinghua University)

2234: MEET: A Monte Carlo Exploration-Exploitation Trade-off for Buffer Sampling

Julius Ott (Infineon Technologies AG / Technical University Munich)*; Lorenzo Servadei (Infineon
Technologies AG); Jose Arjona-Medina (Johannes Kepler University Linz); Enrico Rinaldi (University of
Michigan); Gianfranco Mauro (Infineon Technologies AG); Daniela Sanchez Lopera (Infineon
Technologies AG / Technical University Munich); Michael Stephan (Infineon Technologies AG ); Thomas
Stadelmayer (Infineon Technologies AG); Avik Santra (Infineon Technologies AG); Robert Wille (Technical
University of Munich)

2244: A Nested Ensemble Method to Bilevel Machine Learning

Lisha Chen (RENSSELAER POLYTECHNIC INST); Momin Abbas (Rensselaer Polytechnic Institute);
Tianyi Chen (Rensselaer Polytechnic Institute)*

2246: POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural Networks
Randall Balestriero (Facebook AI Research)*; yann lecun (Facebook)

2257: Prefix-Level Detection and Autocorrection of Keyboard Input Errors

Jerome R Bellegarda (Apple)*

2259: Enhanced Embeddings in Zero-Shot Learning for Environmental Audio

Ysobel Sims (The University of Newcastle)*; Alexandre Mendes (The University of Newcastle); Stephan K
Chalup (The University of Newcastle)

2275: Removing Radio Frequency Interference from Auroral Kilometric Radiation with Stacked
Autoencoders
Allen Chang (University of Southern California)*; Mary Knapp (Massachusetts Institute of Technology
Haystack Observatory); James LaBelle (Dartmouth College); John Swoboda (Massachusetts Institute of
Technology Haystack Observatory); Ryan Volz (Massachusetts Institute of Technology Haystack
Observatory); Philip Erickson (Massachusetts Institute of Technology Haystack Observatory)

2285: Transformer-based tracking Network for Maneuvering Targets

yushu zhang (Tsinghua University)*; Gang Li (Tsinghua University); Xiao-Ping Zhang (Toronto
Metropolitan University); You He (Tsinghua University)

2375: Maximum Likelihood Distillation for Robust Modulation Classification

Javier J Maroto (EPFL)*; Gérôme Bovet (armasuisse Science & Technology); Pascal Frossard (EPFL)

2382: DIFFERENCE GUIDED VHR REMOTE SENSING IMAGE CHANGE DETECTION

Jiukai Sun (Northwestern Polytechnical University); Ganchao Liu (Northwestern Polytechnical
University); Xuelong Li (Northwestern Polytechnical University); Yuan Yuan (Northwestern Polytechnical
University)*

2388: PARAFAC2-based Coupled Matrix and Tensor Factorizations

Carla Schenker (Simula Metropolitan Center for Digital Engineering)*; Xiulin Wang (Affiliated Zhongshan
Hospital of Dalian University); Evrim Acar (Simula Metropolitan Center for Digital Engineering)

2391: MCKD: Mutually Collaborative Knowledge Distillation for Federated Domain Adaptation and
Generalization
Ziwei Niu (Zhejiang University); Hongyi Wang (Zhejiang University); Hao Sun (Zhejiang University); Shuyi
Ouyang (Zhejiang University); Yen-Wei Chen (Ritsumeikan University); Lanfen Lin (Zhejiang University)*

120
2398: A BANDIT ONLINE CONVEX OPTIMIZATION APPROACH TO DISTRIBUTED ENERGY
MANAGEMENT IN NETWORKED SYSTEMS
Ioannis Tsetis (University of Tübingen)*; Xiaotong Cheng (University Tübingen); Setareh Maghsudi
(University of Tübingen)

2434: Structural Reparameterization Lightweight Network for Video Action Recognition

AnLei Zhu (Jiangnan University)*; Wang Yinghui (Jiangnan University); Wei Li (Jiangnan University);
Pengjiang Qian (Jiangnan University)

2443: FFFN: Fashion Feature Fusion Network by Co-attention Model for Fashion Recommendation
Zhantu Lin (College of Computer Science and Software Engineering, Shenzhen University); Xiaoyan
Zhang (College of Computer Science and Software Engineering, Shenzhen University)*

2451: RØROS: Building a Responsive Online Recommender System via Meta-Gradients Updating
Xudong Pan (Fudan University)*; Mi Zhang (Fudan University); Duocai Wu (Ant Group)

2501: Learnable frontends that do not learn: Quantifying sensitivity to filterbank initialisation
Mark Anderson (Trinity College Dublin)*; Tomi H. Kinnunen (University of Eastern Finland); Naomi Harte
(Trinity College Dublin)

2503: Balanced Mixup Loss for Long-tailed Visual Recognition

Haibo Ye (Nanjing University of Aeronautics and Astronautics )*; Fangyu Zhou (Nanjing University of
Aeronautics and Astronautics); Xinjie Li (Nanjing University of Aeronautics and Astronautics); Qingheng
Zhang (Nanjing University of Aeronautics and Astronautics)

2518: PRIV-AUG-SHAP-ECGRESNET: PRIVACY PRESERVING SHAPLEY-VALUE ATTRIBUTED

AUGMENTED RESNET FOR PRACTICAL SINGLE-LEAD ELECTROCARDIOGRAM
CLASSIFICATION
Arijit Ukil (Tata Consultancy Services)*; Leandro Marin (University of Murcia); Antonio J. Jara (Libelium)

2526: Local Graph-homomorphic Processing for Privatized Distributed Systems

Elsa Rizk (EPFL)*; Stefan Vlaski (Imperial College London); Ali H. Sayed (Ecole Polytechnique Fédérale
de Lausanne)

2547: TREEXGNN: CAN GRADIENT-BOOSTED DECISION TREES HELP BOOST

HETEROGENEOUS GRAPH NEURAL NETWORKS?
Ming-Yi Hong (National Taiwan University); Shih-Yen Chang (National Taiwan University); Hao-Wei Hsu
(National Taiwan University); Yi-Hsiang Huang (National Taiwan University); Chih-Yu Wang (Academia
Sinica); Che Lin (National Taiwan University)*

2555: I hear your true colors: Image Guided Audio Generation

Roy Sheffer (The Hebrew University of Jerusalem, Israel)*; Yossi Adi (Facebook AI Research )

2579: Enhancing Representation Learning with Deep Classifiers in Presence of Shortcut

Amirhossein Ahmadian (Linköping University)*; Fredrik Lindsten (Linköping University)

2583: AN ONLINE ALGORITHM FOR CHANCE CONSTRAINED RESOURCE ALLOCATION

Yuwei Chen (Cainiao Network)*; Zengde Deng (Cainiao Network); Yinzhi Zhou (Cainiao Network); Zaiyi
Chen (Cainiao Network); yujie chen (Cainiao network); Haoyuan Hu (Cainiao Network)

2586: Learning with Multigraph Convolutional Filters

Landon G Butler (University of California, Berkeley)*; Alejandro Parada-Mayorga (University of
Pennsylvania); Alejandro Ribeiro (University of Pennsylvania)

121
2596: Learned Kalman Filtering in Latent Space with High-Dimensional Data
Itay Buchnik (Ben Gurion University); Damiano Steger (ETH Zurich); Guy Revach (ETH Zürich); Ruud J.
G. van Sloun (Technical university of Eindhoven); Tirza S Routtenberg (Ben Gurion University of the
Negev); Nir Shlezinger (Ben-Gurion University)*

2598: MENDAM: Multi-Expert Network with Distribution-Aware Momentum for Long-Tailed

Recognition
Qingheng Zhang (Nanjing University of Aeronautics and Astronautics)*; Haibo Ye (Nanjing University of
Aeronautics and Astronautics ); Kaicheng Yu (Alibaba Inc.)

2612: Implicit Bayes Adaptation: A Collaborative Transport Approach

Bo Jiang (North Carolina State University)*; Hamid Krim (North Carolin. State Univ.); Tianfu Wu (NC State
University); Derya Cansever (US Army Research Office)

2626: Utility pole localization by learning from ambient traces on distributed acoustic sensing
Zhuocheng Jiang (NEC laboratories America, Inc. )*; Yue Tian (NEC laboratories America, Inc. ); Yangmin
Ding (NEC Labs America); Sarper Ozharar (NEC laboratories America, Inc.); Ting Wang (NEC
laboratories America, Inc.)

2651: Generative Modeling Based Manifold Learning for Adaptive Filtering Guidance
Karim Helwani (Amazon)*; Paris Smaragdis (University of Illinois at Urbana-Champaign); Michael M
Goodwin (AWS )

2655: AURA: PRIVACY-PRESERVING AUGMENTATION TO IMPROVE TEST SET DIVERSITY IN

SPEECH ENHANCEMENT
xavier gitiaux (Microsoft)*; Aditya Khant (Microsoft); Ross Cutler ( Microsoft Corporation); Chandan Reddy
(Google); Ebrahim Beyrami (Microsoft); Jayant Gupchup (Microsoft)

2659: QuantPipe: Applying Adaptive Post-Training Quantization for Distributed Transformer

Pipelines in Dynamic Edge Environments
Haonan Wang (University of Southern California)*; Connor Imes (Information Sciences Institute, USC);
Souvik Kundu (University of Southern California); Peter A. Beerel (University of Southern California);
Stephen Crago (Information Sciences Institute, USC); John Paul Walters (Information Sciences Institute,
USC)

2672: Fed-3DA: A Dynamic and Personalized Federated Learning Framework

Hui Wang (SKLSDE, School of Computer Science and Engineering, Beihang University, Beijing, China)*;
Jie Sun (Beihang University); Tianyu Wo (Beihang University); Xudong Liu (Beihang University)

2675: Performing Neural Architecture Search Without Gradients

Pavel Rumiantsev (McGill University)*; Mark Coates (McGill University)

2678: GANStrument: Adversarial Instrument Sound Synthesis with Pitch-invariant Instance

Conditioning
Gaku Narita (Sony Computer Science Laboratories)*; Junichi Shimizu (Sony Computer Science
Laboratories); Taketo Akama (Sony CSL)

2696: ADAPTIVE SUBMANIFOLD-PRESERVING SPARSE REGRESSION FOR FEATURE

SELECTION AND MULTICLASS CLASSIFICATION
Rui Xu (Renmin University of China)*; Xun Liang (Renmin University of China)

122
2707: Training Stronger Spiking Neural Networks with Biomimetic Adaptive Internal Association
Neurons
Haibo Shen (Huazhong University of Science and Technology)*; Yihao Luo (Yichang Testing Technique
R&D Institute); Xiang Cao (School of Computer Science and Technology, Huazhong University of Science
and Technology); Liangqi Zhang (Huazhong University of Science and Technology); Juyu Xiao (Huazhong
University of Science and Technology); Tianjiang Wang (School of Computer Science and Technology,
Huazhong University of Science and Technology)

2728: Cross-Domain Object Classification via Successive Subspace Alignment

Kecheng Chen (City University of Hong Kong)*; Haoliang Li (CityU); Hong Yan (City University of Hong
Kong)

2745: Robust Time Series Recovery and Classification Using Test-Time Noise Simulator Networks
Eun Som Jeon (Arizona State University)*; Suhas Lohit (Mitsubishi Electric Research Laboratories);
Rushil Anirudh (Lawrence Livermore National Laboratory); Pavan Turaga (Arizona State University)

2747: CoRe: Transferable Long-Range Time Series Forecasting Enhanced by Covariates-Guided

Representation
Xin-Yi Li (State Key Laboratory for Novel Software Technology, Nanjing University); Pei-Nan Zhong
(General Development Dept, Huawei Technologies Co. Ltd.); Di Chen (State Key Laboratory for Novel
Software Technology, Nanjing University); Yu-Bin Yang (State Key Laboratory for Novel Software
Technology, Nanjing University)*

2785: Improving Noisy Student Training on Non-target Domain Data for Automatic Speech
Recognition
YU CHEN (University of Hong Kong)*; Wen Ding (NVIDIA); Junjie Lai (NVIDIA)

2794: Strategies for Enhanced Signal Modulation Classifications Under Unknown Symbol Rates
and Noise Conditions
Ruixuan Wang (Villanova University); Yue Qi (villanova university); Mojtaba Vaezi (Villanova University);
Xun Jiao (Villanova University)*; Moeness Amin (Villanova University)

2813: Invariant Adversarial Imitation Learning from Visual Inputs

Haoran Zhang (East China Normal university)*; Yinghong Tian (East China Normal University); Liang
Yuan (Beijing University of Chemical Technology); Yue Lu (East China Normal University)

2828: MEASURING DEVIATION FROM STOCHASTICITY IN TIME-SERIES USING AUTOENCODER

BASED TIME-INVARIANT REPRESENTATION: APPLICATION TO BLACK HOLE DATA
Sai Pradeep Chakka (IIIT Bangalore)*; Neelam Sinha (IIIT Bangalore); Banibrata Mukhopadhyay (Indian
Institute of Science)

2848: Regularized Deep Generative Model Learning for Real-time Massive MIMO Channel Tracking
Lixiang Lian (ShanghaiTech University ); Ben Wang (ShanghaiTech University)*

2853: PU-EdgeFormer: Edge Transformer for Dense Prediction in Point Cloud Upsampling
Dohoon Kim (Chung-Ang University); Minwoo Shin (Chungang University); Joonki Paik (Chungang
University)*

2855: Tree-like Interaction Learning for Bundle Recommendation

Haole Ke (Wuhan University of Technology)*; Lin Li (Wuhan University of Technology); Peipei Wang
(Wuhan University of Technology); Jingling Yuan (Wuhan University of Technology); Xiaohui Tao (The
University of Southern Queensland)

123
2886: Towards Real-Time Person Search with Invariant Feature Learning
Chengyou Jia (Xi'an Jiaotong University)*; Minnan Luo (School of Electronic and Information Engineering,
Xi'an Jiaotong University); Zhuohang Dang (Xi'an Jiaotong University); Xiaojun Chang (University of
Technology Sydney); Qinghua Zheng (Xi'an Jiaotong University)

2906: Select the Best: Enhancing Graph Representation with Adaptive Negative Sample Selection
Xiangping Zheng (Renmin University of China)*; Xun Liang (Renmin University of China); Bo Wu (Renmin
University of China)

2911: NOWCASTING OF EXTREME PRECIPITATION USING DEEP GENERATIVE MODELS

Haoran Bin (TU Delft); Max Kyryliuk (TU Delft); Zhiyi Wang (TU Delft); Cristian Meo (TUDelft); Yanbo
Wang (TU Delft); Ruben Imhoff (Deltares); Remko Uijlenhoet (TU Delft); Justin Dauwels (TU Delft)*

2925: Leveraging neural koopman operators to learn continuous representations of dynamical

systems from scarce data
Anthony Frion (IMT Atlantique)*; Lucas Drumetz (IMT Atlantique); Mauro Dalla Mura (Grenoble INP);
Guillaume Tochon (EPITA Research and Development Laboratory (LRDE)); Abdeldjalil Aissa-El-Bey
(France)

2934: ROBUST BINARY COMPONENT DECOMPOSITIONS

Christos Kolomvakis (University of Mons)*; Nicolas Gillis (Université de Mons)

2943: PERSONALIZED FEDERATED LEARNING ON LONG-TAILED DATA VIA ADVERSARIAL

FEATURE AUGMENTATION
Yang Lu (Xiamen University); Pinxin Qian (Xiamen University); Gang Huang (Zhejiang Lab); Hanzi Wang
(Xiamen University)*

2946: SEMI-SUPERVISED LEARNING WITH PER-CLASS ADAPTIVE CONFIDENCE SCORES FOR

ACOUSTIC ENVIRONMENT CLASSIFICATION WITH IMBALANCED DATA
Luan V. Fiorio (Eindhoven University of Technology)*; Boris Karanov (Eindhoven University of
Technology); Johan David (NXP Semiconductors); Wim van Houtum (NXP Semiconductors); Frans
Widdershoven (NXP Semiconductors); Ronald Aarts (Eindhoven University of Technology)

3028: Constrained Dynamical Neural ODE for Time Series Modelling: A Case Study on Continuous
Emotion Prediction
Ting Dang (University of Cambridge)*; Antoni Dimitriadis (University of New South Wales); Jingyao Wu
(University of New South Wales); Vidhyasaharan Sethu (University of New South Wales); Eliathamby
Ambikairajah (The University of New South Wales)

3045: Feature Space Recovery for Incomplete Multi-view Clustering

Zhen Long (University of Electronic Science and Technology of China); Ce Zhu (University of Electronic
Science & Technology of China)*; Pierre Comon (Univ. Grenoble Alpes); Yipeng Liu (University of
Electronic Science and Technology of China)

3052: DTTR: DETECTING TEXT WITH TRANSFORMERS

Jing Yang (Hunan University)*; Zhiqiang You (Hunan University); Zhiwei Zhong (Hunan University); peng
liu (Guangdong university of technology); Langqi Mei (npic); Shenguang Huang (Ningbo Port Information
Communication Co., Ltd.)

3080: OTW: Optimal Transport Warping for Time Series

Fabian R Latorre (EPFL)*; Chenghao Liu (Salesforce); Doyen Sahoo (Salesforce); Steven Hoi
(Salesforce)

124
3085: Voice Conversion Using Feature Specific Loss Function based Self-Attentive Generative
Adversarial Network
Sandipan Dhar (National Institute of Technology Durgapur); Padmanabha Banerjee (Jalpaiguri
Engineering College); Dr. Nanda Dulal Jana (NIT Durgapur); Swagatam Das (Indian Statistical Institute)*

3090: Exploration of Language Dependency for Japanese Self-Supervised Speech Representation

Models
Takanori Ashihara (NTT Corp.)*; Takafumi Moriya (NTT); Kohei Matsuura (NTT); Tomohiro Tanaka (NTT
Corp.)

3097: STRUCTURED-ANCHOR PROJECTED CLUSTERING FOR HYPERSPECTRAL IMAGES

Guozhu Jiang (China University of Geosciences); jie zhang (University of Macau); Yongshan Zhang
(China University of Geosciences)*; Xinwei Jiang (China University of Geosciences); Zhihua Cai (China
University of Geosciences)

3100: Self-supervised Facial Action Unit Detection with Region and Relation Learning
Juan Song (Tianjin University); Zhilei Liu (Tianjin University)*

3159: FAST SINGLE-PERSON 2D HUMAN POSE ESTIMATION USING MULTI-TASK

CONVOLUTIONAL NEURAL NETWORKS
Christos Papaioannidis (Aristotle University of Thessaloniki)*; Ioannis Mademlis (Department of
Informatics, Aristotle University of Thessaloniki); Ioannis Pitas (Aristotle University of Thessaloniki)

3180: CONDITIONING AND SAMPLING IN VARIATIONAL DIFFUSION MODELS FOR SPEECH

SUPER-RESOLUTION
Chin-Yun Yu (Queen Mary University of London)*; Sung-Lin Yeh (University of Edinburgh); George
Fazekas (QMUL); Hao Tang (The University of Edinburgh)

3184: ACTIVITY-INFORMED INDUSTRIAL AUDIO ANOMALY DETECTION VIA SOURCE

SEPARATION
Jaechang Kim (POSTECH); YUNJOO LEE (POSTECH); Hyun Mi Cho (POSCO ICT); Dong Woo Kim
(POSCO ICT); Chi Hoon Song (POSCO ICT); Jungseul Ok (POSTECH)*

3202: WordReg: Mitigating the Gap between Training and Inference with Worst-case Drop
Regularization
Jun Xia (Westlake University)*; Ge Wang (Westlake University); Bozhen Hu (Zhejiang University &
Westlake University); Cheng Tan (Zhejiang University & Westlake University); Jiangbin Zheng (Westlake
University); Yongjie Xu (Westlake University); Stan Z. Li (Westlake University)

3207: JOINT ANN-SNN CO-TRAINING FOR OBJECT DETECTION AND IMAGE SEGMENTATION
Marc J Baltes (Ohio University); Nidal Abuhajar (Ohio University); Ye Yue (Ohio University); Charles
Smith (University of Kentucky); Jundong Liu (Ohio University)*

3256: Enrollment Rate Prediction in Clinical Trials based on CDF Sketching and Tensor
Factorization tools
Magda Amiridi (University of Virginia)*; Cheng Qian (IQVIA); Nicholas D Sidiropoulos (University of
Virginia); Lucas Glass (IQVIA)

3259: TOWARDS ROBUST DATA-DRIVEN UNDERWATER ACOUSTIC LOCALIZATION: A DEEP CNN

SOLUTION WITH PERFORMANCE GUARANTEES FOR MODEL MISMATCH
Amir Weiss (Massachusetts Institute of Technology)*; Andrew C Singer (University of Illinois); Gregory W
Wornell (MIT)

125
3267: Prune then Distill: Dataset Distillation with Importance Sampling
Anirudh S Sundar (Georgia Institute of Technology)*; Gokce Keskin (Amazon Inc.); Chander Chandak
(Amazon Inc.); I-Fan Chen (Amazon Inc.); Pegah Ghahremani (Amazon Inc.); Shalini Ghosh (Amazon
Alexa AI)

3270: Audio Barlow Twins: Self-Supervised Audio Representation Learning

Jonah Anton (Imperial College London)*; Harry Coppock (Imperial College London); Pancham Shukla
(Imperial College London); Bjoern W. Schuller (Imperial College London)

3308: MCROOD: MULTI-CLASS RADAR OUT-OF-DISTRIBUTION DETECTION

Sabri Mustafa Kahya (Technical University of Munich)*; Muhammet Sami Yavuz (Technical University of
Munich); Eckehard Steinbach (TUM)

3315: SuperCM: Revisiting Clustering for Semi-Supervised Learning

Durgesh K. Singh (UiT The Arctic University of Norway)*; Ahcène Boubekki ( UiT - The Arctic University of
Norway ); Robert Jenssen ( UiT - The Arctic University of Norway); Michael C. Kampffmeyer (UiT The
Arctic University of Norway)

3335: Visual Prompting for Adversarial Robustness

Aochuan Chen (Michigan State University)*; Peter Lorenz (Fraunhofer); Yuguang Yao (Michigan State
University); Pin-Yu Chen (IBM Research); Sijia Liu (Michigan State University)

3364: Guided Speech Enhancement Network

Yang Yang (Google LLC)*; Shao-Fu Shih (Google LLC); Hakan Erdogan (Google); Jamie Menjay Lin
(Google); Chehung Lee (Google LLC); Yunpeng Li (Google); George Sung (Google LLC); Matthias
Grundmann (Google Research)

3374: ADAPTIVE STEP-SIZE METHODS FOR COMPRESSED SGD

Adarsh Muthuveeru-Subramaniam (University of Illinois at Urbana-Champaign)*; Akshayaa Magesh
(University of Illinois at Urbana-Champaign); Venugopal V. Veeravalli (University of Illinois at Urbana
Champaign)

3380: Improving Electric Load Demand Forecasting with Anchor-based Forecasting Method
Maria Tzelepi (Aristotle University of Thessaloniki)*; Paraskevi Nousi (Aristotle University of Thessaloniki);
ANASTASIOS TEFAS (Aristotle University of Thessaloniki)

3392: Bayesian Optimization with Ensemble Learning Models and Adaptive Expected
Improvement
Konstantinos D. Polyzos (University of Minnesota)*; Qin Lu (University of Minnesota); Georgios B.
Giannakis (University of Minnesota)

3394: Physics-Informed Transfer Learning for Voltage Stability Margin Prediction

Manish K Singh (University of Minnesota)*; Konstantinos D. Polyzos (University of Minnesota); Panagiotis
Traganitis (Michigan State University); Sairaj Dhople (University of Minnesota); Georgios B. Giannakis
(University of Minnesota)

3402: Active Subsampling Using Deep Generative Models by Maximizing Expected Information
Gain
Koen van de Camp (Eindhoven University of Technology)*; Hamdi Joudeh (Eindhoven University of
Technology); Duarte Antunes (Eindhoven University of Technology); Ruud J. G. van Sloun (Technical
university of Eindhoven)

3414: PROGRESSIVE DIVERSIFYING POLICY FOR MULTI-AGENT REINFORCEMENT LEARNING

Shaoqi Sun (National University of Defense Technology); Yuanzhao Zhai (National University of Defense
Technology); Kele Xu (National Key Laboratory of Parallel and Distributed Processing (PDL))*; Dawei
Feng (National University of Defense Technology); Ding Bo (National University of Defense Technology)

126
3438: Zero-shot domain adaptation of anomalous samples for semi-supervised anomaly detection
Tomoya Nishida (Hitachi, Ltd.)*; Takashi Endo (Hitachi, Ltd.); Yohei Kawaguchi (Hitachi, Ltd.)

3439: Estimation of High-Dimensional Differential Graphs from Multi-Attribute Data

Jitendra K Tugnait (Auburn University)*

3448: Tempo vs. Pitch: understanding self-supervised tempo estimation

Giovana V Morais (University of São Paulo)*; Matthew Davies (INESTEC); Marcelo Queiroz (University of
São Paulo); Magdalena Fuentes (New York University)

3450: Leveraging Language Embeddings for Cross-lingual Self-supervised Speech

Representation Learning
Tomohiro Tanaka (NTT)*; Ryo Masumura (NTT Corporation); Mana Ihori (NTT); Hiroshi Sato (NTT
Corporation); Taiga Yamane (NTT); Takanori Ashihara (NTT Corp.); Kohei Matsuura (NTT); Takafumi
Moriya (NTT)

3468: SADI: A SELF-ADAPTIVE DECOMPOSED INTERPRETABLE FRAMEWORK FOR

ELECTRICITY LOAD FORECASTING UNDER EXTREME EVENTS
Hengbo LIU (Alibaba DAMO Academy)*; Ziqing MA (Alibaba); Linxiao Yang (Machine Intelligence
Technology, Alibaba Group, Hangzhou, China); Tian Zhou (Alibaba DAMO Academy); Rui Xia (University
of Cambridge); Yi Wang (The University of Hong Kong); Qingsong Wen (Alibaba Group U.S.); Liang Sun
(Alibaba Group)

3492: Search for efficient deep visual-inertial odometry through neural architecture search
Yu Chen (University of Michigan)*; Mingyu Yang (University of Michigan); Hun Seok Kim (Nil)

3508: Optimal Compression for Minimizing Classification Error Probability: an Information-

Theoretic Approach
Jingchao Gao (the University of Iowa)*; Ao Tang (Cornell University); Weiyu Xu (University of Iowa)

3520: DECOMFORMER: DECOMPOSE SELF-ATTENTION VIA FOURIER TRANSFORM FOR VHR

AERIAL IMAGE SCENE CLASSIFICATION
Yan Zhang (Chongqing University of Posts and Telecommunications); Xiyuan Gao (Chongqing University
of Posts and Telecommunications); Xiao PU (Chongqing University of Posts and Telecommunications);
Tao Wang (Chongqing University of Posts and Telecommunications); Xinbo Gao (Chongqing University of
Posts and Telecommunications)*

3546: Multimodal Knowledge Distillation for Arbitrary-Oriented Object Detection in Aerial Images
Zhanchao Huang (Beijing Institute of Technology)*; Wei Li (Beijing Institute of Technology, Beijing, China);
Ran Tao (Beijing Institute of Technology)

3557: REDUCING THE COMPUTATIONAL COMPLEXITY OF LEARNING WITH RANDOM

CONVOLUTIONAL FEATURES
Mohammad Amin Omidi (Shahed University)*; Babak Seyfe (Shahed University); Shahrokh Valaee
(University of Toronto)

3565: Scalable Weight Reparametrization for Efficient Transfer Learning

Byeonggeun Kim (Amazon Alexa AI)*; Jun-Tae Lee (Qualcomm AI Research); Seunghan Yang
(Qualcomm AI Research); Simyung Chang (Qualcomm AI Research)

3571: A Bayesian Perspective for Determinant Minimization Based Robust Structured Matrix
Factorization
Gokcan Tatli (University of Wisconsin-Madison)*; Alper Erdogan (Koc University)

127
3590: Large-Scale Contrastive Language-Audio Pretraining with Feature Fusion and Keyword-to-
Caption Augmentation
Yusong Wu (Mila, University of Montreal)*; Ke Chen (University of California San Diego); Tianyu Zhang
(Mila, Université de Montréal); Yuchen Hui (Université de Montréal); Taylor Berg-Kirkpatrick (UCSD);
Shlomo Dubnov (UC San Diego)

3638: Zero-Shot Anomalous Sound Detection in Domestic Environments Using Large-Scale

Pretrained Audio Pattern Recognition Models
Alessandro I Mezza (Politecnico di Milano )*; Giulio Zanetti (Politecnico di Milano); Maximo Cobos
(Universitat de Valencia); Fabio Antonacci (Politecnico di Milano)

3645: Hint-dynamic Knowledge Distillation

Yiyang Liu (Xiamen University)*; Chenxin Li (Xiamen University); Xiaotong Tu (Xiamen University);
Xinghao Ding (Xiamen University); Yue Huang (Xiamen University)

3663: EXPLOITING SEMANTIC ATTRIBUTES FOR TRANSDUCTIVE ZERO-SHOT LEARNING

Zhengbo Wang (University of Science and Technology of China)*; Jian Liang (CASIA); Zilei Wang
(University of Science and Technology of China); Tieniu Tan (NLPR, China)

3665: Robust Log-based Anomaly Detection with Hierarchical Contrastive Learning

Yuhui Zhao (Sichuan University); Ruichun Yang (The Chinese University of Hong Kong, Shenzhen); Ning
Yang (Sichuan University)*; Tao LIN (Sichuan University); Qiuai Fu (HUAWEI CLOUD COMPUTING
TECHNOLOGIES CO., LTD.); YUCHI MA (HUAWEI CLOUD)

3667: CONVERGENCE ANALYSIS OF GRAPHICAL GAME-BASED NASH $Q-$LEARNING USING

THE INTERACTION DETECTION SIGNAL OF $\mathcal{N}-$STEP RETURN
Yunkai Zhuang (Nanjing University)*; Shangdong Yang (Nanjing University of Posts and
Telecommunications); Wenbin Li (Nanjing University); Yang Gao (Nanjing University)

3670: Convex Optimization of Deep Polynomial and ReLU Activation Neural Networks
Burak Bartan (Stanford University)*; Mert Pilanci (Stanford University)

3690: On Adversarial Robustness of Audio Classifiers

Kangkang Lu (A-STAR)*; Cuong Nguyen (Institute for Infocomm Research, A*STAR); Xun Xu (Institute for
Infocomm Research, A*STAR); Chuan Sheng Foo (Institute for Infocomm Research, A*STAR)

3717: Diversifying Message Aggregation in Multi-Agent Communication via Normalized Tensor

Nuclear Norm Regularization
Yuanzhao Zhai (National University of Defense Technology); Kele Xu (National Key Laboratory of Parallel
and Distributed Processing (PDL))*; Ding Bo (National University of Defense Technology); Dawei Feng
(National University of Defense Technology); Zijian Gao (National University of Defense Technology);
Huaimin Wang (National University of Defense Technology)

3724: Time-varying Signals Recovery via Graph Neural Networks

Jhon A Castro Correa (University of Delaware); Jhony H. Giraldo (Télécom Paris)*; Anindya Mondal
(Jadavpur University); Mohsen Badiey (University of Delaware); Thierry BOUWMANS (Univ. La Rochelle);
Fragkiskos Malliaros (CentraleSupelec)

3732: Change Point Detection with Neural Online Density-ratio Estimator

Xiuheng Wang (Université Côte d’Azur, CNRS, OCA)*; Ricardo Borsoi (UL); Cédric Richard (University
Nice Sophia Antipolis); Jie Chen (Northwestern Polytechnical University)

3735: Audio-Visual Inpainting: Reconstructing Missing Visual Information with Sound

Valentina Sanguineti (Istituto Italiano di Tecnologia); Sanket Thakur (Istituto Italiano di Tecnologia); Pietro
Morerio (Istituto Italiano di Tecnologia)*; Alessio Del Bue (Istituto Italiano di Tecnologia (IIT)); Vittorio
Murino (Istituto Italiano di Tecnologia)

128
3740: A MEMORY-FREE EVOLVING BIPOLAR NEURAL NETWORK FOR EFFICIENT MULTI-LABEL
STREAM LEARNING
Sourav Mishra (Indian Institute of Science, Bangalore)*; Suresh Sundaram (Indian Institute of Science)

3748: UAV Local Path Planning Based on Improved Proximal Policy Optimization Algorithm
Jiahao xu (Nanjing University of Aeronautics and Astronautics)*; Xuefeng Yan (Nanjing University of
Aeronautics and Astronautics ); Peng Cui (Dalian Naval Academy); Xinquan Wu (Nanjing University of
Aeronautics and Astronautics); Lipeng Gu (Nanjing University of Aeronautics and Astronautics); Yan biao
Niu (Nanjing University of Aeronautics and Astronautics)

3750: Does Your Model Think Like an Engineer? Explainable AI for Bearing Fault Detection with
Deep Learning
Thomas Decker (Siemens AG and Ludwig Maximilians University)*; Michael Lebacher (Siemens AG);
Volker Tresp (Siemens AG and Ludwig Maximilian University of Munich )

3752: Incorporating reliability in graph information propagation by fluid dynamics diffusion: a

case of multimodal semisupervised deep learning
Andrea Marinoni (UiT the Arctic University of Norway)*; Marine Mercier (University of Cambridge); Qian
Shi (Sun Yat-sen University); Sivasakthy Selvakumaran (University of Cambridge); Mark Girolami
(University of Cambridge)

3759: Multi-layer Seasonal Perception Network for Time Series Forecasting

Ruoshu Wang (Engineering Research Center of Cyberspace;Yunnan University); Shengfa Miao (Yunnan
University)*; Di Liu (Yunnan University); Xin Jin (Yunnan University); Weisheng Zhang (Yunnan
University)

3766: Intent Does Matter! Propagating High-order Relations for Exploring Interest Preferences
Xiangping Zheng (Renmin University of China)*; Xun Liang (Renmin University of China); Bo Wu (Renmin
University of China); Junlan Feng (China Mobile Research Institute); Yuhui Guo (Renmin University of
China); Sensen Zhang (Renmin University of China)

3798: Feature-Rich Audio Model Inversion for Data-Free Knowledge Distillation Towards General
Sound Classification
Zuheng Kang (Ping An Technology (Shenzhen) Co., Ltd); Yayun He (Ping An Technology (Shenzhen)
Co., Ltd); Jianzong Wang (Ping An Technology (Shenzhen) Co., Ltd)*; Junqing Peng (Ping An Technology
(Shenzhen) Co., Ltd); Xiaoyang Qu (Ping An Technology (Shenzhen) Co., Ltd); Jing Xiao (Ping An
Insurance (Group) Company of China)

3811: TeAw: Text-Aware Few-Shot Remote Sensing Image Scene Classification

Kaihui Cheng (National Innovation Institute of Defense Technology, Academy of Military Science)*; Chule
Yang (Defense Innovation Institute（DII）); Zunlin Fan (National Innovation Institute of Defense
Technology, China); Dayan Wu (Institute of Information Engineering, Chinese Academy of Sciences);
Naiyang Guan (National Innovation Institute of Defense Technology;Tianjin Artificial Intelligence
Innovation Center)

3817: Learning from Label Proportion with Online Pseudo-Label Decision by Regret Minimization
Shinnosuke Matsuo (Kyushu University)*; Seiichi Uchida (Kyushu University); Ryoma Bise (Kyushu
University); Daiki Suehiro (Kyushu University)

3818: Blind Estimation of Audio Processing Graph

Sungho Lee (Seoul National University)*; Jaehyun Park (Seoul National University); Seungryeol Paik
(Seoul National University); Kyogu Lee (Seoul National University)

129
3861: Spatial Cross-Attention for Transformer-based Image Captioning
Khoa Anh Ngo (Seoul National University)*; Kyuhong Shim (Seoul National University); Byonghyo Shim
(Seoul National University)

3875: On the Value of Stochastic Side Information in Online Learning

Junzhang Jia (University of Melbourne)*; Xuetong Wu (University of Melbourne); Jamie S Evans
(University of Melbourne); Jingge Zhu (University of Melbourne)

3879: Towards hyperbolic regularizers for point cloud part segmentation

Antonio Montanaro (Politecnico di Torino); Diego Valsesia (Politecnico di Torino)*; Enrico Magli (POLITO)

3882: Topology Uncertainty Modeling For Imbalanced Node Classification on Graphs

Jiayi Gao (Southeast University); Jiaxing Li (Southeast University); Ke Zhang (Southeast University);
Youyong Kong (Southeast University)*

3897: MULTI-RESOLUTION CONVOLUTIONAL DICTIONARY LEARNING FOR RIVERBED

DYNAMICS MODELING
Eisuke Kobayashi (Niigata Univ.)*; Hiroyasu Yasuda (Niigata Univ.); Kiyoshi Hayasaka (Niigata Univ.); Yu
Otake (Tohoku Univ.); Shunsuke Ono (Tokyo Institute of Technology); Shogo Muramatsu (Niigata Univ.)

3902: Smoothing Point Adjustment-based Evaluation of Time Series Anomaly Detection

Mingyu Liu ("National University of Defense Technology, China")*; Yijie Wang (" National University of
Defense Technology, China"); Hongzuo Xu (National University of Defense Technology); Xiaohui Zhou
(National University of Defense Technology); Bin Li (National University of Defense Technology); Yongjun
Wang (College of Computer, National University of Defense Technology)

3942: DEEP REINFORCEMENT LEARNING FOR GREEN UAV-ASSISTED DATA COLLECTION

Abhishek Mondal (National Institute of Technology Silchar)*; Deepak Mishra (University of New South
Wales, Sydney); Ganesh Prasad (National Institute of Technology Silchar); Ashraf Hossain (National
Institute of Technology Silchar)

3947: CLASS-GUIDED TRIPLE HEAD PREDICTION NETWORK FOR LONG-TAIL OBJECT

DETECTION
xuyang liu (Inner Mongolia University); Yuan Zheng (Inner Mongolia University)*

3996: Multi-Agent Adversarial Training Using Diffusion Learning

Ying Cao (École polytechnique fédérale de Lausanne - EPFL)*; Elsa Rizk (EPFL); Stefan Vlaski (Imperial
College London); Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)

4044: DEEP AUTOENCODING ONE-CLASS TIME SERIES ANOMALY DETECTION

Xudong Mou (Beihang University)*; Rui Wang (Beihang University); tiejun wang (BeiHang University); Jie
Sun (Beihang University); Bo Li (Beihang University); Tianyu Wo (Beihang University ); Xudong Liu
(Beihang University )

4047: SIGNAL RECONSTRUCTION FOR FMCW RADAR INTERFERENCE MITIGATION USING DEEP
UNFOLDING
Jeroen Overdevest (NXP Semiconductors, Technical University of Eindhoven)*; Arie G.C. Koppelaar
(NXP Semiconductors); Marco J.G. Bekooij (NXP Semiconductors); Jihwan Youn (Technical University of
Eindhoven); Ruud J. G. van Sloun (Technical university of Eindhoven)

4048: SHUFFLEAUGMENT: A DATA AUGMENTATION METHOD USING TIME SHUFFLING

Yoshinao Sato (Fairy Devices Inc.)*; Narumitsu Ikeda (Graduate School of Information Science and
Technology, The University of Tokyo); Hirokazu Takahashi (Graduate School of Information Science and
Technology, The University of Tokyo)

130
4064: Frequency and Scale Perspectives of Feature Extraction
Liangqi Zhang (Huazhong University of Science and Technology)*; Yihao Luo (Yichang Testing Technique
R&D Institute); Xiang Cao (School of Computer Science and Technology, Huazhong University of Science
and Technology); Haibo Shen (Huazhong University of Science and Technology); Tianjiang Wang (School
of Computer Science and Technology, Huazhong University of Science and Technology)

4072: Receptive Field Reliant Zero-Cost Proxies for Neural Architecture Search
Prateek Keserwani (Samsung Research Institute Bangalore)*; Srinivas S Miriyala (Samsung Research
Institute Bangalore); Vikram Nelvoy Rajendiran (samsung Research Institute Bangalore); Pradeep
Nelahonne Shivamurthappa (Samsung R & D Institute Banglore)

4074: SMCL: SALIENCY MASKED CONTRASTIVE LEARNING FOR LONG-TAILED VISUAL

RECOGNITION
Sanglee Park (Sogang University, LG Electronics)*; Seung-won Hwang (Seoul National University);
Jungmin So (Sogang University)

4099: INTER-SCALE SURE-LET DENOISE WITH STRUCTURED DEEP IMAGE PRIOR:

INTERPRETABLE SELF-SUPERVISED LEARNING
JIKAI LI (Niigata University)*; Shogo Muramatsu (Niigata Univ.)

4117: GENERAL CATEGORY NETWORK: HANDWRITTEN MATHEMATICAL EXPRESSION

RECOGNITION WITH COARSE-GRAINED RECOGNITION TASK
Xinyu Zhang (Nanjing University); Han Ying (Nanjing University); Ye Tao (Nanjing University); Youlu Xing
(Nanjing University); Guihuan Feng (Nanjing University)*

4120: MCNet:Measurement-Consistent Networks via a Deep Implicit Layer for Solving Inverse
Problems
Rahul Mourya (Heriot-Watt University)*; Joao F.C. Mota (Heriot-Watt University)

4123: Subgradient Descent Learning with Over-the-Air Computation

Tamir L.S. Gez (Ben-Gurion University of the Negev); Kobi Cohen (Ben-Gurion University of the Negev)*

4129: Joint Unmixing and Demosaicing Methods for Snapshot Spectral Images
Kinan ABBAS (Univ. Littoral Cote d’Opale , LISIC); Matthieu PUIGT (Univ. Littoral Côte d'Opale, LISIC)*;
Gilles Delmaire (LISIC); Gilles Roussel (Univ. Littoral Côte d'Opale)

4130: On Cross-Layer Alignment for Model Fusion of Heterogeneous Neural Networks

Dang Nguyen (VinAI)*; Thien Trang Nguyen Vu (Hanoi University of Science and Technology); Khai
Nguyen (University of Texas at Austin); Dinh Q Phung (Monash University); Hung Bui (VinAI Research);
Nhat Ho (University of Texas at Austin)

4142: Neural Source Coding for bandwidth-efficient brain-computer interfacing with wireless
neuro-sensor networks
Thomas Strypsteen (KU Leuven)*; Alexander Bertrand (KU Leuven)

4161: Graph Contrastive Learning with Learnable Graph Augmentation

Xinyan Pu (Southeast University); Ke Zhang (Southeast University); Huazhong Shu (Southeast
University); Jean-Louis Coatrieux (" LTSI, Rennes, France"); Youyong Kong (Southeast University)*

4172: Newton-based Trainable Learning Rate

George Retsinas (National Technical University of Athens)*; Giorgos Sfikas (University of West Attica);
Panagiotis P Filntisis (National Technical University of Athens); Petros Maragos (National Technical
University of Athens)

131
4211: A principled approach to model validation in domain generalization
Boyang Lyu (Tufts University); Thuan Nguyen (Tufts University)*; Matthias Scheutz (Tufts University);
Prakash Ishwar (Boston University); Shuchin Aeron (Tufts University)

4220: Scale-adaptive tiny object detection enhanced by across-scale and shape-preserved

semantic location
Yuting He (Southwest University)*; Renjie Huang (Southwest University); Yangguang Shi (Southwest
University); Guoqiang Xiao (College of Computer and Information Science, Southwest University,
Chongqing, China); Bin Yang (Southwest University); Yuqi Li (Southwest University)

4224: ENLIGHTENING THE STUDENT IN KNOWLEDGE DISTILLATION

Yujie Zheng (Ningbo University); Chong Wang (Ningbo University)*; Yi Chen (Ningbo University); Jiangbo
Qian (Ningbo University); Jun Wang (China University of Mining and Technology); JIAFEI WU
(SenseTime Research)

4225: D-Conformer: Deformable Sparse Transformer Augmented Convolution for Voxel-based 3D

Object Detection
Xiao Zhao (Fudan University)*; Liuzhen Su (Fudan University); Xukun Zhang (Fudan University);
Dingkang Yang (Fudan University); Mingyang Sun (Fudan University); Shunli Wang (Fudan University);
Peng Zhai (Fudan university); Lihua Zhang (Fudan University)

4256: HyperSteg: Hyperbolic Learning for Deep Steganography

Shivam Agarwal (University of Illinois Urbana-Champaign)*; Ritesh Singh Soun (Sri Venkateswara
College); Rahul Shivani (M.B.M. Engineering College, Jodhpur); Vishnuvardhan Varanasi V (IIT Kanpur);
Navroop Gill (Scaler ); Ramit Sawhney (IIIT Delhi)

4276: On Neural Architectures for Deep Learning-based Source Separation of Co-Channel OFDM
Signals
Gary CF Lee (MIT)*; Amir Weiss (Massachusetts Institute of Technology); Alejandro Lancho (MIT); Yury
Polyanskiy (MIT); Gregory W Wornell (MIT)

4293: QUANTILE ONLINE LEARNING FOR SEMICONDUCTOR FAILURE ANALYSIS

bangjian Zhou (A*STAR,I2R,MI); Pan Jieming (Electrical and Computer Engineering, National University
of Singapore); Maheswari Sivan (Electrical and Computer Engineering, National University of Singapore);
Aaron Voon-Yew Thean (Department of Electrical and Computer Engineering, NUS, Singapore);
Senthilnath Jayavelu (Institute for Infocomm Research , A*STAR, Singapore)*

4309: MarginNCE: Robust Sound Localization with a Negative Margin

Sooyoung Park (ETRI); Arda Senocak (KAIST)*; Joon Son Chung (KAIST)

4321: ICEL: Learning with Inconsistent Explanations

Biao Liu (Southern University of Science and Technology)*; xiaoyu wu (Huawei); Bo Yuan (Southern
University of Science and Technology)

4339: Full-band General Audio Synthesis with Score-based Diffusion

Santiago Pascual (Dolby Laboratories)*; Gautam Bhattacharya (Dolby Laboratories); Chunghsin Yeh
(Dolby Laboratories); Jordi Pons (Dolby Laboratories); Joan Serra (Dolby Laboratories)

4346: ZO-DARTS: DIFFERENTIABLE ARCHITECTURE SEARCH WITH ZEROTH-ORDER

APPROXIMATION
Lunchen Xie (Tongji University)*; Kaiyu Huang (Tongji University); Fan Xu (Peng Cheng Laboratory);
Qingjiang Shi (Tongji University)

4350: A Deep Temporal Factor Analysis Method for Large Scale Financial Portfolio Selection
Yao Zhou (Shanghai JiaoTong University)*; Ruidan Su (Shanghai Jiao Tong University); Shikui Tu
(Shanghai Jiao Tong University); Lei Xu (Shanghai Jiao Tong University)

132
4384: Investigating SINDy As a Tool For Causal Discovery In Time Series Signals
Andrew O'Brien (Drexel University )*; Rosina Weber (Drexel University); Edward Kim (Drexel University)

4400: MULTI-RESOLUTION SEQUENCE AGGREGATION AND MODEL AGNOSTIC FRAMEWORK

FOR TIME SERIES FORECASTING
Juhyun Lyu (LG AI Research)*; Jinseok Yang (LG AI Research ); Junghee Kim (LG AI Research);
Woohyung Lim (LG AI Research); Wonbin Ahn (LG AI Research); Dongwan Kang (LG AI Research);
Minjae Kim (LG AI Research); Nam Soo Kim (Seoul National University)

4402: DUAL-GRAPH CO-REPRESENTATION LEARNING FOR KNOWLEDGE-GRAPH ENHANCED

RECOMMENDATION
Xinbiao Liu (Fudan University)*; Bin Liang (Fudan University); JunYu Niu (" Fudan University, China");
Chaofeng Sha (Fudan University); Dong Wu (Fudan University)

4407: Weight-based Mask for Domain Adaptation

EunSeop Lee (POSTECH)*; Inhan Kim (POSTECH); Daijin Kim (Pohang University of Science and
Technology)

4431: LEARNING FROM POSITIVE AND UNLABELED DATA USING OBSERVER-GAN

Omar Zamzam (University of Southern California)*; Haleh Akrami (Signal and Image Processing Institute
at University of Southern California); Richard Leahy (Signal and Image Processing Institute at University
of Southern California)

4442: Multi-Label Temporal Evidential Neural Networks for Early Event Detection
Xujiang Zhao (NEC Lab America)*; Xuchao Zhang (Microsoft); Chen Zhao (Kitware Inc.); Jin-Hee Cho
(Virginia Tech); Lance Kaplan (DEVCOM Army Research Laboratory); DONG HYUN JEONG (University
of the District of Columbia); Audun Jøsang (University of Oslo); Haifeng Chen (NEC Labs); Feng Chen
(UT Dallas)

4443: Is Quality Enough? Integrating Energy Consumption in a Large-Scale Evaluation of Neural

Audio Synthesis Models
Constance Douwes (IRCAM)*; Giovanni Bindi (IRCAM); Antoine CAILLON (IRCAM); Philippe Esling
(IRCAM); Jean-Pierre Briot (CNRS)

4453: TRINET: STABILIZING SELF-SUPERVISED LEARNING FROM COMPLETE OR SLOW

COLLAPSE
Lixin Cao (Tencent); Jun Wang (Tencent)*; ben yang (Peking University); Dan Su (Tencent); Dong Yu
(Tencent AI Lab)

4469: ASYMMETRIC POLYNOMIAL LOSS FOR MULTI-LABEL CLASSIFICATION

Yusheng Huang (Shanghai Jiao Tong University)*; Jiexing Qi (Shanghai Jiao Tong University); Xinbing
Wang (Shanghai Jiao Tong University); Zhouhan Lin (Shanghai Jiao Tong University)

4484: Learning Properties of Holomorphic Neural Networks of Dual Variables

Dmitry Kozlov (Huawei RRI)*; Mikhail V Bakulin (Huawei RRI); Stanislav Pavlov (HSE); Aleksandr Zuev
(Huawei); Maria Krylova (Huawei RRI); Igor Kharchikov (Huawei)

4498: Towards low-power heart rate estimation based on user's demographics and activity level
for wearables
Andre GC Pacheco (Samsung)*; Frank Cabello (Samsung); Paula Rodrigues (Samsung); Paula Pinto
(Samsung); Adriana Fonoff (Samsung); Otávio Penatti (SAMSUNG )

4530: SafeDeep: A Scalable Robustness Verification Framework for Deep Neural Networks
Anahita Baninajjar (Lund University)*; Kamran Hosseini (Linköping University); Ahmed Rezine (Linköping
University); Amir Aminifar (Lund University)

133
4551: Improving the Stochastic Gradient Descent's test accuracy by manipulating the l_\infty
norm of its gradient approximation
Paul Rodriguez (PUCP)*

4563: Hierarchical Graph Learning for Stock Market Prediction via a Domain-Aware Graph Pooling
Operator
Arie N Arya (Imperial College London); Yao Lei Xu (Imperial College London)*; Ljubisa Stankovic
(University of Montenegro); Danilo P. Mandic ((Imperial College of London, UK))

4602: Study of Manifold Geometry using Multiscale Non-Negative Kernel Graphs

Carlos Hurtado (Universitat Politècnica de Catalunya)*; Sarath Shekkizhar (University of Southern
California); Javier Ruiz-Hidalgo (Universitat Politècnica de Catalunya ); Antonio Ortega (University of
Southern California)

4603: Understandable ReLU Neural Network for Signal Classification

Marie Guyomard (Université Côte d'Azur, CNRS, I3S)*; Susana Barbosa (Université Côte d'Azur, CNRS,
IPMC); Lionel Fillatre (Université Côte d'Azur, CNRS, I3S)

4627: CAT: Causal Audio Transformer for Audio Classification

Xiaoyu Liu (University of Maryland, College Park)*; Hanlin Lu (ByteDance Inc.); Jianbo Yuan (Bytedance);
Xinyu Li (Amazon)

4628: WATER LEAK DETECTION AND LOCALIZATION USING CONVOLUTIONAL AUTOENCODERS

Daniele Ugo Leonzio (Politecnico di Milano)*; Paolo Bestagini (Politecnico di Milano); Marco Marcon
(Politecnico di Milano); Gian Paolo Quarta (Onyax); Stefano Tubaro (Politecnico di Milano, Italy)

4631: VPPT: Visual Pre-trained Prompt Tuning Framework for Few-Shot Image Classification
Zhao Song (National Innovation Institute of Defense Technology); Ke YANG (NIIDT)*; Naiyang Guan
(National Innovation Institute of Defense Technology;Tianjin Artificial Intelligence Innovation Center);
Junjie Zhu (NIIDT); Peng Qiao (NUDT); Qingyong Hu (University of Oxford)

4644: Self-attention for Enhanced OAMP Detection in MIMO Systems

Alexander Fuchs (University of Technology Graz); Christian Knoll (Graz, University of Technology); Nima
Najari Moghadam (Huawei Technologies Sweden AB); Alexey Pak (Huawei Technologies Sweden AB);
Jinliang Huang (Huawei Technologies Sweden AB)*; Erik Leitinger (Graz University of Technology); Franz
Pernkopf (Graz University of Technology)

4668: Bayesian Network Modeling and Prediction of Transitions within the Homelessness System
Khandker Sadia Rahman (University at Albany)*; Daphney-Stavroula Zois (University at Albany);
Charalampos Chelmis (University at Albany)

4727: Low-Resource Music Genre Classification with Cross-Modal Neural Model Reprogramming
Yun-Ning Hung (TikTok)*; Chao-Han Huck Yang (Georgia Institute of Technology ); Pin-Yu Chen (IBM
Research); Alexander Lerch (Georgia Institute of Technology)

4729: MAST: Multiscale Audio Spectrogram Transformers

Sreyan Ghosh (University of Maryland, College Park)*; Ashish Seth (IIT Madras); S Umesh (IIT Chennai);
Dinesh Manocha (University of Maryland at College Park)

4736: SLICER: Learning universal audio representations using low-resource self-supervised pre-
training
Ashish Seth (IIT Madras)*; Sreyan Ghosh (University of Maryland, College Park); S Umesh (IIT Chennai);
Dinesh Manocha (University of Maryland at College Park)

134
4742: Data-Driven Graph Convolutional Neural Networks for Power System Contingency Analysis
Valentin Bolz (DIgSILENT GmbH & University of Tuebingen)*; Johannes Ruess (DIgSILENT GmbH);
Andreas Zell (University of Tuebingen)

4762: Improving Self-Supervised Learning for Audio Representations by Feature Diversity and
Decorrelation
Bac Nguyen (Sony Europe B.V.)*; Stefan Uhlich (Sony European Technology Center); Fabien Cardinaux
(Sony European Technology Center)

4763: Asymptotically Optimal Nonparametric Classification Rules for Spike Train Data
Mirosław Pawlak (University of Manitoba); Mateusz Pabian (AGH UST); Dominik Rzepka (AGH
University of Science and Technology)*

4764: FULLY COMPLEX-VALUED DEEP LEARNING MODEL FOR VISUAL PERCEPTION

Aniruddh Sanjoy Sikdar (Indian Institute of Science)*; Sumanth V Udupa (Indian Institute of Science);
Suresh Sundaram (Indian Institute of Science)

4795: InfoShape: Task-Based Neural Data Shaping via Mutual Information

Homa Esfahanizadeh (Massachusetts Institute of Technology)*; William Wu (MIT); Manya Ghobadi
(Massachusetts Institute of Technology (MIT)); Dr.Regina Barzilay (Massachusetts institute of
technology); Muriel Medard (MIT)

4809: Speech Privacy Leakage from Shared Gradients in Distributed Learning

Zhuohang Li (University of Tennessee, Knoxville)*; Jiaxin Zhang (Intuit AI Research); Jian Liu (The
University of Tennessee, Knoxville)

4810: Neural networks with quantization constraints.

Ignacio Hounie (University of Pennsylvania); Juan Elenter (University of Pennsylvania)*; Alejandro Ribeiro
(University of Pennsylvania)

4840: Client Selection for Generalization in Accelerated Federated Learning: A Bandit Approach
Dan Ben Ami (Ben-Gurion University of the Negev)*; Kobi Cohen (Ben-Gurion University of the Negev);
Qing Zhao (Cornell University)

4843: Robust Monocular Localization of Drones by Adapting Domain Maps to Depth Prediction
Inaccuracies
Priyesh Shukla (University of Illinois Chicago)*; Sureshkumar Senthilkumar (University of Illinois at
Chicago); Alex C Stutts (University of Illinois Chicago); Sathya Ravi (University of Illinois at Chicago);
Theja Tulabandhula (UIC); Amit R Trivedi (University of Illinois at Chicago)

4871: Anomalous signal detection for cyber-physical systems using interpretable causal neural
network
Shuo Zhang (East China Normal University)*; Jing Liu (East China Normal University)

4904: Continuous descriptor-based control for deep audio synthesis

Ninon Devis (IRCAM)*; Nils Demerlé (IRCAM); Sarah Nabi (IRCAM); David Genova (IRCAM); Philippe
Esling (IRCAM)

4911: Improved Projection Learning for Lower Dimensional Feature Maps

Ilan Price (University of Oxford)*; Jared Tanner (Oxford University)

4914: Counterfactual explanation for multivariate times series using a contrastive variational
autoencoder
William Todo (Liebherr aerospace )*; Merwann Selmani (Liebherr Aerospace Toulouse); Béatrice Laurent
(Institut de Mathématiques de Toulouse (UMR 5219), Université de Toulouse, INSA de Toulouse); Jean-
Michel Loubes (Université Toulouse Paul Sabatier Institut de Mathématiques de Toulouse)

135
4915: GAITMIXER: SKELETON-BASED GAIT REPRESENTATION LEARNING VIA WIDE-SPECTRUM
MULTI-AXIAL MIXER
Ekkasit Pinyoanuntapong (University of North Carolina at Charlotte)*; Ayman Ali (UNCC); Pu Wang
(UNCC); Minwoo Lee (University of North Carolina at Charlotte); Chen Chen (University of Central
Florida)

4956: MATRIX LOW-RANK APPROXIMATION FOR POLICY GRADIENT METHODS

Sergio Rozada (King Juan Carlos University)*; Antonio G. Marques (King Juan Carlos University)

4977: Single-Shot Domain Adaptation via Target-Aware Generative Augmentations

Rakshith Subramanyam (Arizona State University)*; Kowshik Thopalli (Arizona State University); Spring
Berman (Arizona State University, USA); Pavan Turaga (Arizona State University); Jayaraman J.
Thiagarajan (Lawrence Livermore National Laboratory)

4997: Fully Distributed Federated Learning with Efficient Local Cooperations

Evangelos Georgatos (Computer Engineering and Infomatics Dept., University of Patras)*; Christos
Mavrokefalidis (Computer Engineering and Informatics Dept., University of Patras, Greece); Kostas
Berberidis (University of Patras)

5012: ANALYSING THE MASKED PREDICTIVE CODING TRAINING CRITERION FOR PRE-
TRAINING A SPEECH REPRESENTATION MODEL
Hemant Yadav (MIDAS)*; Sunayana Sitaram (Microsoft Research); Rajiv Ratn Shah (IIIT Delhi)

5019: Jamming Source Localization Using Augmented Physics-based Model

Andrea Nardin (Politecnico di Torino)*; Tales Imbiriba (Northeastern University); Pau Closas
(Northeastern University)

5021: Audio-visual speaker diarization in the framework of multi-user human-robot interaction

Timothée Dhaussy (Université Avignon)*; Bassam Jabaian (LIA - Avignon university); Fabrice Lefevre
(Univ. Avignon); Radu Horaud (Inria)

5031: Towards Dialogue Modeling Beyond Text

Tongzi Wu (University of Toronto)*; Yuhao Zhou (Talka AI); Wang Ling (Talka Ai); Hojin Yang (talka ai);
Joana Veloso (Talka AI); Lin Sun (Talka AI); Ruixin Huang (Talka AI); Norberto Guimaraes (Talka AI);
Scott Sanner (University of Toronto)

5034: Variable Rate Allocation for Vector-Quantized Autoencoders

Federico Baldassarre (KTH - Royal Institute of Technology)*; Alaaeldin M El-Nouby (Facebook AI
Research); Herve Jegou (Facebook AI Research)

5036: Identifiable Bounded Component Analysis via Minimum Volume Enclosing Parallelotope
Jingzhou Hu (University of Florida); Kejun Huang (University of Florida)*

5042: DEEP LEARNING FOR LAGRANGIAN DRIFT SIMULATION AT THE SEA SURFACE
Daria Botvynko (ENIB)*; Carlos Granero-Belinchon (IMT Atlantique); Simon van Gennip (Mercator Ocean
International); Abdesslam BENZINOU (ENIB); ronan fablet (IMT Atlantique)

5045: Volume-regularized Nonnegative Tucker Decomposition with Identifiability Guarantees

Yuchen Sun (University of Florida); Kejun Huang (University of Florida)*

5055: HeartToHeart: The Arts of Infant Versus Adult-Directed Speech Classification

Najla D Al Futaisi (Imperial College London)*; Alejandrina Cristia (PSL Research University); Bjoern W.
Schuller (Imperial College London)

136
5062: SMUG: Towards robust MRI reconstruction by smoothed unrolling
Hui Li (Huazhong University of Science and Technology); jinghan jia (Michigan state university)*; Shijun
Liang (michigan state university); Yuguang Yao (Michigan State University); Saiprasad Ravishankar
(Michigan State University); Sijia Liu (Michigan State University)

5063: RepackagingAugment: Overcoming Prediction Error Amplification in Weight-averaged

Speech Recognition Models Subject to Self-training
Jae-Hong Lee (Hanyang University)*; Dong-Hyun Kim (Hanyang University); Joon-Hyuk Chang (Hanyang
University)

5068: EVALUATION OF CATEGORICAL GENERATIVE MODELS - BRIDGING THE GAP BETWEEN

REAL AND SYNTHETIC DATA
Florence Regol (McGill University)*; Anja M Kroon (McGill University); Mark Coates (McGill University)

5072: Towards a Robust and Efficient Classifier for Real World Radio Signal Modulation
Classification
Dancheng Liu (University of California, San Diego)*; Kazim Ergun (University of California San Diego);
Tajana S Rosing (University of California, San Diego)

5081: Online Model Compression for Federated Learning with Large Models
Tien-Ju Yang (Google)*; Yonghui Xiao (Google); Giovanni Motta (Google, Inc.); Françoise Beaufays
(Google); Rajiv Mathews (Google); Mingqing Chen (Google Inc.)

5101: Robustness-preserving Lifelong Learning via Dataset Condensation

jinghan jia (Michigan state university)*; Yihua Zhang (Michgan State University); Dogyoon Song
(University of Michigan); Sijia Liu (Michigan State University); Alfred Hero (University of Michigan)

5108: A Content Adaptive Learnable “Time-Frequency” Representation For Audio Signal

Processing
Prateek Verma (Stanford University)*; Chris Chafe (organization)

5109: gSwin: Gated MLP Vision Model with Hierarchical Structure of Shifted Window
Mocho Go (PKSHA Technology Inc.)*; Hideyuki Tachibana (PKSHA Technology)

5118: Efficient personalized federated learning on selective model training

Yeting Guo (College of Computer, National University of Defense Technology)*; Liu Fang (Hunan
University); Tongqing Zhou (National University of Defense Technology); Zhiping Cai (NUDT); Nong Xiao
(N)

5141: DICTIONARY LEARNING ON GRAPH DATA WITH WEISFIELER-LEHMAN SUB-TREE KERNEL

AND KSVD
Kaveen G Liyanage (Montana State University)*; Reese Pearsall (Montana State University); Clemente
Izurieta (Montana State University); Bradley M Whitaker (Montana State University)

5143: NETWORKED POLICY GRADIENT PLAY IN MARKOV POTENTIAL GAMES

Sarper Aydin (Texas A&M University); Ceyhun A Eksin (Texas A&M University)*

5159: GraphMAD: Graph Mixup for Data Augmentation using Data-Driven Convex Clustering
Madeline Navarro (Rice University)*; Santiago Segarra (Rice University)

5168: M22: RATE-DISTORTION INSPIRED GRADIENT COMPRESSION

Yangyi Liu (McMaster University)*; Sadaf Dr Salehkalaibar (McMaster university); stefano rini (nycu); Jun
Chen (McMaster University)

137
5201: Training Graph Neural Networks on Growing Stochastic Graphs
Juan Cervino (University of Pennsylvania)*; Luana Ruiz (University of Pennsylvania); Alejandro Ribeiro
(University of Pennsylvania)

5222: RECURSIVE ESTIMATION OF USER INTENT FROM NONINVASIVE

ELECTROENCEPHALOGRAPHY USING DISCRIMINATIVE MODELS
Niklas Smedemark-Margulies (Northeastern University)*; Basak Celik (Northeastern University); Tales
Imbiriba (Northeastern University); Aziz Kocanaogullari (Northeastern University); Deniz Erdogmus
(Northeastern University)

5237: Modeling the Wave Equation Using Physics-Informed Neural Networks Enhanced with
Attention to Loss Weights
Shaikhah Alkhadhr (Pennsylvania State University)*; Mohamed Almekkawy (Pennsylvania State
University)

5246: DIRECTION AWARE POSITIONAL AND STRUCTURAL ENCODING FOR DIRECTED GRAPH
NEURAL NETWORKS
Yonas A Sium (Iowa State University)*; Georgios Kollias (IBM Research); Tsuyoshi Ide (IBM Research, T.
J. Watson Research Center); Payel Das (IBM Research); Naoki Abe (IBM Research); Aurelie Lozano
(IBM Research); Qi Li (Iowa State University)

5265: Clip4VideoCap: Rethinking CLIP for Video Captioning with Multiscale Temporal Fusion and
Commonsense Knowledge
Tanvir Mahmud (The University of Texas ar Austin)*; Feng Liang (The University of Texas at Austin);
Yaling Qing (University of Texas at Austin); Diana Marculescu (The University of Texas at Austin)

5273: Music Mixing Style Transfer: A Contrastive Learning Approach to Disentangle Audio Effects
Junghyun Koo (Seoul National University)*; Marco A Martinez Ramirez (Sony Group Corporation);
WeiHsiang Liao (Sony Group Corporation); Stefan Uhlich (Sony European Technology Center); Kyogu
Lee (Seoul National University); Yuki Mitsufuji (Sony Group Corporation)

5277: Global and Nodal Mutual Information Maximization in Heterogeneous Graphs

Costas Mavromatis (University of Minnesota)*; George Karypis (University of Minnesota, Twin Cities)

5288: SEMI-SUPERVISED GRAPH ULTRA-SPARSIFIERS USING REWEIGHTED L1 OPTIMIZATION

Jiayu Li (Syracuse University)*; Tianyun Zhang (Cleveland State University); Shengmin Jin (Syracuse
University); Reza Zafarani (Syracuse University)

5294: ERSAM: Neural Architecture Search For Energy-Efficient and Real-Time Social Ambiance
Measurement
Chaojian Li (Georgia Institute of Technology)*; Wenwan Chen (Rice University); Jiayi Yuan (Rice
University); Yingyan (Celine) Lin (Georgia Tech); Ashutosh Sabharwal (Rice University)

5310: Graph Representation Learning for Stroke Recurrence Prediction

Nicholas Glaze (Rice University)*; Artun Bayer (Rice University); Xiaoqian Jiang (The University of Texas
Health Science Center at Houston); Sean Savitz (University of Texas Health Science Center at Houston);
Santiago Segarra (Rice University)

5321: Space-Time Graph Neural Networks with Stochastic Graph Perturbations

Samar Hadou (University of Pennsylvania)*; Charilaos Kanatsoulis (University of Pennsylvania);
Alejandro Ribeiro (University of Pennsylvania)

5323: Interpretation of Neural Networks is Susceptible to Universal Adversarial Perturbations

Haniyeh Ehsani Oskouie (Sharif University of Technology); Farzan Farnia (The Chinese University of
Hong Kong)*

138
5327: Fast and Exact Enumeration of Deep Networks Partitions Regions
Randall Balestriero (Facebook AI Research)*; yann lecun (Facebook)

5329: CNEG-VC: Contrastive Learning using Hard Negative Example in Non-parallel Voice
Conversion
Bima Prihasto (National Central University); YiXing Lin (National Central University); Le Phuong (National
Central University); CHIEN-LIN HUANG (NCKU); Jia-Ching Wang (National Central University)*

5346: Algebraic Convolutional Filters on Lie Group Algebras

Harshat Kumar (University of Pennsylvania)*; Alejandro Parada-Mayorga (University of Pennsylvania);
Alejandro Ribeiro (University of Pennsylvania)

5348: GENERALIZED INVARIANT MATCHING PROPERTY VIA LASSO

Kang Du (University of Utah)*; Yu Xiang (University of Utah)

5349: Exploring Approaches to Multi-Task Automatic Synthesizer Programming

Daniel A Faronbi (New York University)*; Iran R Roman (NYU); Juan P Bello (New York University)

5372: Towards Scale Adaptive Underwater Detection through Refined Pyramid Grid
Xiaoheng Deng (Central South University)*; Lirong Liao (Xinjiang Univiersity); Ping Jiang (Central South
University); Yurong Qian (Xinjiang Univiersity)

5397: Spammer Detection on Short Video Applications: A New Challenge and Baselines
Muyang Yi (Shanghai Jiao Tong University)*; Dong Liang (ByteDance); Rui Wang (Bytedance AI Lab);
Yue Ding (Shanghai Jiao Tong University); Hongtao Lu (Shanghai Jiao Tong University)

5426: MedleyVox: An Evaluation Dataset for Multiple Singing Voices Separation

Chang-Bin Jeon (Seoul National University)*; Hyeongi Moon (Gaudio Lab.); Keunwoo Choi (Gaudio Lab);
Ben Sangbae Chon (Gaudio Lab); Kyogu Lee (Seoul National University)

5437: POSITION-AWARE GRAPH-BASED LEARNING OF WHOLE SLIDE IMAGES

Milan Aryal (Marquette University); Nasim Yahyasoltani (Marquette university)*

5459: A Closer Look at Scoring Functions and Generalization Prediction

Puja Trivedi (University of Michigan)*; Danai Koutra (U Michigan); Jayaraman J. Thiagarajan (Lawrence
Livermore National Laboratory)

5461: Accelerated Distributed Stochastic Non-Convex Optimization over Time-Varying Directed

Networks
Yiyue Chen (University of Texas at Austin)*; Abolfazl Hashemi (Purdue University); Haris Vikalo
(University of Texas at Austin)

5467: Sub-Band Contrastive Learning-Based Knowledge Distillation For Sound Classification

Achyut Mani Tripathi (Indian Institute of Technology Guwahati, Assam)*; Aakansha Mishra (IIT
Guwahati)

5487: A Gaussian Latent Variable Model for Incomplete Mixed Type Data
Marzieh Ajirak (Stony Brook University)*; Petar Djuric ()

5490: A METHOD OF CONSTRUCTING AND AUTOMATICALLY LABELING RADIO FREQUENCY

SIGNAL TRAINING DATASET FOR UAV
Chao Liu (Fudan University)*; Ruipeng Ma (ZhengZhou University); Zheng Si (ZhengZhou University);
mingmin Chi (Fudan university)

139
5498: ONLINE CACHING WITH FETCHING COST FOR ARBITRARY DEMAND PATTERN: A DRIFT-
PLUS-PENALTY APPROACH
Shashank P (IIT Dharwad); Bharath Bettagere (IIT Dharwad)*

5510: AutoGCF: Personalized Aggregation on Neural Graph Collaborative Filtering

Xiaoyu You (Fudan University)*; Chi Li (Fudan University); Jianwei Xu (Fudan University); Mi Zhang
(Fudan University)

5514: Dual Collaborative Visual-Semantic Mapping for Multi-Label Zero-Shot Image Recognition
Yunqing Hu (Zhejiang University); Xuan Jin (Alibaba Turing Lab, Alibaba Group); Xi Chen (Zhejiang
University ); Yin Zhang (Zhejiang University)*

5518: Communication-Constrained Exchange of Zeroth-Order Information with Application to

Collaborative Target Tracking
Ege Can Kaya (Purdue University); Mehmet Berk Şahin (Purdue University ); Abolfazl Hashemi (Purdue
University)*

5542: CODED MATRIX COMPUTATIONS FOR D2D-ENABLED LINEARIZED FEDERATED LEARNING

Anindya Bijoy Das (Purdue University )*; Aditya RAMAMOORTHY (Iowa State University); David Love
(Purdue University); Christopher Brinton (Purdue University)

5544: Meta-Learning for Image-Guided Millimeter-Wave Beam Selection in Unseen Environments

Jerry Gu (Northeastern University)*; Liam Collins (University of Texas at Austin); Debashri Roy
(Northeastern University); Aryan Mokhtari (UT Austin); Sanjay Shakkottai (University of Texas at Austin);
Kaushik Chowdhury (Northeastern University)

5551: Dual-Stage Graph Convolution Network With Graph Learning For Traffic Prediction
Li Zilong (Heilongjiang University); Qianqian Ren (Heilongjiang University)*; Long Chen (Heilongjiang
University); jianguo sun (xidian university)

5578: A Contrastive Knowledge Transfer Framework for Model Compression and Transfer
Learning
kaiqi zhao (Arizona State Univesity)*; Yitao Chen (Arizona State University); Ming Zhao (Arizona State
University)

5587: BALANCED DEEP CCA FOR BIRD VOCALIZATION DETECTION

SUMIT KUMAR (IIT Kanpur)*; B Anshuman (IIT Kanpur); Linus Ruettimann (University of Zurich and ETH
Zurich); Richard Hahnloser (University of Zurich and ETH Zurich); Vipul Arora (IIT Kanpur)

5601: Learning Speech Representations with Flexible Hidden Feature Dimensions

Huaizhen Tang (University of Science and Technology of China); Xulong Zhang (Ping An Technology
(Shenzhen) Co., Ltd.); Jianzong Wang (Ping An Technology (Shenzhen) Co., Ltd)*; Ning Cheng (Ping An
Technology (Shenzhen) Co., Ltd); Jing Xiao (Ping An Insurance (Group) Company of China)

5620: A Probabilistic Framework for Pruning Transformers via a Finite Admixture of Keys
Tan Minh Nguyen (University of California, Los Angeles)*; Tam Minh Nguyen (FPT Software); Long Minh
Bui (FPT Software); Hai Do (FPT Software); Duy Khuong Nguyen (FPT Software Ltd. - FPT Corporation);
Dung D. D. Le (College of Engineering and Computer Science, VinUniversity); Hung Tran-The (Deakin
University); Nhat Ho (University of Texas at Austin); Stanley Osher (UCLA); Richard Baraniuk (Rice
University)

5666: Forensics for Adversarial Machine Learning through Attack Mapping Identification
Allen H Yan (Oregon State University)*; Jinsub Kim ("); Raviv Raich (Oregon State University)

140
5679: Multi-task Bias-Variance Trade-off Through Functional Constraints
Juan Cervino (University of Pennsylvania)*; Juan Andres Bazerque (Univerity of Pittsburgh); Miguel
Calvo-Fullana (Universitat Pompeu Fabra); Alejandro Ribeiro (University of Pennsylvania)

5682: M-CTRL: A CONTINUAL REPRESENTATION LEARNING FRAMEWORK WITH SLOWLY

IMPROVING PAST PRE-TRAINED MODEL
Jin-Seong Choi (Hanyang university)*; Jae-Hong Lee (Hanyang University); Chae-Won Lee (Hanyang
University,Seoul); Joon-Hyuk Chang (Hanyang University)

5703: A hybrid deep neural network for nonlinear causality analysis in complex industrial control
system
Tian Feng (Zhejiang University)*; Qiming Chen (DAMOAcademy,AlibabaGroup); Yao Shi (Zhejiang
University); Xun Lang (Yunnan University); Lei Xie (Zhejiang University); Hongye Su (Zhejiang
University)

5761: RETHINKING RANDOM WALK IN GRAPH REPRESENTATION LEARNING

DingYi Zeng (University of Electronic Science and Technology of China)*; Wenyu Chen (University of
Electronic Science and Technology of China); Wanlong Liu (University of Electronic Science and
Technology of China); Li Zhou (University of Electronic Science and Technology of China); Hong Qu
(University of Electronic Science and Technology of China)

5786: Rigid-Body Sound Synthesis with Differentiable Modal Resonators

Rodrigo Diaz (Queen Mary University of London)*; Ben Hayes (Queen Mary University of London);
Charalampos Saitis (Queen Mary University of London); Gyorgy Fazekas (Queen Mary University of
London); Mark Sandler (Queen Mary University of London)

5791: Large-Scale Nonverbal Vocalization Detection Using Transformers

Panagiotis Tzirakis (Hume AI)*; Alice Baird (Hume AI); Jeff Brooks (Hume AI); Chris Gagne (Hume.ai);
Lauren Kim (Hume AI); Michael Opara (Hume AI); Christopher Gregory (Hume AI); Jacob Metrick (Hume
AI); Garrett Boseck (Hume AI); Vineet Tiruvadi (Hume AI); Bjoern W. Schuller (Imperial College London);
Dacher Keltner (UC Berkeley); Alan S Cowen (Hume AI)

5825: DIFFICULTY-AWARE DATA AUGMENTOR FOR SCENE TEXT RECOGNITION

Guanghao Meng (Tsinghua University)*; Tao Dai (Shenzhen University); Bin Chen (Harbin Institute of
Technology, Shenzhen); Naiqi Li (Tsinghua-Berkeley Shenzhen Institute); Yong Jiang (Tsinghua
University); Shu-Tao Xia (Tsinghua University)

5828: Sinusoidal Frequency Estimation by Gradient Descent

Ben Hayes (Queen Mary University of London)*; Charalampos Saitis (Queen Mary University of London);
Gyorgy Fazekas (Queen Mary University of London)

5829: Multi-view K-means with Laplacian Embedding

zhezheng hao (Northwestern Polytechnical University)*; Zhoumin Lu (Northwestern Polytechnical
University); Feiping Nie (Northwestern Polytechnical University); Rong Wang (Northwestern Polytechnical
University); Xuelong Li (Northwestern Polytechnical University)

5846: Learning on Graphs under Label Noise

Jingyang Yuan (Peking University)*; Xiao Luo (UCLA); Yifang Qin (Peking University); Yusheng Zhao
(Peking University); Wei Ju (Peking University); Ming Zhang (Peking University)

5854: Learning Unbiased Rewards with Mutual Information in Adversarial Imitation Learning
LiHua Zhang (School of Computer Science and Technology, Soochow University)*; Quan Liu (School of
Computer Science and Technology, Soochow University); Zhigang Huang (School of Computer Science
and Technology, Soochow University, Suzhou, China); Lan Wu (School of Computer Science and
Technology, Soochow University)

141
5885: Differential Analysis for Networks Obeying Conservation Laws
Anirudh Rayas (Arizona State University)*; Rajasekhar Anguluri (Arizona State University); Jiajun Cheng
(Arizona State University); Gautam Dasarathy (Arizona State University)

5891: Training Robust Spiking Neural Networks with ViewPoint Transform and SpatioTemporal
Stretching
Haibo Shen (Huazhong University of Science and Technology)*; Juyu Xiao (Huazhong University of
Science and Technology); Yihao Luo (Yichang Testing Technique R&D Institute); Xiang Cao (School of
Computer Science and Technology, Huazhong University of Science and Technology); Liangqi Zhang
(Huazhong University of Science and Technology); Tianjiang Wang (School of Computer Science and
Technology, Huazhong University of Science and Technology)

5910: HINDI AS A SECOND LANGUAGE: IMPROVING VISUALLY GROUNDED SPEECH WITH

SEMANTICALLY SIMILAR SAMPLES
Hyeonggon Ryu (KAIST); Arda Senocak (KAIST)*; In So Kweon (KAIST); Joon Son Chung (KAIST)

5940: Large dimensional analysis of LS-SVM transfer learning: Application to POLSAR

classification
Cyprien DOZ (Sondra - Centrale Supelec (University Paris Saclay))*; Chengfang Ren (Sondra -
CentraleSupelec); Jean-Philippe Ovarlez (ONERA, CentraleSupélec, SONDRA, Université Paris-Saclay
); Romain COUILLET (CentraleSupélec, GIPSA-lab @ Université Grenoble-Alpes)

5959: Towards a More Stable and General Subgraph Information Bottleneck

Hongzhi Liu (Xi'an Jiaotong University); Kaizhong Zheng (Xi'an Jiaotong University); Shujian Yu (Vrije
Universiteit Amsterdam)*; Badong Chen ("Xi'an Jiaotong University, China")

5963: LE-DTA: Local Extrema convolution for Drug Target Affinity Prediction
Tanoj Langore (National Taiwan University); Te-Cheng Hsu (National Tsing Hua University); Yi Hsien
Hsieh (National Taiwan University); Che Lin (National Taiwan University)*

6016: A Game of Snakes and GANs

Siddarth Asokan (Indian Institute of Science)*; Fatwir Sheikh Mohammed (University of Washington);
Chandra Sekhar Seelamantula (IISc Bangalore)

6021: Deep architecture for doa trajectory localization.

Shreyas Jaiswal (SPCRC, IIIT Hyderabad)*; Ruchi Pandey (IIIT Hyderabad); Santosh Nannuru (IIIT
Hyderabad)

6041: On the Fairness of Multitask Representation Learning

Yingcong Li (University of California, Riverside)*; Samet Oymak (University of California, Riverside)

6053: Diffusion Probabilistic Modeling for Fine-Grained Urban Traffic Flow Inference With Relaxed
Structural Constraint
Xovee Xu (University of Electronic Science and Technology of China)*; Yutao Wei (University of
Electronic Science and Technology of China); Pengyu Wang (School of Information and Software
Engineering, University of Electronic Science and Technology of China); Xucheng Luo (University of
Electronic Science and Technology of China); Fan Zhou (School of Information and Software
Engineering, University of Electronic Science and Technology of China); Goce Trajcevski (Iowa State
University)

6088: Deep plug-and-play for tensor robust principal component analysis

Hao Tan (Southwest University)*; Jianjun Wang (Southwest University); Weichao Kong (Southwest
University)

142
6100: Multi-aspect Interest Neighbor-augmented Network for Next-basket Recommendation
Zhiying Deng (Huazhong University of Science and Technology); Jianjun Li (School of Computer Science
and Technology, Huazhong University of Science and Technology)*; Zhiqiang Guo (School of Computer
Science and Technology, Huazhong University of Science and Technology ); Guohui Li (School of
Computer Science and Technology Huazhong University of Science and Technology)

6125: Geometric Matrix Completion with Collaborative Routing between Capsules

Xuan Li (School of Software Tsinghua University); Li Zhang (School of Software Tsinghua University)*

6138: Inv-SENet: Invariant Self Expression Network for clustering under biased data
Ashutosh Singh (Northeastern University)*; Ashish Singh (University of Massachusetts Amherst); Aria
Masoomi (Northeastern University); Tales Imbiriba (Northeastern University); Erik Learned-Miller
(University of Massachusetts, Amherst); Deniz Erdogmus (Northeastern University)

6144: Sequential Invariant Information Bottleneck

Yichen Zhang (Xi'an Jiaotong University, China); Shujian Yu (Vrije Universiteit Amsterdam)*; Badong
Chen ("Xi'an Jiaotong University, China")

6178: Relevance Propagation through Deep Conditional Random Fields

Xiangyu Yang (Vrije Universiteit Brussel); Boris Joukovsky (Vrije Universiteit Brussel - imec)*; Nikos
Deligiannis (Vrije Universiteit Brussel - imec)

6181: BOOSTING TRANSFERABILITY OF ADVERSARIAL EXAMPLE VIA AN ENHANCED EULER'S

METHOD
Anjie Peng (Southwest University of Science and Technology); Zhi Lin (Southwest University of Science
and Technology); Hui Zeng (Southwest University of Science and Technology)*; Wenxin Yu (Southwest
University of Science and Technology); Xiangui Kang (Sun Yat-Sen University)

6204: Boosting Semi-Supervised Federated Learning with Model Personalization and Client-
Variance-Reduction
Shuai Wang (Singapore University of Technology and Design)*; Yanqing Xu (The Chinese University of
HongKong, Shenzhen); Yanli Yuan (Singapore University of Technology and Design); Xiuhua Wang
(Huazhong University of Science and Technology); Tony Quek (Singapore University of Technology and
Design)

6214: RUNTIME PREDICTION OF MACHINE LEARNING ALGORITHMS IN AUTOML SYSTEMS

Parijat Dube (IBM Research)*; Theodoros Salonidis (IBM T.J. Watson Research Center); Parikshit Ram
(IBM Research); Ashish Verma (Amazon)

6242: High-level Feature Fusion Network for Session-based Social Recommendation

Liuyin Wang (Tsinghua University)*; Mingchao Li (Tsinghua University); Hai-Tao Zheng (Tsinghua
University)

6262: Rethinking Rule-based Approaches in Session-based Recommendation

Liuyin Wang (Tsinghua University)*; Mingchao Li (Tsinghua University); Hai-Tao Zheng (Tsinghua
University)

6278: DPP-based Client Selection for Federated Learning with Non-IID Data
Yuxuan Zhang (Northwest A&F University)*; chao xu (Northwest A&F University); Howard H. Yang (ZJU-
UIUC Institute); Xijun Wang (Sun Yat-sen University); Tony Quek (Singapore University of Technology
and Design)

6297: The Uniqueness Problem of Physical Law Learning

Philipp Scholl (Ludwig Maximilian University of Munich)*; Aras Bacho (Ludwig Maximilian University of
Munich); Holger Boche (Technische Universität München); Gitta Kutyniok (Ludwig Maximilian University
of Munich)

143
6300: SyncNet: correlating objective for time delay estimation in audio signals
Akshay Raina (Indian Institute of Technology Kanpur); Vipul Arora (IIT Kanpur)*

6356: Learning silhouettes with group sparse autoencoders

Emmanouil Theodosis (Harvard University)*; Demba Ba (Harvard)

6375: Data leakage in cross-modal retrieval training: A case study

Benno Weck (Music Technology Group, Universitat Pompeu Fabra (UPF))*; Xavier Serra (Universitat
Pompeu Fabra )

6385: Joint Cryo-ET Alignment and Reconstruction with Neural Deformation Fields
Valentin Debarnot (University of Basel)*; Sidharth Gupta (University of Illinois at Urbana-Champaign);
Konik Kothari (University of Illinois at Urbana-Champaign); Ivan Dokmanic (University of Basel)

6417: Asymptotic Distribution of Stochastic Mirror Descent Iterates in Average Ensemble Models
Taylan Kargin (California Institute of Technology)*; Fariborz Salehi (California Institute of Technology);
Babak Hassibi (Caltech)

6423: SpectraNet-SO(3): Learning Satellite Orientation from Optical Spectra by Implicitly Modeling
Mutually Exclusive Probability Distributions on the Rotation Manifold
Matthew Phelps (Odyssey Systems)*; Ryan Swindle (Odyssey Systems); Zack Gazak (Odyssey
Systems); Andrew Vandenberg (AFRL); Justin Fletcher (Odyssey Systems)

6430: FedSD: A New Federated Learning Structure Used in Non-iid Data

Minmin Yi (Tsinghua University)*; Houchun Ning (Tsinghua University); Peng Liu (PingAn Tech/Hong
Kong Polytechnic University)

6453: Learning Gradients of Convex Functions with Monotone Gradient Networks

Shreyas Chaudhari (Carnegie Mellon University); Srinivasa Pranav (Carnegie Mellon University)*; José
M. F. Moura (Carnegie Mellon University)

6527: On weighted cross-entropy for label-imbalanced separable data: An algorithmic-stability

study
Puneesh Deora (University of British Columbia); Christos Thrampoulidis (University of British Columbia)*

144
 Multimedia Signal Processing

265: Surface-Sampling based Objective Quality Assessment Metrics for Meshes

Chunyang Fu (SECE, Shenzhen Graduate School, Peking University); Xiang Zhang (Tencent America);
Thuong Nguyen Canh (Tencent America); Xiaozhong Xu (Tencent America); Ge Li (SECE, Shenzhen
Graduate School, Peking University)*; Shan Liu (Tencent America)

332: TOWARDS EXPLAINABLE RECOMMENDATION VIA BERT-GUIDED EXPLANATION

GENERATOR
Huijing Zhan (I2R, Astar)*; LING LI (Nanyang Technological University); Shaohua Li (IHPC, A*STAR);
Weide Liu (Institute for Infocomm Research); Manas Gupta (Institute for Infocomm Research (I2R),
Agency for Science, Technology and Research (A*STAR), Singapore); Alex Kot (Nanyang Technological
University)

345: Perceptual Quality Assessment for Digital Human Heads

Zicheng Zhang (Shanghai Jiaotong university)*; Yingjie Zhou (Shanghai Jiao Tong University); Wei Sun
(Shanghai Jiao Tong Unviersity); Xiongkuo Min (Shanghai Jiao Tong University); Yuzhe Wu (DongHua
University); Guangtao Zhai (Shanghai Jiao Tong University)

481: VarietySound: Timbre-Controllable Video to Sound Generation via Unsupervised Information

Disentanglement
Chenye Cui (Zhejiang University)*; Zhou Zhao (Zhejiang University); Yi Ren (Bytedance); Jinglin Liu
(Zhejiang University); Rongjie Huang (Zhejiang University); chen feiyang (huawei); Zhefeng Wang
(Huawei Cloud); Baoxing Huai (Huawei Cloud); Fei Wu (Zhejiang University, China)

493: A Point Is A Wave: Point-wave Network for Place Recognition

Ge Li (SECE, Shenzhen Graduate School, Peking University); Ruonan Zhang (Peking University,
shenzhen graduate school)*

726: C2BN: Cross-modality and Cross-scale Balance Network for multi-modal 3D Object Detection
BoNan Ding (Chingqing University); Jin Xie (Chongqing University)*; Jing Nie (Chongqing University)

768: FedVMR: A New Federated Learning method for Video Moment Retrieval
Yan Wang (Shandong University); Xin Luo (Shandong University)*; Zhen-Duo Chen (Shandong
University); Peng-Fei Zhang (University of Queensland); Meng Liu (Shandong Jianzhu University); Xin-
Shun Xu (Shandong University)

793: Step Restriction for Improving Adversarial Attacks

Keita Goto (Tokyo Institute of Technology); Shinta Otake (Tokyo Institute of Technology); Rei Kawakami
(Tokyo Institute of Technology); Nakamasa Inoue (Tokyo Institute of Technology)*

822: AUDIO-DRIVEN HIGH DEFINETION AND LIP-SYNCHRONIZED TALKING FACE GENERATION

BASED ON FACE REENACTMENT
Xianyu Wang (Huawei Technologies Co., Ltd.)*; Yuhan Zhang (Peking University); Weihua He (Tsinghua
University); Yaoyuan Wang (Huawei Technologies Co., Ltd.); Minglei Li (Huawei Technologies Co., Ltd.);
Yuchen Wang (Huawei Technologies Co., Ltd.); Jingyi Zhang (Huawei Technologies Co., Ltd.); Shunbo
Zhou (Huawei Cloud); Ziyang Zhang (HUAWEI TECHNOLOGIES CO.LTD)

919: LEARNING TO LOCATE VISUAL ANSWER IN VIDEO CORPUS USING QUESTION

Bin Li (Hunan University)*; Yixuan Weng (CASIA); Bin Sun (Hunan University); Shutao Li (Hunan
University)

954: Boosting Fine-grained Sketch-based Image Retrieval with Self-supervised Learning

Zhaolong Zhang (Fudan University); Yangdong Chen (Fudan University)*; Yuejie Zhang (Fudan
University); Rui Feng (Fudan University); Tao Zhang (Shanghai University of Finance and Economics)

145
976: Multi-source Templates Learning for Real-time Aerial Tracking
Yiming Sun (East China Normal University); Yang Li (East China Normal University)*; Changbo Wang
(East China Normal University)

1030: IMPROVING DROPOUT IN GRAPH CONVOLUTIONAL NETWORKS FOR RECOMMENDATION

VIA CONTRASTIVE LOSS
Hiroki Okamura (Hokkaido University)*; Keisuke Maeda (Hokkaido University); Ren Togo (Hokkaido
University); Takahiro Ogawa (Hokkaido University); Miki Haseyama (Hokkaido University)

1051: NF-PCAC: Normalizing Flow based Point Cloud Attribute Compression

Rodrigo Borba Pinheiro (InterDigital)*; Jean-Eudes Marvie (InterDigital); Giuseppe Valenzise (CNRS);
Frederic Dufaux (CNRS)

1106: Adaptive Mask Co-optimization for Modal Dependence in Multimodal Learning

Ying Zhou (Xidian University); Xuefeng Liang (Xidian University)*; ShiQuan Zheng (Xidian University);
Huijun Xuan (Xidian University); Takatsune Kumada (Kyoto University)

1185: Lip-to-speech Synthesis in the Wild with Multi-task Learning

Minsu Kim (KAIST)*; Joanna Hong (KAIST); Yong Man Ro (KAIST)

1238: Salient Co-Speech Gesture Synthesizing with Discrete Motion Representation

Zijie Ye (Tsinghua University)*; Jia Jia (Tsinghua University); Haozhe Wu (Tsinghua University); Shuo
Huang (Tsinghua University); Shikun Sun (Tsinghua University); Junliang Xing (Tsinghua University)

1258: Rethink pair-wise self-supervised cross-modal retrieval from a contrastive learning

perspective
Tiantian Gong (Nanjing University of Aeronautics and Astronautics)*; Junsheng Wang (Nanjing University
of Science And Technology); Liyan Zhang (Nanjing University of Aeronautics and Astronautics)

1264: Embrace Smaller Attention: Efficient Cross-Modal Matching with Dual Gated Attention
Fusion.
Weikuo Guo (Dalian Univercity of Technology); Xiangwei Kong (Zhejiang Univercity)*

1289: CF-VTON: Multi-Pose Virtual Try-On with Cross-domain Fusion

Chenghu Du (Wuhan university of technology); Shengwu Xiong (Wuhan University of Technology)*

1382: Shuffled Autoregression For Motion Interpolation

Shuo Huang (Tsinghua University)*; Jia Jia (Tsinghua University); Zongxin Yang (Zhejiang University);
Wei Wang (University of Oxford); Haozhe Wu (Tsinghua University); Yi Yang (Zhejiang University);
Junliang Xing (Tsinghua University)

1467: Interaction-Assisted Multi-Modal Representation Learning for Recommendation

Hao Wu (Alibaba Group)*; Jiajie Wang (Alibaba Group); Zhonglin Zu (Alibaba Group)

1519: MULTI-SCALE COMPOSITIONAL CONSTRAINTS FOR REPRESENTATION LEARNING ON

VIDEOS
Georgios Paraskevopoulos (National Technical University of Athens); Chandrashekhar Lavania (AWS AI
Labs)*; Lovish Chum (Amazon Inc.); Shiva Sundaram (Amazon)

1586: MMATR: A lightweight approach for Multimodal Sentiment Analysis based on tensor
methods
Panagiotis Koromilas (University of Athens)*; Mihalis A Nicolaou (The Cyprus Institute); Theodoros
Giannakopoulos (NCSR Demokritos); Yannis Panagakis (University of Athens)

146
1700: Detection of Real-time DeepFakes in Video Conferencing with Active Probing and Corneal
Reflection
Hui Guo (University at Buffalo, SUNY)*; Xin Wang (University at Buffalo, SUNY); Siwei Lyu (University at
Buffalo)

1751: Class-aware Shared Gaussian Process Dynamic Model

Ryosuke Sawata (Sony Group Corporation / Hokkaido University)*; Takahiro Ogawa (Hokkaido
University); Miki Haseyama (Hokkaido University)

1923: Region-awared transformer with asymmetric loss in multi-label classification

Lei Zhang (Guangdong University of Petrochemical Technology)*; Jie Liu (University of Amsterdam);
Yanqi Bao (Nanjing University); Jie Wang (Northeastern University)

2015: NATURALISTIC HEAD MOTION GENERATION FROM SPEECH

Trisha Mittal (University of Maryland); Zakaria Aldeneh (Apple)*; Masha Fedzechkina (Apple); Anurag
Ranjan (Apple); Barry Theobald (Apple)

2017: ON THE ROLE OF LIP ARTICULATION IN VISUAL SPEECH PERCEPTION

Zakaria Aldeneh (Apple)*; Masha Fedzechkina (Apple); Skyler Seto (Apple); Katherine Metcalf (Apple,
Inc.); Miguel Sarabia (Apple); Nicholas Apostoloff (Apple Inc.); Barry Theobald (Apple)

2103: Multi-Temporal Lip-Audio Memory for Visual Speech Recognition

Jeong Hun Yeo (Korea Advanced Institute of Science and Technology)*; Minsu Kim (KAIST); Yong Man
Ro (KAIST)

2337: Locality Preserving Multiview Graph Hashing for Large Scale Remote Sensing Image Search
Wenyun Li (University of Macau); Guo Zhong (University of Macau); XINGYU LU (University of Macau);
Chi-Man Pun (University of Macau)*

2460: Your Camera Improves Your Point Cloud Compression

Lin Yuhuan (Tsinghua University)*; Tongda Xu (Tsinghua University); ziyu zhu (Tsinghua University);
Yanghao Li (Tsinghua University); Zhe Wang (Tsinghua University); Yan Wang (Tsinghua University)

2464: INDUCTIVE RELATION PREDICTION FROM RELATIONAL PATHS AND CONTEXT WITH
HIERARCHICAL TRANSFORMERS
Jiaang Li (University of Science and Technology of China)*; Quan Wang (Beijing University of Posts and
Telecommunications); Zhendong Mao (University of Science and Technology of China)

2507: A Multi-signal Perception Network For Textile Composition Identification

Bo Peng (Fudan University); Liren He (Fudan University); Dong Wu (Fudan University); mingmin Chi
(Fudan university)*; Jintao Chen (Shanghai Fabric Eyes Artificial Intelligence Technology Co., Ltd)

2730: Dual-Path Cross-Modal Attention for better Audio-Visual Speech Extraction

Zhongweiyang Xu (University of Illinois Urbana-Champaign)*; Xulin Fan (University of Illinois at Urbana-
Champaign); Mark Hasegawa-Johnson (University of Illinois)

2823: Single-branch Network for Multimodal Training

Muhammad Saad Saeed (University of Engineering and Technology); Shah Nawaz (German Electron
Synchrotron); Muhammad Haris Khan (Muhammad Bin Zayed University of Artificial Intelligence);
Muhammad Zaigham Zaheer (Mohamed bin Zayed University of Artificial Intelligence); Karthik
Nandakumar ( Mohamed Bin Zayed University of Artificial Intelligence); Mohammad Haroon Yousaf (UET
Taxila, Pakistan)*; Arif Mahmood (Information Technology University)

147
2980: Multimodal Propaganda Detection via Anti-persuasion Prompt Enhanced Contrastive
Learning
Jian Cui (Wuhan University of Technology)*; Lin Li (Wuhan University of Technology); Xin Zhang (Wuhan
University of Technology); Jingling Yuan (Wuhan University of Technology)

3113: GTN-Bailando: Genre Consistent Long-Term 3D Dance Generation based on Pre-trained

Genre Token Network
Haolin Zhuang (Tsinghua University)*; Shun Lei (Tsinghua University); Long Xiao (Tsinghua University);
Weiqin Li (Tsinghua University); Liyang Chen (Tsinghua University); Sicheng Yang (Tsinghua University);
Zhiyong Wu (Tsinghua University); Shiyin Kang (XVerse Inc.); Helen Meng (The Chinese University of
Hong Kong)

3117: CNN Filter for Super-Resolution with RPR functionality in VVC

Shimin Huang (Xidian University); Cheolkon Jung (Xidian University)*; Yang Liu (OPPO Mobile); Ming Li
(OPPO)

3133: Audio-driven Talking Head Video Generation with Diffusion Model

Yizhe Zhu (Shanghai Jiao Tong University)*; Chunhui Zhang (Shanghai Jiaotong University, CloudWalk
Technology Co., Ltd); Qiong Liu (CloudWalk); Xi Zhou (CloudWalk Technology)

3186: CC-POSENET: TOWARDS HUMAN POSE ESTIMATION IN CROWDED CLASSROOMS

Zefang Yu (Shanghai Jiao Tong University)*; Yanping Hu (Shanghai Jiao Tong University); Suncheng
Xiang (Shanghai Jiao Tong University); Ting Liu (Shanghai Jiao Tong University); Yuzhuo Fu (sjtu)

3337: SPARSE CONVOLUTION BASED OCTREE FEATURE PROPAGATION FOR LIDAR POINT
CLOUD COMPRESSION
Muhammad Asad Lodhi (InterDigital)*; Jiahao Pang (InterDigital); Dong Tian (InterDigital)

3476: On the Role of Visual Context in Enriching Music Representations

Kleanthis Avramidis (University of Southern California)*; Shanti Stewart (University of Southern
California); Shrikanth Narayanan (USC)

3489: SEMANTIC PREPROCESSOR FOR IMAGE COMPRESSION FOR MACHINES

Mingyi Yang (State Key Laboratory of ISN, Xidian University, Xi’an, China)*; Luis Herranz (Computer
Vision Center); Fei Yang (Universitat Autònoma de Barcelona); Luka Murn (British Broadcasting
Corporation); Marc Gorriz Blanch (BBC); Shuai Wan (Northwestern Polytechnical University); FuZheng
Yang (Xidian University); Marta Mrak (Queen Mary University of London)

3515: Unrestricted Anchor Graph based GCN for Incomplete Multi-view Clustering
Liang Zhao (Dalian University of Technology)*; Zihao Wang (Dalian University of Technology); Yukun
Yuan (Dalian University of Technology); Feng Ding (Dalian University of Technology)

3605: A Mutli-stage Hierarchical Relational Graph Neural Network for Multimodal Sentiment
Analysis
Peizhu Gong (Shanghai Maritime University)*; Jin Liu (Shanghai Maritime University); Xiliang Zhang
(Shanghai Maritime University); XingYe Li (Shanghai Maritime University)

3616: Multi-view Graph Regularized Deep Autoencoder-like NMF Framework

Liang Zhao (Dalian University of Technology)*; Zihao Wang (Dalian University of Technology); Ziyue
Wang (Dalian University of Technology); Zhikui Chen (Dalian University of Technology)

3694: An End-to-End Framework for Partial View-aligned Clustering with Graph Structure
Liang Zhao (Dalian University of Technology)*; Qiongjie Xie (大连理工大学); Songtao Wu (大连理工大学);
shubin ma (Dalian University of Technology)

148
3786: Whether Contribution of Features Differ Between Video-mediated and In-person Meetings in
Important Utterance Estimation
Fumio Nihei (NTT)*; Ryo Ishii (NTT); Yukiko Nakano (Seikei Univeristy); Atsushi Fukayama (NTT); Takao
Nakamura (NTT)

3853: Visual Answer Localization with Cross-modal Mutual Knowledge Transfer

Yixuan Weng (CASIA); Bin Li (Hunan University)*

3854: Visual Graph Reasoning Network

Dingbang Li (ECNU)*; Xin Lin (ECNU); Haibin Cai (East China Normal University); Wenzhou Chen
(Zhejiang University)

3883: A dataset for Audio-Visual Sound Event Detection in Movies

Rajat Hebbar (University of Southern California)*; Digbalay Bose (University of Southern California);
Krishna Somandepalli (University of Southern California); Veena Vijai (University of Southern California);
Shrikanth Narayanan (USC)

3997: EFFICIENT SUPER-RESOLUTION FOR COMPRESSION OF GAMING VIDEOS

Yifan Wang (Xidian University)*; Luka Murn (British Broadcasting Corporation); Luis Herranz (Computer
Vision Center); Fei Yang (Universitat Autònoma de Barcelona); Marta Mrak (Queen Mary University of
London); Wei Zhang (Xidian University); Shuai Wan (Northwestern Polytechnical University); Marc Gorriz
Blanch (BBC)

4007: DyLiteRADHAR: DYNAMIC LIGHTWEIGHT SLOWFAST NETWORK FOR HUMAN ACTIVITY

RECOGNITION USING MMWAVE RADAR
Biyun Sheng (Nanjing University of Posts and Telecommunications)*; Yan Bao (Nanjing University of
Posts and Telecommunications); Fu Xiao (Nanjing University of Posts and Telecommunications); Linqing
Gui (Nanjing University of Posts and Telecommunications)

4025: JOINT ROBUST REPRESENTATION AND GENERALIZATION ENHANCEMENT FOR CROSS-

MODALITY PERSON RE-IDENTIFICATION
Heqing Cheng (Chongqing University)*; Yong Feng (Chongqing University); Mingliang ZHOU (Chongqing
University); Xian-cai Xiong (Key Laboratory of Monitoring, Evaluation and Early Warning of Territorial
Spatial Planning Implementation, Ministry of Natural Resources); Yongheng Wang (Zhejiang Lab); Qiang
Baohua (Guilin University of Electronic Technology)

4241: Estimating Uncertainty on Video Quality Metrics

Pierre David (Capacités)*; Patrick Le Callet ("Universite de Nantes, France"); Suiyi Ling (University of
Nantes); Haixiong Wang (Meta); Ioannis Katsavounidis (Facebook); Zafar Shahid (Facebook); Cosmin
Stejerean (Meta)

4260: GAZE PRE-TRAIN FOR IMPROVING DISPARITY ESTIMATION NETWORKS

Ron M Hecht (General Motors)*; Ohad Rahamim (General Motors); Shaul Oron (GM); Andrea Forgacs
(General Motors); Gershon Celniker (General Motors); Dan Levi (General Motors); Omer Tsimhoni
(General Motors)

4268: A novel efficient multi-view traffic-related object detection framework

Kun Yang (Fudan University)*; Jing Liu (Fudan University); Dingkang Yang (Fudan University); Hanqi
Wang (Fudan University); Peng Sun (Duke Kunshan University); Liang Song (Fudan University)

4345: AV-SepFormer: Cross-attention SepFormer for Audio-Visual Target Speaker Extraction

Jiuxin Lin (Tsinghua University)*; Xinyu Cai (Tsinghua University); Heinrich Dinkel (Xiaomi ); Jun Chen
(Tsinghua University); Zhiyong Yan (xiaomi); Yongqing Wang (xiaomi); Junbo Zhang (Xiaomi); Zhiyong
Wu (Tsinghua University); Yujun Wang (xiaomi); Helen Meng (The Chinese University of Hong Kong)

149
4422: WL-MSR: Watch and Listen for Multimodal Subtitle Recognition
Jiawei Liu (Institute of Automation, Chinese Academy of Sciences and School of Artificial Intelligence,
University of Chinese Academy of Sciences)*; Hao Wang (National Laboratory of Pattern Recognition,
Institute of Automation, Chinese Academy of Sciences and School of Artificial Intelligence, University of
Chinese Academy of Sciences); Weining Wang ( The Laboratory of Cognition and Decision Intelligence
for Complex Systems, Institute of Automation, Chinese Academy of Sciences); Xingjian He (National
Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of Sciences and School of
Artificial Intelligence, University of Chinese Academy of Sciences); Jing Liu (National Lab of Pattern
Recognition, Institute of Automation,Chinese Academy of Sciences)

4532: Exploiting modality-invariant feature for robust multimodal emotion recognition with
missing modalities
Haolin Zuo (Inner Mongolia University)*; Rui Liu (Inner Mongolia University); Jinming Zhao (Qiyuan Lab);
Guanglai Gao (Inner Mongolia University); Haizhou Li (The Chinese University of Hong Kong
(Shenzhen))

4561: CN-CVS: A Mandarin Audio-Visual Dataset for Large Vocabulary Continuous Visual to
Speech Synthesis
Chen Chen (Tsinghua University)*; Dong Wang (Tsinghua University); Thomas Fang Zheng ("CSLT,
Tsinghua University")

4567: FlowGrad: Using Motion for Visual Sound Source Localization

Rajsuryan Singh (Universitat Pompeu Fabra); Pablo Zinemanas (Universitat Pompeu Fabra); Xavier
Serra (Universitat Pompeu Fabra ); Juan P Bello (New York University); Magdalena Fuentes (New
York University)*

4648: Multimodal Dyadic Impression Recognition via Listener Adaptive Cross-Domain Fusion
Yuanchao Li (University of Edinburgh)*; Peter Bell (University of Edinburgh ); Catherine Lai
(University of Edinburgh)

4725: Vision, Deduction and Alignment: An Empirical Study on Multi-modal Knowledge Graph
Alignment
Li Yangning (Tsinghua Shenzhen International Graduate School)*; Jiaoyan Chen (The University of
Manchester); Yinghui Li (Tsinghua University); Yuejia Xiang (Tencent); Xi Chen (Tencent); Hai-Tao Zheng
(Tsinghua University)

4791: Toward privacy-enhancing ambulatory-based well-being monitoring: Investigating user re-

identification risk in multimodal data
Ravi Pranjal (Texas A&M University); Ranjana Seshadri (Texas A&M University); Rakesh Kumar Sanath
Kumar Kadaba (Texas A&M University); Tiantian Feng (University of Southern California); Shrikanth
Narayanan (University of Southern California); Theodora Chaspari (Texas A&M University)*

4860: Contrastive Self-Supervised Learning for Automated Multi-Modal Dance Performance

Assessment
Yun Zhong (Imperial College London)*; Fan Zhang (Imperial College London); Yiannis Demiris (Imperial
College London)

5005: JPEG Pleno Call for Proposals responses quality assessment

João P.C Prazeres (Universidade da Beira Interior)*; Zhe Luo (University of Technology Sydney); Antonio
Pinheiro (U.B.I. & I.T.); Luis A da Silva Cruz (Dep. Electrical and Computer Engineering - Univ. of
Coimbra); Stuart Perry (University of Technology Sydney)

5104: CM-CS : CROSS-MODAL COMMON-SPECIFIC FEATURE LEARNING FOR AUDIO-VISUAL

VIDEO PARSING
Hongbo Chen (ShanghaiTech University); Dongchen Zhu (SIMIT); Guanghui Zhang (SIMIT); Wenjun Shi
(SIMIT); Xiaolin Zhang (SIMIT); Jiamao Li (SIMIT)*

150
5289: Contextually-rich human affect perception using multimodal scene information
Digbalay Bose (University of Southern California)*; Rajat Hebbar (University of Southern California);
Krishna Somandepalli (University of Southern California); Shrikanth Narayanan (USC)

5444: ModEFormer: Modality-Preserving Embedding for Audio-Video Synchronization using

Transformers
Akash Gupta (New York University)*; Rohun Tripathi (Amazon); Won-Dong Jang (Amazon Studios)

5528: Unsupervised Video Anomaly Detection for Stereotypical Behaviours in Autism

Jiaqi Gao (Fudan University); Xinyang Jiang (Microsoft Research Asia)*; Yuqing Yang (Microsoft
Research); Dongsheng Li (Microsoft Research Asia); Lili Qiu (The University of Texas at Austin)

5559: Audio-driven facial landmark generation in violin performance using 3DCNN network with
self attention model
Ting-Wei Lin (Academia Sinica)*; Chao-Lin Liu (National Chengchi University); Li Su (Academia Sinica)

5564: REAL-TIME AUDIO-VISUAL END-TO-END SPEECH ENHANCEMENT

Zirun Zhu (Microsoft)*; Hemin Yang (Microsoft); Min Tang (Microsoft); Ziyi Yang (Microsoft); Sefik Emre
Eskimez (Microsoft); Huaming Wang (Microsoft)

5707: Binauralization Robust to Camera Rotation Using 360° Videos

Masaki Yoshida (Hokkaido University)*; Ren Togo (Hokkaido University); Takahiro Ogawa (Hokkaido
University); Miki Haseyama (Hokkaido University)

5749: BAT: Bi-Alignment Based on Transformation in Multi-Target Domain Adaptation for Semantic
Segmentation
Xian Zhong (Wuhan University of Technology); Wei Li (WuHan University of Technology); Liang Liao
(Nanyang Technological University)*; Jing Xiao (Wuhan University); Wenxuan Liu (Wuhan University of
Technology); Wenxin Huang (Hubei University); Zheng Wang (Wuhan University)

5772: Next-speaker Prediction Based on Non-Verbal Information in Multi-party Video Conversation

Saki Mizuno (NTT Computer & Data Science Laboratories)*; Nobukatsu Hojo (NTT); Satoshi
Kobashikawa (NTT Corporation); Ryo Masumura (NTT Corporation)

5856: Confidence-based Event-centric Online Video Question Answering on a Newly Constructed

ATBS Dataset
Weikai Kong (University of Nottingham Ningbo, China); Shuhong Ye (University of Nottingham Ningbo
China); Chenglin Yao (UNNC); Jianfeng Ren (University of Nottingham Ningbo China)*

5879: Imaginary Voice: Face-styled Diffusion Model for Text-to-Speech

Jiyoung Lee (NAVER AI Lab)*; Joon Son Chung (KAIST); Soo-Whan Chung (Naver Corporation)

5893: BIRD-PCC: Bi-directional Range Image-based Deep LiDAR Point Cloud Compression
Chia-Sheng Liu (National Taiwan University)*; Jia-Fong Yeh (National Taiwan University); Hao Hsu
(National Taiwan University); Hung-Ting Su (National Taiwan University); Ming-Sui Lee (National Taiwan
University); Winston H. Hsu (National Taiwan University)

6037: Improving Few-Shot Learning for Talking Face System with TTS Data Augmentation
Qi Chen (Shanghai Jiao Tong University)*; Ziyang Ma (Shanghai Jiao Tong University); Tao Liu (Shanghai
Jiao Tong University); Xu Tan (Microsoft Research Asia); Qu Lu (Shanghai Media Tech); Kai Yu
(Shanghai Jiao Tong University); Xie Chen (Shanghai Jiaotong University)

151
6090: TWO-STREAM JOINT-TRAINING FOR SPEAKER INDEPENDENT ACOUSTIC-TO-
ARTICULATORY INVERSION
Jianrong Wang (School of Computer Science and Technology, Tianjin University, Tianjin, China); Jinyu
Liu (Tianjin University); Xuewei Li (Tianjin University); Mei Yu (Tianjin University); Jie Gao (Tianjin
University); Qiang Fang (Chinese Academy of Social Sciences); Li Liu (Shenzhen Research Institute of
Big Data, the chinese university of hong kong shenzhen)*

6122: Code-Switching Speech Synthesis Based on Self- Supervised Learning and Domain
Adaptive Speaker Encoder
YiXing Lin (National Central University); Cheng-Hsun Pai (National Central University); Le Phuong
(National Central University); Bima Prihasto (National Central University); CHIEN-LIN HUANG (NCKU);
Jia-Ching Wang (National Central University)*

6163: The Multimodal Information Based Speech Processing (MISP) 2022 Challenge: Audio-Visual
Diarization and Recognition
Zhe Wang (University of Science and Technology of China)*; Shilong Wu (University of Science and
Technology of China); Hang Chen (USTC); Mao-Kui He (University of Science and Technology of China);
Jun Du (University of Science and Technology of China); Chin-hui Lee (Georgia Institute of Technology);
Shinji Watanabe (Carnegie Mellon University); Sabato M Siniscalchi (Kore University of Enna); Odette
Scharenborg (Multimedia Computing Group, Delft University of Technology); Baocai Yin
(USTC,iFLYTEK); Jia Pan (iFlytek Research); Cong Liu (iFLYTEK Research)

6206: SEMGEO: SEMANTIC KEYWORDS FOR CROSS-VIEW IMAGE GEO-LOCALIZATION

Royston Rodrigues (NEC)*; Masahiro Tani (NEC)

6251: A DATABASE FOR MULTI-MODAL SHORT VIDEO QUALITY ASSESSMENT

Yukun Zhang (Institute of Information Engineering, Chinese Academy of Sciences)*; Chuan Wang
(Chinese Academy of Sciences ); Sanyi Zhang (Institute of Information Engineering, Chinese Academy of
Sciences); Xiaochun Cao (Sun Yat-sen University)

6261: Detecting Out-of-distribution Examples via Class-conditional Impressions Reappearing

Jinggang Chen (Huazhong University of Science and Technology); Xiaoyang Qu (Ping An Technology
(Shenzhen) Co., Ltd); Junjie Li (Huazhong University of Science and Technology); Jianzong Wang (Ping
An Technology (Shenzhen) Co., Ltd)*; Jiguang Wan (Huazhong University of Science and Technology);
Jing Xiao (Ping An Insurance (Group) Company of China)

6290: Guide and Select: A Transformer-based Multimodal Fusion Method for Points of Interest
Description Generation
Hanqing Liu (Tsinghua Shenzhen International Graduate School)*; Wei Wang (Tsinghua University); Niu
Hu (Tsinghua University); Hai-Tao Zheng (Tsinghua University); Rui Xie (Meituan); Wei Wu (Meituan);
Yang Bai (Tsinghua University)

6294: Deep probabilistic model for lossless scalable point cloud attribute compression
Dat Thanh Nguyen (University of Erlangen-Nuremberg)*; Kamal Nambiar (Friedrich-Alexander-Universität
Erlangen-Nürnberg); Andre Kaup (Friedrich-Alexander-Universität Erlangen-Nürnberg)

6332: Abusive activity detection with multi-modality based on convolutional neural network
Jisoo Kim (Korea Institute of Science and Technology (KIST))*; Hyebin Ahn ( Korea Institute of
Science and Technology (KIST)); Byounghyun Yoo (Korea Institute of Science and Technology (KIST))

6404: MRML: Multimodal Rumor Detection by Deep Metric Learning

Liwen Peng (National University of Defence Technology)*; Songlei Jian (National University of Defense
Technology); Dongsheng Li (School of Computer Science, National University of Defense Technology);
Siqi Shen (Xiamen University)

152
6478: IMPROVING THE MODALITY REPRESENTATION WITH MULTI-VIEW CONTRASTIVE
LEARNING FOR MULTIMODAL SENTIMENT ANALYSIS
Peipei Liu (School of Cyber Security, University of Chinese Academy of Sciences); Xin Zheng (Henan
University); Hong Li (Institute of Information Engineering，Chinese Academy of Sciences)*; Liu Jie
(Institute of Information Engineering，Chinese Academy of Sciences); Yimo Ren (Beijing Haidian);
Hongsong Zhu (Institute of information Engineering, CAS); Limin Sun (Institute of Information
Engineering, Chinese Academy of Sciences)

6513: SSVMR: SALIENCY-BASED SELF-TRAINING FOR VIDEO-MUSIC RETRIEVAL

Xuxin Cheng (Peking University)*; Zhihong Zhu (Peking University); Hongxiang Li (Peking University);
Yaowei Li (Peking University); Yuexian Zou (Peking University)

153
 Sensor Array and Multichannel Signal Processing

268: Deep fusion of multi-object densities using transformer

Lechi Li (Chalmers University of Technology); Chen Dai (Chalmers University of Technology); Yuxuan Xia
(Chalmers University of Technology)*; Lennart Svensson (Chalmers University of Technology)

278: Improved Deep Speaker Localization and Tracking: Revised Training Paradigm and
Controlled Latency
Alexander Bohlender (IDLab, Ghent University - imec)*; Liesbeth Roelens (IDLab, Ghent University -
imec); Nilesh Madhu (IDLab, Ghent University - imec)

327: ENHANCED COPRIME ARRAY CONFIGURATION FOR DOA ESTIMATION OF NON-CIRCULAR

SIGNALS
Nabil Mohsen (University of Science and Technology of China (USTC))*; Ammar Hawbani (University of
Science and Technology of China); Xing-Fu Wang (USTC); Benjamin Bairrington (USTC); Liang Zhao
(Shenyang Aerospace University); Saeed Alsamhi (Software Research Institute, AthloneInstitute of
Technology)

910: Variational Message Passing-based Respiratory Motion Estimation and Detection Using
Radar Signals
Jakob Möderl (Graz University of Technology)*; Erik Leitinger (Graz University of Technology); Franz
Pernkopf (Graz University of Technology); Klaus Witrisal (Graz University of Technology, Austria)

981: Optimal Mixed-ADC arrangement for DOA estimation via CRB under ULA
Xinnan Zhang (University of Science and Technology of China)*; Yuanbo Cheng (University of Science
and Technology of China); Xiaolei Shang (University of Science and Technology of China); Jun Liu
(University of Science and Technology of China)

986: Robust Iterative Solution for Linear Array-Based 3-D Localization By Message Passing
Yimao Sun (Sichuan University); Dominic Ho (Nil); Yanbing Yang (Sichuan University); Lei Zhang
(Sichuan University)*; Liangyin Chen (Sichuan University)

1089: super-resolution harmonic retrieval of non-circular signals

Yu Zhang (Nanjing University of Aeronautics and Astronautics)*; Yue Wang (George Mason University);
Zhi Tian (George Mason University); Geert Leus (TU Delft); Gong Zhang (Nanjing University of
Aeronautics and Astronautics)

1361: ERROR ANALYSIS OF CONVOLUTIONAL BEAMSPACE ALGORITHMS

Po-Chih Chen (California Institute of Technology)*; Dr.P P Vaidyanathan (California Institute of
Technology)

1362: UNITARY ESPRIT FOR COPRIME ARRAYS

Po-Chih Chen (California Institute of Technology)*; Dr.P P Vaidyanathan (California Institute of
Technology)

1372: CD-FSOD: A Benchmark for Cross-domain Few-shot Object Detection

Wuti Xiong (University of Oulu, Finland)*

154
1482: GCC-speaker: Target Speaker Localization with Optimal Speaker-dependent Weighting in
Multi-speaker Scenarios
Guanjun Li (Institute of Automation, Chinese Academy of Sciences)*; Wei Xue (Department of Computer
Science, Hong Kong Baptist University, Hong Kong SAR, China); Wenju Liu (National Laboratory of
Pattern Recognition, Institute of Automation, University of Chinese Academy of Sciences, Beijing, China);
Jiangyan Yi (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of
Sciences); Jianhua Tao ("National Laboratory of Pattern Recognition, Institute of Automation, Chinese
Academy of Sciences")

1669: Using Received Power in Microphone Arrays to Estimate Direction of Arrival

Gustav Zetterqvist (Linköping University)*; Fredrik Gustafsson (Linköping University); Gustaf Hendeby
(Linköping University)

1709: Direction-of-arrival estimation using Gaussian process interpolation

Ishan D Khurjekar (Scripps Institute of Oceanography)*; Peter Gerstoft (UCSD); Christoph F
Mecklenbräuker (Technische Universität Wien); Zoi-Heleni Michalopoulou (New Jersey Institute of
Technology)

1762: LiQuiD-MIMO Radar: Distributed MIMO Radar with Low-Bit Quantization

Yikun Xiang (Nanjing University of Science and Technology); Feng Xi (Nanjing University of Science and
Technology)*; Shengyao Chen (Nanjing University of Science and Technology)

1813: EXPLICIT ZIV-ZAKAI BOUND FOR MULTIPLE SOURCES DOA ESTIMATION

Zongyu Zhang (Zhejiang University)*; Yujie Gu (Aptiv); Zhiguo Shi (Zhejiang University)

1816: Radio-astronomy imaging and interference excision using tensor decomposition and
canonical correlation analysis
Mikael Sorensen (University of Virginia)*; Nicholas D Sidiropoulos (University of Virginia)

2026: Improved Mask-Based Neural Beamforming for Multichannel Speech Enhancement by

Snapshot Matching Masking
Ching-Hua Lee (Samsung Research America)*; Chouchang Yang (Samsung Research America); Yilin
Shen (Samsung Research America); Hongxia Jin (Samsung Research America)

2049: Resolving Doppler Ambiguity via Spread Phase Alignment in FDA-MIMO Radar
Yanxing Wang (National Laboratory of Radar Signal Processing, Xidian University,)*; Shengqi
Zhu (National Laboratory of Radar Signal Processing, Xidian University,); Guisheng Liao (National
Laboratory of Radar Signal Processing, Xidian University,); Lan Lan (National Laboratory of Radar Signal
Processing, Xidian University,); Zhuochen Chen (National Laboratory of Radar Signal Processing, Xidian
University,); Feilong Liu (National Laboratory of Radar Signal Processing, Xidian University,)

2130: Bias Reduced Semidefinite Relaxation Method for Multistatic Localization in the Absence of
Transmitter Position and Its Synchronization
Pei Jian (Ningbo University); Gang Wang (Ningbo University)*; Dominic Ho (Nil); Lei Huang (Shenzhen
University)

2207: Gridless Target Localization for FDA-MIMO Radar with Sparse Arrays
Xiaohuan Wu (Nanjing University of Posts and Telecommunications)*; yaxin liu (Nanjing University of
Posts and Telecommunications); Xiaoyuan Jia (Nanjing University of Posts and Telecommunications)

2229: Exploiting Sparse Recovery Algorithms for Semi-Supervised Training of Deep Neural
Networks for Direction-of-Arrival Estimation
Murtiza Ali (Indian Institute of Technology, Jammu)*; Aditya Arie Nugraha (RIKEN); Karan Nathwani
(Indian Institute of Technology, Jammu)

155
2238: ROBUST SUBSPACE TRACKING WITH CONTAMINATION MITIGATION VIA $\alpha$-
DIVERGENCE
LE Trung Thanh (University of Orleans)*; Aref Miri Rekavandi (University of Melbourne, Melbourne,
Australia); Abd-Krim Seghouane (University of Mebourne); KARIM ABED-MERAIM (PRISME laboratory,
university of Orleans, France)

2321: Wireless location tracking via complex-domain Super MDS with time series self-localization
information
Yuya Nishi (Osaka University)*; Takumi Takahashi (Osaka University); Hiroki Iimori (Ericsson Research);
Giuseppe Abreu (Jacobs University Bremen); Shinsuke Ibi (Doshisha University); Seiichi Sampei (Osaka
University)

2330: Dual-Stream Siamese Vision Transformer with Mutual Attention for Radar Gait Verification
Ran Ji (School of Computer Science, University of Nottingham Ningbo China); Jiarui Li (School of
Computer Science, University of Nottingham Ningbo China); Wentao He (University of Nottingham
Ningbo China); Jianfeng Ren (University of Nottingham Ningbo China)*; Xudong Jiang (Nanyang
Technological University)

2404: ONE-SHOT MEDICAL ACTION RECOGNITION WITH A CROSS-ATTENTION MECHANISM AND

DYNAMIC TIME WARPING
Leiyu Xie (Newcastle University)*; Yuxing Yang (Newcastle University); Zeyu Fu (University of Exeter);
Syed Mohsen Naqvi (Newcastle University)

2463: Angle-of-arrival Target Tracking Using a Mobile UAV In External Signal-denied Environment
Bing Zhu (Shenzhen Institute of Advanced Technology, Chinese Academy of Sciences); Sheng Xu
(Shenzhen Institute of Advanced technology, Chinese Academy of Sciences)*; Feng Rice (QinetiQ
Australia); Kutluyil Dogancay (University of South Australia)

2571: Order Reduction of Multi-Channel FIR Filters by Balanced Truncation

Florian Hilgemann (Institute of Communication Systems, RWTH Aachen University)*; Peter Jax (RWTH
Aachen University, Institute of Communication Systems (IKS))

2604: DIFFERENCE COARRAYS OF RATIONAL ARRAYS

Pranav D Kulkarni (California Institute of Technology)*; Dr.P P Vaidyanathan (California Institute of
Technology)

2632: Passive Acoustic Tracking of Whales in 3-D

Junsu Jang (UC San Diego)*; Florian Meyer (UC San Diego); Eric Snyder (UC San Diego); Sean Wiggins
(UC San Diego); Simone Baumann-Pickering (UC San Diego); John Hildebrand (Univ of California San
Diego)

2662: Fast Cross-Correlation for TDoA Estimation on Small Aperture Microphone Arrays
François Grondin (Université de Sherbrooke)*; Marc-Antoine Maheux (Université de Sherbrooke); Jean-
Samuel Lauzon (Université de Sherbrooke); Jonathan Vincent (Université de Sherbrooke); Francois
Michaud (Universite de Sherbrooke)

2821: A Distributed Adaptive Algorithm for Non-Smooth Spatial Filtering Problems

Charles Hovine (KULeuven)*; Alexander Bertrand (KU Leuven)

2839: Hypothesis test for leakage detection in water pipelines with high-dimensional sensor
signals
Liusha Yang (Shenzhen Technology University)*; Matthew McKay (University of Melbourne); Xun Wang
(Beihang University)

156
2937: A Computationally Efficient Algorithm for Distributed Adaptive Signal Fusion based on
Fractional Programs
Cem A. Musluoglu (KU Leuven)*; Alexander Bertrand (KU Leuven)

2973: Dynamic Independent Component Extraction with Blending Mixing Vector: Lower Bound on
Mean Interference-to-Signal Ratio
Jaroslav Čmejla (Technical University of Liberec)*; Zbynek Koldovsky (Technical University of Liberec);
Václav Kautský (Technical University of Liberec); Tulay Adali (University of Maryland, Baltimore County)

3098: Target Velocity Estimation for Quantization-Based Cooperative MIMO Radar and
Communications System
Zhen Wang (Southwest Petroleum University); xue xue yan (yanxuedan); Qian He (University of
Electronic Science and Technology of China)*; Rick S Blum (Lehigh University)

3121: MIMO RADAR TRANSMIT BEAMPATTERN MATCHING VIA MANIFOLD OPTIMIZATION

Weijie Xiong (University of Electronic Science and Technology of China)*; Jinfeng Hu (University of
Electronic Science and Technology of China); Kai Zhong (University of Electronic Science and
Technology of China)

3214: Tensorized Neural Layer Decomposition for 2-D DOA Estimation

Hang Zheng (Zhejiang University)*; Chengwei Zhou (Zhejiang University); Sergiy A. Vorobyov (Aalto
University); Zhiguo Shi (Zhejiang University)

3217: Data Driven Joint Sensor Fusion and Regression based on Geometric Mean Squared Error
Carlos A Lopez Molina (Polythecnic University of Catalonia)*; Jaume Riba (UPC)

3226: TO REGULARIZE OR NOT TO REGULARIZE: THE ROLE OF POSITIVITY IN SPARSE ARRAY

INTERPOLATION WITH A SINGLE SNAPSHOT
Mehmet Hucumenoglu (University of California San Diego); Pulak Sarangi (UCSD)*; Robin Rajamaki
(UCSD); Piya Pal (Nil)

3235: ON SUPER-RESOLUTION WITH SEPARATION PRIOR

Xingyun Mao (Shanghai Jiao Tong university)*; HENG QIAO (SHANGHAI JIAO TONG UNIVERSITY)

3298: Optimal Carrier Frequency Design for Frequency Diverse Array MIMO Radar
Jie Cheng (University of electronic science and technology of China); Maria Juhlin (Lund University);
Wen-Qin Wang (University of electronic science and technology of China)*; Andreas Jakobsson (Lund
University)

3324: Equivalence of aperture reduction in element space and constrained combination of DFT
beams in beamspace
Damir Rakhimov (TU-Ilmenau)*; Martin Haardt (Ilmenau University of Technology)

3472: LIGHT-WEIGHT SEQUENTIAL SBL ALGORITHM: AN ALTERNATIVE TO OMP

Rohan Ramchandra Pote (University of California San Diego)*; Bhaskar Rao (UC San Diego)

3474: MMWAVE WI-FI TRAJECTORY ESTIMATION WITH CONTINUOUS-TIME NEURAL DYNAMIC

LEARNING
Cristian J Vaca Rubio (Aalborg University); Pu Wang (MERL)*; Toshiaki Koike-Akino (Mitsubishi Electric
Research Laboratories); Ye Wang (Mitsubishi Electric Research Laboratories); Petros Boufounos
(Mitsubishi Electric Research Laboratories); Petar Popovski (Aalborg University)

3637: Binary sequence set optimization for CDMA applications via mixed-integer quadratic
programming
Alan Yang (Stanford University)*; Tara Mina (Stanford University); Grace Gao (Stanford University)

157
3824: Graph Signal Processing for Narrowband Direction of Arrival Estimation
Disheng Li (University of Sheffield); Wei Liu (University of Sheffield)*; Yuriy Zakharov (University of York);
Paul Mitchell (University of York)

3913: DIFFUSION-BASED SOUND SOURCE LOCALIZATION USING NETWORKS OF PLANAR

MICROPHONE ARRAYS
Davide Albertini (Politecnico di Milano)*; Gioele Greco (Politecnico di Milano); Alberto Bernardini
(Politecnico di Milano); Augusto Sarti (Politecnico di Milano)

3948: Sparse Bayesian Learning Based Three-Dimensional Imaging for Antenna Array Radar
Yuhan Li (Xiamen University)*; Jesper Rindom Jensen (Aallborg University); Maozhong Fu (Xiamen
University of Technology); Zhenmiao Deng (Sun Yat-sen University); Mads G. Christensen (Audio
Analysis Lab., AD:MT, Aalborg University, Denmark)

3975: AN AUTOMOTIVE RADAR DATASET FOR OBJECT CLASSIFICATION

Akshad Shyam (Indian Institute of Technology Hyderabad ); Kusum K (IIT Hyderabad ); Monika Gautam
(Indian Institute of Technology ); Vamshi Krishna Kancharla (IIIT Bangalore college); vennela gudisa (IIT
HYDERABAD); Virendra Patil (Indian Institute of Technology Hyderabad)*; Aanandh S Balasubramanian
(Intel); Sumohana S. Channappayya (IIT Hyderabad)

4027: SUBSPACE-BASED DETECTOR FOR DISTRIBUTED MMWAVE MIMO RADAR SENSORS

Moein Ahmadi (University of Luxembourg, SNT)*; Mohammad Alaee (University of Luxembourg); Bhavani
Shankar Mysore Ramarao (University of Luxembourg); Bjorn Ottersten (SnT)

4043: Sensor Selection for Angle of Arrival Estimation Based on the Two-Target Cramér-Rao
Bound
Costas A Kokke (Delft University of Technology)*; Mario Coutino (TNO); Laura Anitori (TNO); Richard
Heusdens (Netherlands Defence Academy); Geert Leus (TU Delft)

4108: Transmit Energy Focusing for Parameter Estimation in Transmit Beamspace Slow-time
MIMO Radar
Tingting Zhang (Nanjing University of Science and Technology)*; Feng Xu (Aalto University); Sergiy
Vorobyov ()

4132: Sparse Non-Contact Multiple People Localization and Vital Signs Monitoring Via FMCW
Radar
Yonathan Eder (Weizmann Institute of Science)*; Zhuoyang Liu (Weizmann Institute of Science); Yonina
Eldar ()

4149: Clustered Greedy Algorithm for Large-Scale Sensor Selection

Kaushani Majumder (Indian Institute of Technology, Bombay)*; Sibi Raj B. Pillai (Indian Institute of
Technology, Bombay); Satish Mulleti (Indian Institute of Technology Bombay, India)

4228: Near-field Localization with Dynamic Metasurface Antennas

Qianyu Yang (Nanjing University of Posts and Telecommunications)*; Anna Guerra ( the National
Research Council of Italy, Institute of Electronics, Computer and Telecommunication Engineering);
Francesco Guidi (the National Research Council of Italy, Institute of Electronics, Computer and
Telecommunication Engineering); Nir Shlezinger (Ben-Gurion University); Haiyang Zhang (Nanjing
University of Posts and Telecommunications); Davide Dardari (DEIS-University of Bologna, Italy); Baoyun
Wang (Nanjing University of Posts and Telecommunications); Yonina Eldar ()

4332: Multi-User Data Detection in Massive MIMO with 1-Bit ADCs

Amin Radbord (Centre for Wireless Communications (CWC) at University of Oulu); Italo Atzeni (University
of Oulu)*; Antti Tölli (University of Oulu)

158
4392: Deep learning-based compressive sampling optimization in massive MIMO systems
Saidur Pavel (Temple University); Yimin D Zhang (Temple University)*; Maria S. Greco (University of
Pisa); Fulvio Gini (University of Pisa)

4481: Towards improved sonar performance using environment-informed sparse sub-array

processing
Alexandre L'Her (Thales DMS)*; Angélique Drémeau (ENSTA Bretagne); Florent Le Courtois (DGA TN);
Gaultier Real (DGA TN); Xavier Cristol (Thales DMS); Yann Stéphan (SHOM)

4491: Sample-Efficient Robust MMV Recovery Algorithm

Yuvraj Singh (IIT Bombay); Jahnvi S Rohela (Indian Institute of Technology Bombay); Satish Mulleti
(Indian Institute of Technology Bombay, India)*

4528: Soft label coding for end-to-end sound source localization with ad-hoc microphone arrays
Linfeng Feng (Northwestern Polytechnical University)*; Yijun Gong (Northwestern Polytechnical
University); Zhang XiaoLei (Northwestern Polytechnical University)

4572: A Radar-Jammer Zero-Sum Repeated Bayesian Game

Sofia Suvorova (The University of Melbourne); Ali Pezeshki (Colorado State University)*; Ross Kyprianou
(Defence Science and Technology Group); William Moran (The University of Melbourne)

4633: RATE SPLITTING AND PRECODING STRATEGIES FOR MULTI-USER MIMO BROADCAST
CHANNELS WITH COMMON AND PRIVATE STREAMS
Liana Khamidullina (Ilmenau University of Technology)*; André Almeida (Federal University of Ceará);
Martin Haardt (Ilmenau University of Technology)

4638: Robust Adaptive Beamforming with Proximal Method

Ruifu Li (UCLA)*; Danijela Cabric (University of California, Los Angeles)

4640: RANGE-ISL MINIMIZATION AND SPECTRAL SHAPING IN MIMO RADAR SYSTEMS VIA
WAVEFORM DESIGN
Ehsan Raei (SnT, University of Luxembourg)*; Mohammad Alaee (University of Luxembourg); Bhavani
Shankar Mysore Ramarao (University of Luxembourg); Bjorn Ottersten (SnT)

4658: Deep Learning Sparse Array Design Using Binary Switching Configurations
Syed Ali Hamza (Widener University)*; Kyle Juretus (Villanova University); Moeness Amin (Villanova
University); Fauzia Ahmad (Temple University)

4688: Neural Maximum-A-Posteriori Beamforming For Ultrasound Imaging

Ben Luijten (Eindhoven University of Technology)*; Boudewine Ossenkoppele (Delft University of
Technology); Nico de Jong (Delft University of Technology); Martin Verweij (Delft University of
Technology); Yonina Eldar (); Massimo Mischi (Eindhoven University of Technology); Ruud J. G. van
Sloun (Technical university of Eindhoven)

4824: Low-rank tensor decompositions for quaternion multiway arrays

Osimone Imhogiemhe (Université de Lorraine, CNRS, CRAN); Julien Flamant (CNRS)*; Xavier Luciani
(Université de Toulon, Aix Marseille Université, CNRS, Seatech, LIS); Yassine ZNIYED (LIS/SeaTech);
Sebastian Miron (University of Lorraine)

4838: SPARSITY CONSTRAINT IMPLEMENTATION FOR THE JOINT EIGENVALUE

DECOMPOSITION OF MATRICES
Rémi ANDRÉ (Institut Fresnel)*; Xavier Luciani (LIS)

159
4947: SUPER DILATED NESTED ARRAYS WITH IDEAL CRITICAL WEIGHTS AND INCREASED
DEGREES OF FREEDOM
Ahmed Mohammed Shaalan (University of Science and Technology of China)*; Jun Du (University of
Science and Technology of China)

5035: SIMULTANEOUS ESTIMATION OF DIRECTION OF ARRIVAL AND SOUND SPEED USING A

NON-UNIFORM SENSOR ARRAY
Ryouichi Nishimura (National Institute of Information and Communications Technology)*; Kenichi
Takizawa (National Institute of Information and Communications Technology)

5233: Multi-User Methods for Vibrational Radar Backscatter Communications

Jessica M Centers (Duke University)*; Jeffrey Krolik (Duke University)

5266: DIRECT POSITION DETERMINATION WITH ONE-BIT SIGNAL FOR MULTIPLE TARGETS
Lihua Ni (University of Electronic Science and Technology of China)*; Di Zhang (University of Electronic
Science and Technology of China); Tianyi Xing (University of Electronic Science and Technology of
China); Maoyan Ran (University of Electronic and technology of China); Ning Liu (Northern Institute of
Electronic Equipment); Qun Wan (University of Electronic Science and Technology of China)

5410: Active IRS-Assisted MIMO Channel Estimation and Prediction

Mirza Asif Haider (Temple University); Saidur Pavel (Temple University); Yimin D Zhang (Temple
University)*; Elias Aboutanios (University of New South Wales)

5483: Waveform design to improve the estimation of target parameters using the Fourier
Transform method in a MIMO OFDM DFRC system
Satwika Bhogavalli (Department of Electrical Communication Engineering, Indian Institute of Science,
Bangalore)*; Eric Grivel (Bordeaux INP, IMS laboratory); KVS Hari (Department of Electrical
Communication Engineering, Indian Institute of Science, Bangalore); Vincent Corretja (THALES)

5517: JOINT ESTIMATION OF DOA AND DISTANCE IN NOISY REVERBERANT CONDITIONS

Suliang Bu (University of Missouri); Tuo Zhao (University of Missouri)*; Yunxin Zhao (University of
Missouri)

5677: DEEP NEURAL MEL-SUBBAND BEAMFORMER FOR IN-CAR SPEECH SEPARATION

Vinay Kothapally (Tencent AI)*; Yong Xu (Tencent); Meng Yu (Tencent); Shixiong Zhang (Tencent); Dong
Yu (tencent)

5896: SPARSE ERROR CORRECTION FOR POWER NETWORK PARAMETERS

Dilan S Senaratne (Oregon State University)*; Jinsub Kim (Oregon State)

5973: SOURCE LOCALIZATION FOR EXTREMELY LARGE-SCALE ANTENNA ARRAYS WITH

SPATIAL NON-STATIONARITY
Xiaohuan Wu (Nanjing University of Posts and Telecommunications)*; Ji Sun (Nanjing University of Posts
and Telecommunications); Xiaoyuan Jia (Nanjing University of Posts and Telecommunications); Shuxin
Wang ( Nanjing University of Posts and Telecommunications)

6019: Quantized Precoding and RIS-Assisted Modulation for Integrated Sensing and
Communications Systems
R.S. Prasobh Sankar (Indian Institute of Science Bangalore)*; Sundeep Prabhakar Chepuri (Indian
Institute of Science)

6240: Nonnegative block-term decomposition with the β-divergence: joint data fusion and blind
spectral unmixing
Clémence Prévost (University of Lille)*; Valentin Leplat (Skoltech)

160
6272: A DNN BASED NORMALIZED TIME-FREQUENCY WEIGHTED CRITERION FOR ROBUST
WIDEBAND DOA ESTIMATION
Kuan-Lin Chen (University of California San Diego)*; Ching-Hua Lee (University of California, San Diego);
Bhaskar Rao (UC San Diego); Harinath Garudadri (University of California, San Diego)

6338: A PROXIMAL APPROACH TO IVA-G WITH CONVERGENCE GUARANTEES

Clément Cosserat (CVN)*; Ben Gabrielson (University of Maryland, Baltimore County); Emilie
Chouzenoux (Inria Saclay); Jean-Christophe Pesquet (CentraleSupelec); Tulay Adali (University of
Maryland, Baltimore County)

6422: Mixed Far-field and Near-field Source Localization Based on Low-Rank Matrix
Reconstruction
Yunchang Liu (Jilin University); Hong Jiang (Jilin University)*; Qi Zhang (Jilin University)

6466: EFFICIENT LARGE-SCALE MULTI-UNIMODULAR WAVEFORM DESIGN WITH GOOD

CORRELATION PROPERTIES VIA DIRECT PHASE OPTIMIZATIONS
xiaohan zhao (Beijing Institute of Technology)*; Yongzhe Li (Beijing Institute of Technology); Ran Tao
(Beijing Institute of Technology)

161
 Signal Processing Education

3212: EFFECTIVE GRAPH-BASED MODELING OF ARTICULATION TRAITS FOR

MISPRONUNCIATION DETECTION AND DIAGNOSIS
Bi-Cheng Yan (National Taiwan Normal University )*; Hsin-Wei Wang (National Taiwan Normal
University); Yi-Cheng Wang (National Taiwan Normal University); Berlin Chen (National Taiwan Normal
University)

4731: StuArt: Individualized Classroom Observation of Students with Automatic Behavior

Recognition and Tracking
Huayi Zhou (Shanghai Jiao Tong University)*; Fei Jiang (East China Normal University); Jiaxin Si
(Shanghai Jiao Tong University); Lili Xiong (Chongqing Academy of Science and Technology); Hongtao
Lu (Shanghai Jiao Tong University)

4966: SIGNAL ANALYSIS-SYNTHESIS USING THE QUANTUM FOURIER TRANSFORM

Aradhita Sharma (Arizona State University)*; Glen Uehara (Arizona State University); Vivek
Narayanaswamy (Arizona State University); Leslie Miller (Arizona State University); Andreas Spanias
(ASU)

5324: On Designing A 3D Imaging Summer Project for Ontario's High School Students during
Covid-19 Pandemic
Fengbo Lan (York University); Gene Cheung (York University)*; Prabhkirat Arora (York University);
Deinabo Richard-Koko (York University); Lisa Cole (York University)

162
 Signal Processing for Communications and Networking

174: ON BIDIRECTIONAL PREESTIMATES AND THEIR APPLICATION TO IDENTIFICATION OF

FAST TIME-VARYING SYSTEMS
Maciej Niedzwiecki (n/a)*; Artur Gancza (Gdansk University of Technology); Lu Shen (School of Physics,
Engineering and Technology,University of York); Yuriy Zakharov (School of Physics, Engineering and
Technology,University of York)

219: A CRITICAL LOOK AT RECENT TRENDS IN COMPRESSION OF CHANNEL STATE

INFORMATION
Marcus Valtonen Örnhag (Ericsson Research); Stefan Adalbjörnsson (Ericsson Research)*; Püren Güler
(Ericsson); Mojtaba Mahdavi (Ericsson)

478: Downlink Covariance Estimation in URA FDD Massive MIMO systems

Salime Bameri (Carleton University)*; Khalid Almahrog (Carleton university); Ramy Gohary (Carleton
University); Amr El-Keyi (Ericsson); Yahia Ahmed (Ericsson)

569: Noncoherent multiuser Grassmannian Constellations for the MIMO Multiple Access Channel
Javier Álvarez Vizoso (Universidad de Cantabria)*; Diego Cuevas (Universidad de Cantabria); Carlos
Beltrán (Universidad de Cantabria); Ignacio Santamaria (University of Cantabria); Vít Tucek (Huawei
Technologies); Gunnar Peters (Huawei Sweden)

584: Model-based vs. Data-driven Approaches for Predicting Rain-induced Attenuation in

Commercial Microwave Links: A Comparative Empirical Study
Dror Jacoby (Tel Aviv Univesity)*; Jonatan Ostrometzky (Tel Aviv University); Hagit Messer (Tel Aviv
University)

918: CHANNEL ESTIMATION IN MASSIVE MIMO WITH HEAVY-TAILED NOISE: GAUSSIAN-

MIXTURE VERSUS CAUCHY MODELS
Ziya Gülgün (Linkoping University)*; Erik G. Larsson (Nil)

952: INVERSE QUADRATIC TRANSFORM FOR MINIMIZING A SUM OF RATIOS

Yannan CHEN (The Chinese University of Hong Kong, Shenzhen); Licheng Zhao (Shenzhen Research
Institute of Big Data); Yaowen Zhang (CUHKSZ); Kaiming Shen (The Chinese University of Hong Kong,
Shenzhen)*

1020: EMC²-Net: JOINT EQUALIZATION AND MODULATION CLASSIFICATION BASED ON

CONSTELLATION NETWORK
Hyun Ryu (KAIST)*; Junil Choi (KAIST)

1256: Optimizing distributed multi-sensor multi-target tracking algorithm based on labeled multi-
bernoulli filter
Honggang Liu (Fudan University)*; Jinlong Yang (Jiangnan university); Yue Xu (Jiangnan University); Le
Yang (University of Canterbury)

1417: Interference Leakage Minimization in RIS-assisted MIMO Interference Channels

Ignacio Santamaria (University of Cantabria)*; Mohammad Soleymani (Universität Paderborn); Eduard A
Jorswieck (TU Braunschweig); Jesús Gutiérrez (IHP)

1704: EH-Enabled Distributed Detection Over Temporally Correlated Markovian MIMO Channels
Ghazaleh Ardeshiri (University of central Florida)*; Azadeh Vosoughi (University of Central Florida)

163
1808: Structure-aware Sparse Bayesian Learning-based Channel Estimation for Intelligent
Reflecting Surface-aided MIMO
Yanbin He (Delft University of Technology)*; Geethu Joseph (TU Delft)

1879: Multi-Functional Reconfigurable Intelligent Surface

Wen Wang (BUPT)*; Wanli Ni (Beijing University of Posts and Telecommunications); Hui Tian (Beijing
university of posts and telecommunications); Yonina Eldar ()

1937: Scaling Law Analysis for Covariance Based Activity Detection in Cooperative Multi-Cell
Massive MIMO
Ziyue Wang (Chinese Academy of Sciences)*; Ya-Feng Liu (Chinese Academy of Sciences); Zhaorui
Wang (The Chinese University of Hong Kong); Wei Yu (University of Toronto)

1960: A Causal Convolutional Approach for Packet Loss Concealment in Low Powered Devices
Steven Davy (Huawei)*; Niamh Belton (Science Foundation Ireland Centre for Research Training in
Machine Learning, University College Dublin); Joshua Tobin (Huawei); Owais Bin Zuber (Huawei); Liu
Dong (Huawei); Yuan Xuewen (Huawei)

2036: Transceiver Design for MIMO-DFRC Systems

Cai Wen (Northwest University)*; Timothy N. Davidson (McMaster University)

2115: ANTENNA IMPEDANCE ESTIMATION IN CORRELATED RAYLEIGH FADING CHANNELS

Shaohan Wu (MediaTek USA)*; Brian Hughes (North Carolina State University)

2312: Sparse Aggregation-Based Channel Estimation for Massive MIMO Systems With
Decentralized Baseband Processing
Yanqing Xu (The Chinese University of HongKong, Shenzhen)*; Enbin Song (Sichuan University);
Qingjiang Shi (Tongji University); Tsung-Hui Chang ("The Chinese University of Hong Kong,")

2413: Model-Free Online Learning for Waveform Optimization in Integrated Sensing and
Communications
Petteri Pulkkinen (Aalto University, Saab Finland Oy)*; Visa Koivunen (Aalto university)

2438: INVERSE REINFORCEMENT LEARNING WITH GRAPH NEURAL NETWORKS FOR IOT
RESOURCE ALLOCATION
Guangchen Wang (The University of Sydney)*; Peng Cheng (La Trobe University); Zhuo Chen (CSIRO);
Wei Xiang (La Trobe University); Branka Vucetic (University of Sydney); Yonghui Li (THE UNIVERSITY
OF SYDNEY)

2457: SCALABLE MULTI-TASK SEMANTIC COMMUNICATION SYSTEM WITH FEATURE

IMPORTANCE RANKING
Jiangjing Hu (Beijing University of Posts and Telecommunications)*; Fengyu WANG (Beijing University of
Posts and Telecommunications); Wenjun Xu (Beijing University of Posts and Telecommunications); Hui
Gao (Beijing University of Posts and Telecommunications); Ping Zhang ( Beijing University of Posts and
Telecommunications)

2949: COMPRESSIVE CHANNEL ESTIMATION FOR IRS-AIDED MILLIMETER-WAVE SYSTEMS VIA

TWO-STAGE LAMP NETWORK
Wen-Chiao Tsai (National Taiwan University)*; Chi-Wei Chen (National Taiwan University); An-Yeu (Andy)
Wu (National Taiwan University)

3004: Integrated Sensing and Full-Duplex Communication: Joint Transceiver Beamforming and
Power Allocation
Zhenyao He (Southeast University)*; Wei Xu (Southeast University); Hong Shen (Southeast University);
Derrick Wing Kwan Ng (University of New South Wales); Yonina C. Eldar (Weizmann Institute of
Science); Xiaohu You (Southeast University)

164
3025: Regularized Neural Detection for Millimeter Wave Massive MIMO Communication Systems
with One-bit ADCs
Aditya Sant ("University of California, San Diego")*; Bhaskar Rao (UC San Diego)

3048: ON THE JOINT ESTIMATION OF PHASE NOISE AND TIME-VARYING CHANNELS FOR OFDM
UNDER HIGH-MOBILITY CONDITIONS
Francesco Linsalata (Politecnico di Milano )*; Nassar Ksairi (Huawei Technologies France)

3148: COMPARING DECENTRALIZED GRADIENT DESCENT APPROACHES AND GUARANTEES

Shana Moothedath (Iowa State University)*; Namrata Vaswani (Iowa State University)

3158: Anomaly Detection in Optical Spectra via Joint Optimization

Antonino M Rizzo (Politecnico di Milano)*; Luca Magri (Politecnico di Milano); Pietro Invernizzi (Cisco
Photonics); Enrico Sozio (Cisco Photonics); Stefano Piciaccia (Cisco Photonics); Alberto Tanzi (Cisco
Photonics); Stefano Binetti (Cisco Photonics); Cesare Alippi (Università della Svizzera Italiana); Giacomo
Boracchi (Politecnico di Milano)

3282: EXPECTATION PROPAGATION ON FACTOR GRAPHS BASED ON MATRIX DECOMPOSITION

Adam Mekhiche (Thales)*; Antonio Maria Cipriano (Thales); Charly Poulliat (IRIT/INPT)

3506: ITERATIVE WATER-FILLING POWER AND SUBCARRIER ALLOCATION FOR MULTICARRIER

NOMA DOWNLINK
Chin Choy Chai (Toronto Metropolitan University (formerly Ryerson University))*; Xiao-Ping Steven Zhang
(Ryerson University)

3534: A Novel Extrapolation Technique to Accelerate WMMSE

Kaiwen Zhou (The Chinese University of Hong Kong); Zhilin Chen (Huawei Noah's Ark Lab)*; Guochen
Liu (Huawei); Zhitang Chen (Huawei Noah’s Ark Lab)

3612: Boosting Signal Modulation Few-Shot Learning with Pre-transformation

peng sun (Zhejiang University of Technology); Jie Su (Newcastle University); Zhenyu Wen (Zhejiang
University of Technology)*; Yejian Zhou (Zhejiang University of Technology); Zhen Hong (Zhejiang
University of Technology); Shanqing Yu (Zhejiang University of Technology); Huaji Zhou (Xidian
University)

3775: Bit Error and Block Error Rate Training for ML-Assisted Communication
Reinhard Wiesmayr (ETH Zurich)*; Gian Marti (ETH Zurich); Chris Dick (NVIDIA); Haochuan Song
(Southeast University); Christoph Studer (ETH Zurich)

3878: Frequency-Selective Hybrid Beamforming for mmWave Full-Duplex

Andrea Guamo-Morocho (atlanTTic Research Center, Universidade de Vigo); Roberto Lopez-Valcarce
(atlanTTic Research Center, Universidade de Vigo)*

3944: Delay-aware Backpressure Routing Using Graph Neural Networks

Zhongyuan Zhao (Rice University)*; Bojan Radojicic (University of Novi Sad); Gunjan Verma (US Army’s
DEVCOM Army Research Laboratory); Ananthram Swami (ARL); Santiago Segarra (Rice University)

3952: Structural Optimization of Factor Graphs for Symbol Detection via Continuous Clustering
and Machine Learning
Lukas Rapp (Communications Engineering Lab, Karlsruhe Institute of Technology (KIT))*; Luca Schmid
(Communications Engineering Lab, Karlsruhe Institute of Technology (KIT)); Andrej Rode
(Communications Engineering Lab, Karlsruhe Institute of Technology (KIT)); Laurent Schmalen
(Communications Engineering Lab, Karlsruhe Institute of Technology (KIT))

165
3955: Codes Correcting Burst and Arbitrary Erasures for Reliable and Low-Latency
Communication
Serge Kas Hanna (Aalto)*; Zhiyuan Tan (Huawei); Wen Xu (Huawei); Antonia Wachter-Zeh (TUM)

3960: Capacity Maximization for Active RIS Assisted Outdoor-to-Indoor Communication System
Chen He (Northwest University); GONG WEISHENG (Northwest University); Yangrui Dong (Northwest
University); Xie Xie (Northwest University)*; Z. Jane Wang (University of British Columbia)

3979: Joint Microstrip Selection and Beamforming Design for MmWave Systems with Dynamic
Metasurface Antennas
Wei Huang (Hefei University of Technology)*; Haiyang Zhang (Nanjing University of Posts and
Telecommunications); Nir Shlezinger (Ben-Gurion University); Yonina Eldar ()

4084: Misspecified Cramér-Rao Bound of RIS-aided Localization under Geometry Mismatch

Pinjun Zheng (King Abdullah University of Science and Technology)*; Hui Chen (Chalmers University of
Technology); Tarig Ballal (KAUST); Henk Wymeersch (Chalmers University of Technology); Tareq Al-
NAffouri (CEMSE, KAUST)

4297: Distributed Signal Processing for Out-of-System Interference Suppression in Cell-Free

Massive MIMO
Zakir Hussain Shaik (Linköping University)*; Erik G. Larsson (Nil)

4317: Radio Map based UAV Target Localization

Chen He (Northwest University); GONG WEISHENG (Northwest University); Yangrui Dong (Northwest
University)*; Xie Xie (Northwest University); Z. Jane Wang (University of British Columbia)

4320: Joint Estimation of Clustered User Activity and Correlated Channels with Unknown
Covariance in mMTC
Hamza Djelouat (University of Oulu)*; Markus Leinonen (University of Oulu); Markku Juntti (OULU,
Finland)

4343: RADIO SENSING WITH LARGE INTELLIGENT SURFACE FOR 6G

Cristian J Vaca Rubio (Aalborg University)*; Pablo Ramirez Espinosa (University of Granada); Kimmo
Kansanen (Norwegian University of Science and Technology); Zheng-Hua Tan (Aalborg University);
Elisabeth de Carvalho (Aalborg University)

4374: Information and Sensing Beamforming Optimization for Multi-User Multi-Target MIMO ISAC
Systems
Minghe Zhu (The Chinese University of Hong Kong, Shenzhen); Lei Li (CUHK-Shenzhen); Shuqiang Xia
(ZTE Corporation); Tsung-Hui Chang ("The Chinese University of Hong Kong,")*

4424: DEEP UNFOLDING-ENABLED HYBRID BEAMFORMING DESIGN FOR MMWAVE MASSIVE

MIMO SYSTEMS
Nhan Nguyen (University of Oulu (UOULU))*; Mengyuan Ma (University of Oulu); Nir Shlezinger (Ben-
Gurion University); Yonina Eldar (); Lee Swindlehurst (University of California at Irvine); Markku Juntti
(OULU, Finland)

4497: Joint Channel and Direction Estimation for Ground-to-UAV Communications Enabled by A
Simultaneous Reflecting and Sensing RIS
Jiguang He (Technology Innovation Institute, 9639 Masdar City, Abu Dhabi)*; Aymen Fakhreddine
(Technology Innovation Institute); George Alexandropoulos (National and Kapodistrian University of
Athens)

4596: DEEP-UNFOLDED ADAPTIVE PROJECTED SUBGRADIENT METHOD FOR MIMO DETECTION

Jochen Fink (Fraunhofer HHI)*; Renato Luis Garrido Cavalcante (Fraunhofer Heinrich Hertz Inst); Zoran
Utkovski (Fraunhofer Heinrich hertz Institute); Slawomir Stanczak (Fraunhofer HHI)

166
4635: Sparse Bayesian Learning Assisted Decision Fusion in Millimeter Wave Massive MIMO
Sensor Networks
Apoorva Chawla (Norwegian University of Science and Technology)*; Domenico Ciuonzo (University of
Naples Federico II); Pierluigi Salvo Rossi (NTNU)

4664: Variational Inference Aided Estimation of Time Varying Channels

Benedikt Böck (Technische Universität München)*; Michael Baur (Technische Universität München);
Valentina Rizzello (Technische Universität München); Wolfgang Utschick (Technische Universität
München)

4691: Accelerated massive MIMO detector based on annealed underdamped Langevin dynamics
Nicolas M Zilberstein (Rice University)*; Chris Dick (Nvidia); Rahman Doost-Mohammady (Rice
University); Ashutosh Sabharwal (Rice University); Santiago Segarra (Rice University)

4697: Robust Angle Estimation for Hybrid mmWave Systems

Yuan-Pei Lin (National Yang Ming Chiao Tung University)*; Ting-Ming Yang (MediaTek inc.)

4734: Reducing the communication and computational cost of random Fourier features Kernel
LMS in diffusion networks
Daniel G Tiglea (Universidade de Sao Paulo)*; Renato Candido (Universidade de São Paulo); Luis
Antonio Azpicueta-Ruiz (Universidad Carlos III de Madrid); Magno T.M. Silva (University of Sao Paulo)

4812: Wireless Power Transfer using Chirp Waveforms

Arijit Roy (University of Cyprus); Constantinos Psomas (University of Cyprus)*; Ioannis Krikidis
(University of Cyprus)

4817: Machine Learning-Aided Piece-wise Modeling Technique of Power Amplifier for Digital
Predistortion
Sri Satish Krishna Chaitanya Bulusu (University of Oulu)*; Nuutti Tervo (University of Oulu); Praneeth
Susarla (University of Oulu); Mikko Sillanpää (University of Oulu); Olli Silven (University of Oulu); Markku
Juntti (OULU, Finland); Aarno Pärssinen (University of Oulu)

4825: Received Power Maximization with Practical Phase-dependent Amplitude Response in RIS-
Aided OFDM Wireless Communications
Dimitris Kompostiotis (University Of Patras )*; Dimitris Vordonis (University of Patras); Vassilis Paliouras
(University of Patras)

4878: DISTRIBUTED GAUSSIAN PROCESS HYPERPARAMETER OPTIMIZATION FOR MULTI-

AGENT SYSTEMS
Peiyuan Zhai (Delft University of Technology)*; Raj Thilak Rajan (Delft university of technology)

4899: Multicast Beamformer Design for MIMO Coded Caching Systems

MohammadJavad Salehi (University of Oulu)*; Mohammad NaseriTehrani (University of Oulu); Antti Tölli
(University of Oulu)

4926: ViT-CAT: Parallel Vision Transformers with Cross Attention Fusion for Popularity Prediction
in MEC Networks
Zohreh HajiAkhondi-Meybodi (Concordia University); Arash Mohammadi (Concordia University)*; Ming
Hou (Defence Research and Development Canada (DRDC)); Jamshid Abouei (Yazd University);
Konstantinos N Plataniotis (UofT)

5029: Model-Free Learning of Optimal Beamformers for Passive IRS-Assisted Sumrate

Maximization
Hassaan Hashmi (Yale University)*; Spyridon Pougkakiotis (Yale University); Dionysios Kalogerias (Yale
University)

167
5155: Comparative Study of IRS Assisted Opportunistic Communications Over i.i.d. and LoS
Channels
L Yashvanth (Indian Institute of Science, Bangalore)*; Chandra Murthy (Indian Institute of Science)

5166: Deep Spectrum Cartography Using Quantized Measurements

Subash Timilsina (Oregon State University); Sagar Shrestha (Oregon State University); Xiao Fu (Oregon
State University)*

5174: TDMA-Based Multi-User Binary Computation Offloading in the Finite-Block-Length Regime

Mohammad Amin Manouchehrpour (McMaster University)*; Harvinder Lehal (McMaster University);
Mahsa Salmani (McMaster University); Timothy N Davidson (McMaster University)

5199: Towards Efficient and Optimal Joint Beamforming and Antenna Selection: A Machine
Learning Approach
Sagar Shrestha (Oregon State University)*; Xiao Fu (Oregon State University); Mingyi Hong (University of
Minnesota)

5212: Managing Information Updating with Edge Computing: A Distributed and Learning Approach
Junyi He (Beijing Jiaotong University)*; Di Zhang (Beijing Jiaotong University); Shumeng Liu (Beijing
Jiaotong University ); Yuezhi Zhou (Tsinghua University); Yaoxue Zhang (Tsinghua University)

5341: WHEN IS MIMO MASSIVE IN RADAR?

Jaimin Shah (University of Minnesota, Twin-cities)*; Martina Cardone (University of Minnesota, Twin
Cities); Alex R Dytso (New Jersey Institute of Technology); Cynthia Rush (Columbia University)

5345: Multiple Access Computation Offloading for the K-user Case

Xiaomeng Liu (Mcmaster University)*; Christian Schaible (Mcmaster University); Timothy N Davidson
(McMaster University)

5505: Channel Estimation with Tightly-Coupled Antenna Arrays

Bamelak H Tadele (University of Manitoba)*; Volodymyr Shyianov (University of Manitoba); Faouzi Bellili
(University of Manitoba); Amine Mezghani (University of Manitoba)

5577: Sparse Delay-Doppler Channel Estimation for OTFS Modulation using 2D-MUSIC
Akshay S Bondre (Arizona State University)*; Christ Richmond (Duke University); Ahmed Alkhateeb
(Arizona State University); Nicolo Michelusi (Arizona State University)

5634: Learning to Regularized Resource Allocation with Budget Constraints

Shaoke Fang (Peking University)*; Qingsong Liu (Tsinghua University); Lei Xu (University of Southern
California); Wenfei Wu (Peking University)

6018: Joint Millimeter-Wave AoD and AoA Estimation Using One OFDM Symbol and Frequency-
Dependent Beams
Veljko Boljanovic (University of California, Los Angeles)*; Danijela Cabric (University of California, Los
Angeles)

6150: WITT: A Wireless Image Transmission Transformer For Semantic Communications

Ke Yang (Beijing University of Posts and Telecommunications); Sixian Wang (Beijing University of Posts
and Telecommunications); Jincheng Dai (Beijing University of Posts and Telecommunications)*; Kailin
Tan (Beijing University of Posts and Telecommunications); kai niu (Beijing University of Posts and
Telecommunications); Ping Zhang ( Beijing University of Posts and Telecommunications)

6327: Enhancing the Efficiency of WMMSE and FP for Beamforming by Minorization-Maximization

Zepeng Zhang (ShanghaiTech University)*; Ziping Zhao (ShanghaiTech University); Kaiming Shen (The
Chinese University of Hong Kong, Shenzhen)

168
 Signal Processing Theory and Methods

315: IQGAN: Robust Quantum Generative Adversarial Network for Image Synthesis On NISQ
Devices
Cheng Chu (Indiana University Bloomington); Grant Skipper (Indiana University Bloomington); Martin
Swany (Indiana University Bloomington); Fan Chen (Indiana University Bloomington)*

581: Distributed Bayesian Tracking on the Special Euclidean Group using Lie Algebra Parametric
Approximations
CLAUDIO JOSE BORDIN JUNIOR (Universidade Federal do ABC)*; CAIO DE FIGUEREDO (INSTITUTO
FEDERAL DO CEARA); Marcelo G S Bruno (ITA)

592: Pooling Strategies for Simplicial Convolutional Networks

Domenico Mattia Cinque (Sapienza University of Rome); Claudio Battiloro (Sapienza University of
Rome)*; Paolo Di Lorenzo (Sapienza University of Rome)

657: Passive detection of rank-one Gaussian signals for known channel subspaces and arbitrary
noise
David Ramírez (Universidad Carlos III de Madrid)*; Ignacio Santamaria (University of Cantabria); Louis
Scharf (University of Colorado)

965: SPACE-TIME VARIABLE DENSITY SAMPLINGS FOR SPARSE BANDLIMITED GRAPH

SIGNALS DRIVEN BY DIFFUSION OPERATORS
Qing Yao (UCSB); Longxiu Huang (Michigan State University); Sui Tang (UCSB)*

980: Sparsity-Smoothness-Aware Power Spectral Density Estimation with Application to Phased

Array Weather Radar
Hiroki Kuroda (Nagaoka University of Technology)*; Daichi Kitahara (Osaka University); Eiichi Yoshikawa
(Japan Aerospace Exploration Agency); Hiroshi Kikuchi (The University of Electro-Communications);
Tomoo Ushio (Osaka University)

995: Sparse representations with cone atoms

Denis C Ilie-Ablachim (University Politehnica of Bucharest); Andra Băltoiu (University Politehnica of
Bucharest); Bogdan Dumitrescu (University Politehnica of Bucharest)*

1006: ROBUST MULTI-OBJECT TRACKING WITH SPATIAL UNCERTAINTY

Pin-Jie Liao (National Tsing Hua university)*; Yu-Cheng Huang (National Tsing Hua University); Chen-Kuo
Chiang (National Chung Cheng University); Shang-Hong Lai (National Tsing Hua University)

1008: COMPRESSED DISTRIBUTED REGRESSION OVER ADAPTIVE NETWORKS

Marco Carpentiero (University of Salerno)*; Vincenzo Matta (DIEM, University of Salerno); Ali H. Sayed
(Ecole Polytechnique Fédérale de Lausanne)

1009: THE ROLE OF MEMORY IN SOCIAL LEARNING WHEN SHARING PARTIAL OPINIONS
Michele Cirillo (University of Salerno)*; Virginia Bordignon (EPFL); Vincenzo Matta (DIEM, University of
Salerno); Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)

1028: Learning graph Laplacian from intrinsic patterns via Gaussian process
Koshi Watanabe (Hokkaido University)*; Keisuke Maeda (Hokkaido University); Takahiro Ogawa
(Hokkaido University); Miki Haseyama (Hokkaido University)

1045: Adaptive Axonal Delays in feedforward spiking neural networks for accurate spoken word
recognition
Pengfei SUN (Ghent University)*; Ehsan Eqlimi (Ghent University); Yansong Chua (China Nanhu
Academy of Electronics and Information Technology); Paul Devos (Ghent University); Dick Botteldooren
(Ghent University)

169
1079: ENTROPY BASED FEATURE REGULARIZATION TO IMPROVE TRANSFERABILITY OF DEEP
LEARNING MODELS
Raphaël Baena (IMT Atlantique)*; Lucas Drumetz (IMT Atlantique); Vincent Gripon (IMT Atlantique)

1143: Identifying Opinion Influencers over Social Networks

Valentina Shumovskaia (Ecole Polytechnique Fédérale de Lausanne)*; Mert Kayaalp (Ecole
Polytechnique Fédérale de Lausanne); Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)

1182: High-Dynamic Range ADC for Finite-Rate-of-Innovation Signals

Satish Mulleti (Indian Institute of Technology Bombay, India)*; Yonina Eldar ()

1224: A Compensated Shrinkage Affine Projection Algorithm for Debiased Sparse Adaptive
Filtering
Yi Zhang (Tokyo Institute of Technology)*; Isao Yamada (Tokyo Institute of Technology)

1284: GaPP: Multi-Target Tracking with Gaussian Processes

Alexander F Goodyer (University of Cambridge )*; Bashar I. Ahmad (University of Cambridge); Simon
Godsill (Department of Engineering, University of Cambridge)

1324: A Robust Kalman Filter Based Approach for Indoor Robot Positionning with Multi-Path
Contaminated UWB Data
Justin Cano (ISAE-Supaéro)*; Yi Ding (ISAE-Supaéro); Gaël Pagès (ISAE-Supaéro); Eric Chaumette
(ISAE-Supaero); Jerome Le Ny (Polytechnique Montreal)

1333: Sparse Graph Learning with Spectrum Prior for Deep Graph Convolutional Networks
Jin Zeng (Tongji University)*; Yang Liu (Peking University); Gene Cheung (York University); Wei Hu
(Peking University)

1352: Asynchronous Social Learning

Mert Cemri (Bilkent University)*; Virginia Bordignon (EPFL); Mert Kayaalp (Ecole Polytechnique Fédérale
de Lausanne); Valentina Shumovskaia (Ecole Polytechnique Fédérale de Lausanne ); Ali H. Sayed
(Ecole Polytechnique Fédérale de Lausanne)

1396: ASYMPTOTIC BIAS AND VARIANCE OF KERNEL RIDGE REGRESSION

Victor Solo (University of New South Wales)*

1466: COMBINING DUAL-TREE WAVELET ANALYSIS AND PROXIMAL OPTIMIZATION FOR

ANISOTROPIC SCALEFREE TEXTURE SEGMENTATION
Leo Davy (ENS Lyon)*; Nelly Pustelnik (); Patrice Abry (CNRS, Physics Department, Ecole Normale
Supérieure de Lyon)

1502: CyPMLI: WISL-Minimized Unimodular Sequence Design via Power Method-Like Iterations
Arian Eamaz (University of Illinois - Chicago, IL)*; Farhang Yeganegi (University of Illinois Chicago);
Mojtaba Soltanalian (University of Illinois)

1511: Fast convolution algorithm for Real valued finite length sequences
Weiwei Wang (FSU)*; Victor DeBrunner (FSU); Linda DeBrunner (FSU)

1619: Estimating Inharmonic Signals with Optimal Transport Priors

Filip Elvander (Aalto University)*

1631: MÖBIUS TOTAL VARIATION FOR DIRECTED ACYCLIC GRAPHS

Vedran Mihal (ETH Zurich)*; Markus Püschel (ETH Zurich)

170
1660: Multilevel FISTA for Image Restoration
Guillaume Lauga (Inria/ENS Lyon)*; Elisa Riccietti (ENS Lyon); Nelly Pustelnik (); Paulo Goncalves (ENS
de Lyon)

1761: Dynamic Selection of p-Norm in Linear Adaptive Filtering via Online Kernel-Based
Reinforcement Learning
Minh Vu (Tokyo Institute of Technology); Yuki Akiyama (Tokyo Institute of Technology); Konstantinos
Slavakis (Tokyo Institute of Technology)*

1806: Adaptive Filtering Algorithms for Set-Valued Observations--Symmetric Measurement

Approach to Unlabeled and Anonymized Data
Vikram Krishnamurthy (Cornell University)*

1836: MAKING SYNCHROSQUEEZING LOCALLY ADAPTIVE IN THE TIME-FREQUENCY PLANE

Marcelo A Colominas (CONICET)*; Sylvain Meignen (University Grenoble Alpes)

1869: Distributed Online Learning with Adversarial Participants in An Adversarial Environment

XingRong Dong (Sun Yat-Sen University); Zhaoxian Wu (Sun Yat-Sen University); Qing Ling (Sun Yat-
Sen University)*; Zhi Tian (George Mason University)

1914: Online Residual-Based Key Frame Sampling with Self-Coach Mechanism and Adaptive
Multi-Level Feature Fusion
Rui Zhang (Shanghai Jiao Tong University); Yang Hua (Queen's University Belfast); Tao Song (Shanghai
Jiao Tong University); Zhengui Xue (Shanghai Jiao Tong University); Ruhui Ma (Shanghai Jiao Tong
University)*; Haibing Guan (Shanghai Jiao Tong University)

1940: Blind Polynomial Regression

Alberto Natali (Delft University of Technology)*; Geert Leus (TU Delft)

1956: Byzantine-Robust and Communication-Efficient Personalized Federated Learning

Xuechao He (Sun Yat-sen University)*; Jiaojiao Zhang (The Chinese University of Hong Kong); Qing Ling
(Sun Yat-Sen University)

2120: Large Covariance Matrix Estimation With Oracle Statistical Rate

Quan Wei (ShanghaiTech University)*; Ziping Zhao (ShanghaiTech University)

2211: Robust GMM parameter estimation via the K-BM algorithm

Ori Kenig (Ben Gurion University of The Negev)*; Koby Todros (Ben-Gurion University of the Negev);
Tulay Adali (University of Maryland, Baltimore County)

2218: Convergence of Stochastic PDMM

Sebastian Jordan (TU Delft); Thomas Sherson (Delft University of Technology); Richard Heusdens
(Netherlands Defence Academy)*

2380: ON TRACKING A STOCHASTICALLY TIME-VARYING SUBSPACE

Victor Solo (University of New South Wales)*

2389: False alarm regulation for off-grid target detection with the Matched Filter
Pierre Develter (ONERA; SONDRA, CentraleSupélec, Université Paris-Saclay)*; Jonathan Bosse
(ONERA); Olivier Rabaste (ONERA); Philippe Forster (ENS Paris-Saclay, CNRS, Université Paris-
Saclay); Jean-Philippe Ovarlez (ONERA; SONDRA, CentraleSupélec, Université Paris-Saclay)

2401: Optimized Dithering for Quantization Index Modulation

Shanxiang Lyu ()*

171
2415: GRAPH LEARNING FROM GAUSSIAN AND STATIONARY GRAPH SIGNALS
Andrei Buciulea Vlas (Universidad Rey Juan Carlos); Antonio G. Marques (King Juan Carlos University)*

2492: Meta-DAG: Meta Causal Discovery via Bilevel Optimization

Songtao Lu (IBM Thomas J. Watson Research Center)*; Tian Gao (IBM Research)

2511: Neural Network Models with Integrated Training and Adaptation for Nonlinear Acoustic
System Identification
Svantje Voit (Carl von Ossietzky University of Oldenburg)*; Gerald Enzner (Carl von Ossietzky University
Oldenburg)

2536: Data-Driven Quickest Change Detection in Markov Models

Qi Zhang (University at Buffalo); Zhongchang Sun (University at Buffalo, the State University of New
York); Luis Herrera (University at Buffalo); Shaofeng Zou (University at Buffalo, the State University of
New York)*

2556: Windowed Fourier Analysis for Signal Processing on Graph Bundles

T. Mitchell Roddenberry (Rice University)*; Santiago Segarra (Rice University)

2564: Column-based matrix approximation with quasi-polynomial structure

Jeongmin Chae (University of Southern California)*; Praneeth Narayanamurthy (University of Southern
California); Selin Bac (University of Southern California); Shaama Mallikarjun Sharada (University of
Southern California); Urbashi Mitra (USC)

2592: A New Probabilistic Distance Metric with Application in Gaussian Mixture Reduction
Ahmad Sajedi (University of Toronto)*; Yuri Lawryshyn (University of Toronto); Konstantinos N Plataniotis
(UofT)

2600: Cramér-Rao bound on Lie groups with observations on Lie groups: application to $SE(2)$
Samy LABSIR (IPSA)*; Alexandre Renaux (Université Paris Saclay); Jordi Vilà-Valls (ISAE-SUPAERO);
Eric Chaumette (ISAE-SUPAERO)

2611: Various Performance Bounds on the Estimation of Low-Rank Probability Mass Function
Tensors from Partial Observations
Tomer Hershkovitz (Tel Aviv University); Martin Haardt (Ilmenau University of Technology); Arie Yeredor
(Tel Aviv University)*

2663: INTERPOLATION FILTER MODEL FOR RAMANUJAN SUBSPACE SIGNALS

Pranav D Kulkarni (California Institute of Technology)*; Dr.P P Vaidyanathan (California Institute of
Technology)

2667: WIENER FILTERING WITHOUT COVARIANCE MATRIX INVERSION

Pranav U Damale (Colorado State University)*; Edwin Chong (Colorado State University); Louis Scharf
(Colorado State University)

2792: Efficient Data Loading with Quantum Autoencoder

Siang-Ruei Wu (National Taiwan University); Chun-Tse Li (National Taiwan University); Hao-Chung
Cheng (National Taiwan University)*

2822: Performance of Social Machine Learning under Limited Data

Ping Hu (EPFL)*; Virginia Bordignon (EPFL); Mert Kayaalp (Ecole Polytechnique Fédérale de Lausanne);
Ali H. Sayed (Ecole Polytechnique Fédérale de Lausanne)

172
2908: REGRESSION TO CLASSIFICATION: WAVEFORM ENCODING FOR NEURAL FIELD-BASED
AUDIO SIGNAL REPRESENTATION
TaeSoo Kim (KT Corporation)*; Daniel Rho (KT Corporation); GaHui Lee (KT Corporation); JaeHan Park
(KT Corporation); Jong Hwan Ko (Sungkyunkwan University)

2947: Central nodes detection from partially observed graph signals

Yiran HE (The Chinese University of Hong Kong)*; Hoi-To Wai (Chinese University of Hong Kong)

3008: SPECTRAL SUPER-RESOLUTION ON THE UNIT CIRCLE VIA GRADIENT DESCENT

Xunmeng Wu (Xi’an Jiaotong University)*; Zai Yang (Xi’an Jiaotong University); Jian-Feng Cai (The Hong
Kong University of Science and Technology); Zongben Xu (XJTU)

3027: Smoothing complex-valued signals on Graphs with Monte-Carlo

Hugo Jaquard (GIPSA-lab)*; Michaël Fanuel (CRIStAL); Pierre-Olivier Amblard ("CNRS, Grenoble");
Rémi Bardenet (CRIStAL); Simon Barthelmé (CNRS); Nicolas Tremblay (CNRS)

3051: A NOVEL APPROACH BASED ON VORONO ̈I CELLS TO CLASSIFY SPECTROGRAM ZEROS

OF MULTICOMPONENT SIGNALS
Nils Laurent (University Grenoble Alpes); Sylvain Meignen (University Grenoble Alpes)*; Marcelo A
Colominas (CONICET); Juan M Miramont Taurel (Instituto de Investigación y Desarrollo en Bioingeniería
y Bioinformática (UNER-CONICET)); Francois Auger (Université de Nantes - Laboratoire IREENA)

3107: ROBUST AND GLOBALLY SPARSE PCA VIA MAJORIZATION-MINIMIZATION AND VARIABLE
SPLITTING
Hugo Brehier (SONDRA, CentraleSupélec)*; Arnaud Breloy (Université Paris Nanterre); Mohammed
Nabil EL KORSO (Paris Nanterre University); Sandeep Prof. Kumar (IIT Delhi)

3330: Learned Generative Misspecified Lower Bound

Hai Victor Habi (Tel Aviv University)*; Hagit Messer (Tel Aviv University); Yoram Bresler (UIUC)

3510: Quickest Change Detection with Leave-one-out Density Estimation

Yuchen Liang (UIUC); Venugopal V. Veeravalli (University of Illinois at Urbana Champaign)*

3538: Possibilistic Bernoulli Filter for Extended Target Tracking

Zhijin Chen (RMIT University); Branko Ristic (RMIT University)*; Du Yong Kim (RMIT University)

3569: Eigen-Decomposition-Free Directed Graph Sampling via Gershgorin Disc Alignment

Yuejiang Li (Tsinghua University)*; H. Vicky Zhao (Tsinghua University); Gene Cheung (York University)

3738: ACHIEVABLE ERROR EXPONENTS FOR ALMOST FIXED-LENGTH M-ARY HYPOTHESIS

TESTING
jun diao (北京航空航天大学)*; lin zhou (Beihang University); Lin Bai (BUAA)

3808: Product Graph Learning from Multi-attribute Graph Signals with Inter-layer Coupling
Chenyue Zhang (The Chinese University of Hong Kong)*; Yiran HE (The Chinese University of Hong
Kong); Hoi-To Wai (Chinese University of Hong Kong)

3839: Adaptive Simulated Annealing through Alternating Rényi Divergence Minimization

Thomas Guilmeau (Université Paris-Saclay, CentraleSupélec, Inria, CVN)*; Emilie Chouzenoux (Inria
Saclay); Victor Elvira (University of Edinburgh)

3895: NEURAL MODE ESTIMATION

peng sun (Zhejiang University of Technology); Zhenyu Wen (Zhejiang University of Technology)*; Yejian
Zhou (Zhejiang University of Technology); Zhen Hong (Zhejiang University of Technology); Tao Lin
(Westlake University)

173
3924: Adaptive Gaussian nested filter for parameter estimation and state tracking in dynamical
systems
Sara Pérez-Vieites (IMT Nord Europe)*; Victor Elvira (University of Edinburgh)

4000: Sparse asynchronous samples from networks of TEMS for reconstruction of classes of non-
bandlimited signals
Marek Hilton (Imperial College London)*; Pier Luigi Dragotti (Imperial College London)

4029: Revisit Sampling Theory of Bandlimited Graph Signals: One Bridge Between GSP and DSP
Fen Wang (Zhejiang Lab)*; Taihao Li (zhejianglab); Xue Zhang (Shandong University of Science and
Technology)

4054: Learning Hypergraphs From Signals With Dual Smoothness Prior

Bohan Tang (University of Oxford)*; Siheng Chen (Shanghai Jiao Tong University, Shanghai AI
Laboratory); Xiaowen Dong (University of Oxford)

4101: Multichannel Time-Encoding of Finite-Rate-of-Innovation Signals

Abijith Jagannath Kamath (Indian Institute of Science)*; Chandra Sekhar Seelamantula (IISc Bangalore)

4249: Topological Slepians: Maximally Localized Representations of Signals over Simplicial

Complexes
Claudio Battiloro (Sapienza University of Rome)*; Paolo Di Lorenzo (Sapienza University of Rome);
Sergio Barbarossa (Sapienza University of Rome)

4266: On Parametric Misspecified Bayesian Cramér–Rao bound: An application to linear/Gaussian

systems
Shuo Tang (Northeastern University)*; Gerald LaMountain (Northeastern University); Tales Imbiriba
(Northeastern University); Pau Closas (Northeastern University)

4405: Polarized signal singular spectrum analysis with complex SSA

Sébastien Journé (Univ. Grenoble Alpes,CNRS,Grenoble INP, GIPSA-lab, 38000 Grenoble France)*;
Nicolas Le Bihan (Gipsa-lab/CNRS); Florent Chatelain (Gipsa-lab); Julien Flamant (Université de
Lorraine, CNRS, CRAN, F-54000 Nancy, France)

4570: Simplicial Vector Autoregressive Model for Streaming Edge Flows

Joshin P. Krishnan (Simula Metropolitan Center for Digital Engineering)*; Rohan Money (UiA); Baltasar
Beferull-Lozano (University of Agder); Elvin Isufi (Tu Delft)

4581: Deep Unfolded Tensor Robust PCA with Self-supervised Learning

Harry Dong (Carnegie Mellon University)*; Megna Shah (Air Force Research Laboratory); Sean Donegan
(Air Force Research Laboratory); Yuejie Chi (Carnegie Mellon University)

4585: Dynamic Distributed Convex Optimization "Over-the-Air" in Decentralized Wireless

Networks
Navneet Agrawal (TU Berlin)*; Renato Luis Garrido Cavalcante (Fraunhofer Heinrich Hertz Inst);
Slawomir Stanczak (TU Berlin)

4611: Radar Clutter Covariance Estimation: A Nonlinear Spectral Shrinkage Approach

Shashwat Jain (Cornell University)*; Vikram Krishnamurthy (Cornell University); Muralidhar Rangaswamy
(AFRL); Bosung Kang (University of Dayton Research Institute); Sandeep Gogineni (Information Systems
Laboratories Inc.)

4639: Elliptical Wishart distribution: maximum likelihood estimator from information geometry
Imen AYADI (université Paris Saclay)*; Florent Bouchard (L2S); Frédéric Pascal (CentraleSupélec)

174
4659: SPARSITY-DRIVEN JOINT BLIND DECONVOLUTION-DEMODULATION WITH APPLICATION
TO MOTOR FAULT DETECTION
Varun A Kelkar (University of Illinois at Urbana-Champaign); Dehong Liu (Mitsubishi Electric Research
Laboratories (MERL))*; Hiroshi Inoue (Mitsubishi Electric Corporation); Makoto Kanemaru (Mitsubishi
Electric Corporation)

4705: Bayesian Cramér-Rao Bound Estimation with Score-Based Models

Evan Scope Crafts (The University of Texas at Austin)*; Bo Zhao (University of Texas at Austin )

4746: Consistent estimators of a new class of covariance matrix distances in the large
dimensional regime
Roberto Pereira (Centre Tecnològic de Telecomunicacions de Catalunya); Xavier Mestre (Centre
Tecnològic de Telecomunicacions de Catalunya)*; David Gregoratti (SRS)

4750: Phase Unwrapping in Correlated Noise for FMCW Lidar Depth Estimation
Alfred Ulvog ( Mitusbishi Electric Research Laboratories); Joshua Rapp (Mitusbishi Electric Research
Laboratories)*; Toshiaki Koike-Akino (Mitsubishi Electric Research Laboratories); Hassan Mansour
(Mitsubishi Electric Research Laboratories (MERL)); Petros Boufounos (Mitsubishi Electric Research
Laboratories); Kieran Parsons (Mitsubishi Electric Research Laboratories)

4751: A Bayesian Perspective on Noise2Noise: Theory and Extensions

Sarah Miller (University of Dayton)*; Christina M Karam (Huddly); Achour Idoughi (University of Dayton);
Kodai Kikuchi (Japan broadcasting corporation); Keigo Hirakawa (University of Dayton)

4774: LASSO-BASED FAST RESIDUAL RECOVERY FOR MODULO SAMPLING

Shaik Basheeruddin Shah (Weizmann Institute of Science)*; Satish Mulleti (Indian Institute of Technology
Bombay, India); Yonina Eldar ()

4778: Identifying Coordination in a Cognitive Radar Network - A Multi-Objective Inverse

Reinforcement Learning Approach
Luke Snow (Cornell University)*; Vikram Krishnamurthy (Cornell University); Brian M Sadler (Army
Research Laboratory, USA)

4815: Improved Small Sample Hypothesis Testing using the Uncertain Likelihood Ratio
James Z Hare (DEVCOM Army Research Lab)*; Lance Kaplan (DEVCOM Army Research Laboratory)

4859: An Augmented Gaussian Sum Filter Through a Mixture Decomposition

Kostas Tsampourakis (University of Edinburgh)*; Victor Elvira (University of Edinburgh)

4875: On the primal and dual formulations of the Discrete Mumford-Shah functional
Nelly Pustelnik ()*

4880: Regularized EM algorithm

Pierre HOUDOUIN (CentraleSupélec)*; Esa Ollila (Aalto University); Frédéric Pascal (CentraleSupélec)

4892: Convolutional Filtering on Sampled Manifolds

Zhiyang Wang (University of Pennsylvania)*; Luana Ruiz (MIT CSAIL); Alejandro Ribeiro (University of
Pennsylvania)

4901: Tangent Bundle Filters and Neural Networks: from Manifolds to Cellular Sheaves and Back
Claudio Battiloro (Sapienza University of Rome)*; Zhiyang Wang (University of Pennsylvania); Hans
Riess (Duke University); Paolo Di Lorenzo (Sapienza University of Rome); Alejandro Ribeiro (University
of Pennsylvania)

175
4953: Estimating and Analyzing Neural Information Flow Using Signal Processing on Graphs
Felix Schwock (University of Washington)*; Julien Bloch (University of Washington); Les Atlas (University
of Washington); Shima Abadi (University of Washington ); Azadeh Yazdan-Shahmorad (University of
Washington)

4964: AN IMPLICIT GRADIENT METHOD FOR CONSTRAINED BILEVEL PROBLEMS USING

BARRIER APPROXIMATION
Ioannis Tsaknakis (University of Minnesota)*; Prashant Khanduri (Wayne State University); Mingyi Hong
(University of Minnesota)

5037: A Statistical Interpretation of the Maximum Subarray Problem

Dennis Wei (IBM Research)*; Dmitry M Malioutov (Scarsdale)

5070: Signal processing with optical quadratic random sketches

Remi AAV Delogne (Université catholique de Louvain)*; Vincent Schellekens (CEA); Laurent Daudet
(LightOn); Laurent Jacques (Université catholique de Louvain)

5077: Unique Bispectrum Inversion for Signals with Finite Spectral/Temporal Support
Samuel Pinilla (STFC)*; Kumar Vijay Mishra (United States DEVCOM Army Research Laboratory); Brian
M Sadler (Army Research Laboratory, USA)

5115: Discriminative Vector Learning with Application To Single Channel Speech Separation
Ha Minh Tan (National Central University); Kai-Wen Liang (Department of Communication Engineering,
National Central University); Jia-Ching Wang (National Central University)*

5127: HeMPPCAT: Mixtures of Probabilistic Principal Component Analysers for Data with
Heteroscedastic Noise
Alec Xu (University of Michigan)*; Laura Balzano (University of Michigan); Jeffrey A Fessler (University of
Michigan)

5165: Towards bandwidth estimation for graph signal reconstruction

Ajinkya Jayawant (University of Southern California)*; Antonio Ortega (University of Southern California)

5172: Robust Network Topologies for Distributed Learning

Chutian Wang (Imperial College London); Stefan Vlaski (Imperial College London)*

5175: Robustness and Convergence of Mirror Descent for Blind Deconvolution

Ronak Mehta (University of Wisconsin-Madison)*; Sathya Ravi (University of Illinois at Chicago); Vikas
Singh (University of Wisconsin Madison)

5176: Generalized Two-Stage Particle Filter for High Dimensions

Marija Iloska (Stony Brook University)*; Monica Bugallo (Stony Brook University)

5198: Unlimited Sampling in Phase Space

Peiyu Zhang (Imperial College London); Ayush Bhandari (Imperial College London)*

5300: An Online Algorithm for Contrastive Principal Component Analysis

Siavash Golkar (Flatiron Institute); David Lipshutz (Flatiron Institute)*; Tiberiu Tesileanu (Flatiron
Institute); Dmitri Chklovskii (Flatiron Institute)

5330: ITER-SIS: ROBUST UNLIMITED SAMPLING VIA ITERATIVE SIGNAL SIEVING

Ruiming Guo (Imperial College London); Ayush Bhandari (Imperial College London)*

5332: Higher-order Link Prediction via Learnable Maximum Mean Discrepancy

Georgios V. Karanikolas (University of Minnesota)*; Alba Pagès Zamora (Universitat Politecnica de
Catalunya); Georgios B. Giannakis (University of Minnesota)

176
5352: Adaptive ECCM for Mitigating Smart Jammers
Shashwat Jain (Cornell University)*; Kunal Pattanayak (Cornell University); Vikram Krishnamurthy
(Cornell University); Christopher Berry (Lockheed Martin Advanced Technology Labs)

5364: ENHANCING SPATIO-SPECTRAL REGULARIZATION BY STRUCTURE TENSOR MODELING

FOR HYPERSPECTRAL IMAGE DENOISING
Shingo Takemoto (Tokyo Institute of Technology)*; Shunsuke Ono (Tokyo Institute of Technology)

5373: Fast robust principle component analysis using Gauss-Newton iterations

William Chettleburgh (Michigan State University); Zhishen Huang (Amazon Inc.)*; Ming Yan (The Chinese
University of Hong Kong, SHenzhen)

5398: Low Precision Representations for High Dimensional Models

Rajarshi Saha (Stanford University)*; Mert Pilanci (Stanford University); Andrea Goldsmith (Princeton
University)

5548: SIGNAL PROCESSING AND QUANTUM STATE TOMOGRAPHY ON NOISY DEVICES

Wenbo Shi (The University of New South Wales)*; Robert Malaney (University of New South Wales)

5580: Kernel Ridge Regression for Generalized Graph Signal Processing

Xingchao Jian (School of Electrical and Electronic Engineering, Nanyang Technological University)*; Wee
Peng Tay (Nanyang Technological University)

5589: Restoration of Time-varying Graph Signals Using Deep Algorithm Unrolling

Hayate KOJIMA (Department of Electrical Engineering and Computer Science, Tokyo University of
Agriculture and Technology)*; Hikari Noguchi (Tokyo University of Agriculture and Technology); Koki
Yamada (Tokyo University of Science); Yuichi Tanaka (Osaka University)

5686: Particle Flow Gaussian Sum Particle Filter

Karthik Comandur (Signal Processing and Communication Research Centre, IIIT Hyderabad)*; Yunpeng
Li (University of Surrey); Santosh Nannuru (IIIT Hyderabad)

5765: BEYOND RATE CODING: SIGNAL CODING AND RECONSTRUCTION USING LEAN SPIKE
TRAINS
Anik Chattopadhyay (University of Florida)*; Arunava Banerjee (University of Florida)

5773: Second-Order Statistic Deviation to Model Anomalies in the Design of Unsupervised

Detectors
Andriy Enttsel (University of Bologna)*; Filippo Martinini (University of Bologna); Alex Marchioni
(University of Bologna); Mauro Mangia (University of Bologna); Riccardo Rovatti (University of Bologna);
Gianluca Setti (Politecnico di Torino)

5851: ROBUST HYPERSPECTRAL ANOMALY DETECTION WITH SIMULTANEOUS MIXED NOISE

REMOVAL VIA CONSTRAINED CONVEX OPTIMIZATION
Koyo Sato (Tokyo Institute of Technology)*; Shunsuke Ono (Tokyo Institute of Technology)

5912: Progressive Perception Learning for Distribution Modulation in Siamese Tracking

Kun Hu (National University of Defense Technology)*; Xianchen Zhou (National University of Defense
Technology ); Mingyu Cao (NUDT); Mengzhu Wang (NUDT); Guangjie Gao (NUDT); Wenjing Yang
(National University of Defense Technology); Huibin Tan (NUDT)

5938: SAMPLING ORDER-LIMITED SIGNALS ON THE SPHERE

Salaar Khan (LUMS)*; Salman Nadeem (Lahore University of Management Sciences); Zubair Khalid
(Lahore University of Management Sciences)

177
5951: SPATIAL INFERENCE USING CENSORED MULTIPLE TESTING WITH FDR CONTROL
Martin Gölz (Technische Universität Darmstadt)*; Abdelhak M Zoubir (Technische Universität Darmstadt);
Visa Koivunen (Aalto university)

6007: Element Selection with Wide Class of Optimization Criteria Using Non-convex Sparse
Optimization
Taiga Kawamura (Tokyo Metropolitan University)*; Natsuki Ueno (Tokyo Metropolitan University);
Nobutaka Ono (Tokyo Metropolitan University)

6057: Low-rank plus sparse trajectory decomposition for direct exoplanet imaging
Simon Vary (ICTEAM/INMA, UCLouvain)*; Hazan Daglayan (UCLouvain); Laurent Jacques (Université
catholique de Louvain); P.-A. Absil (UCLouvain)

6159: A SIMPLE SCHEME FOR COUPLED FACTORIZATION FOR HYPERSPECTRAL SUPER-

RESOLUTION: EXPLOITING SPARSITY IN AN EASY WAY
Yuening Li (The Chinese University of Hong Kong)*; Wing-Kin Ma (The Chinese University of Hong
Kong); Ruiyuan Wu (Meituan); Huikang Liu (Shanghai University of Finance and Economics)

6329: Efficient Learning of Balanced Signature Graphs

Gerald Matz (Technische Universität Wien)*; Claudio Verardo (University of Udine); Thomas Dittrich
(Technische Universität Wien)

6351: Robust M-Estimation based Distributed Expectation Maximization Algorithm with Robust
Aggregation
Christian A. Schroth (Technische Universität Darmstadt )*; Stefan Vlaski (Imperial College London);
Abdelhak M Zoubir (Technische Universität Darmstadt)

6378: Global Localisation in Continuous Magnetic Vector Fields Using Gaussian Processes
William T McDonald (University of Technology, Sydney)*; Cedric Le Gentil (University of Technology
Sydney); Teresa A. Vidal-Calleja (University of Technology Sydney)

6401: UNLIMITED SAMPLING OF FRI SIGNALS INDEPENDENT OF SAMPLING RATE

Ruiming Guo (Imperial College London); Ayush Bhandari (Imperial College London)*

6529: Differentiable adaptive short-time Fourier transform with respect to the window length
Maxime Leiber (INRIA)*; Yosra Marnissi (SAFRAN TECH); Axel Barrau (Offroad); Mohammed El Badaoui
(Safran Tech)

178
 Speech and Language Processing

108: Exploring complementary features in multi-modal speech emotion recognition

Suzhen Wang (Netease Fuxi AI Lab)*; Yifeng Ma (Tsinghua University); Yu Ding (Netease Fuxi AI Lab)

111: DST: DEFORMABLE SPEECH TRANSFORMER FOR EMOTION RECOGNITION

Weidong Chen (South China University of Technology)*; Xiaofen Xing ( South China University of
Technology); Xiangmin Xu (South China University of Technology); Jianxin Pang (Ubtech Robotics Corp.);
Lan Du (iFLYTEK Research)

112: Reducing the gap between streaming and non-streaming Transducer-based ASR models by
adaptive two-stage knowledge distillation
Haitao Tang (iFlytek Research)*; Yu Fu (Zhejiang University); Lei Sun (iFlytek Research); Jiabin Xue
(Harbin Institute of Technology); Dan Liu (iFLYTEK Co., LTD.,); Yongchao Li (iFlytek Research); Zhiqiang
Ma (iFlytek Research); Minghui Wu (iFlytek Research); Jia Pan (iFlytek Research); Genshun Wan (iFlytek
Research); Ming'en Zhao (iFlytek Research)

164: Alignment Entropy Regularization

Ehsan Variani (Google)*; Ke Wu (Google); David Rybach (Google); Cyril Allauzen (Google); Michael Riley
(Google)

179: UCONV-CONFORMER: HIGH REDUCTION OF INPUT SEQUENCE LENGTH FOR END-TO-END

SPEECH RECOGNITION
Andrei Andrusenko (ITMO University)*; Rauf Nasretdinov (STC); Aleksei Romanenko (STC-innovations
Ltd)

188: Heuristic Masking for Text Representation Pretraining

Yimeng Zhuang (Samsung Research China - Beijing (SRC-B))*

199: Learning ASR pathways: A sparse multilingual ASR model

Mu Yang (University of Texas at Dallas)*; Andros Tjandra (Meta Platforms, Inc); Chunxi Liu (Two Sigma);
David Zhang (Meta); Duc Le (Meta); Ozlem Kalinli (Meta)

209: Improving Contextual Spelling Correction by External Acoustics Attention and Semantic
Aware Data Augmentation
Xiaoqiang Wang (Microsoft)*; Yanqing Liu (Microsoft); Jinyu Li (Microsoft); sheng zhao (microsoft)

253: ACE-VC: Adaptive and Controllable Voice Conversion using Explicitly Disentangled Self-
supervised Speech Representations
Shehzeen S Hussain (UCSD)*; Paarth Neekhara (UCSD); Jocelyn Huang (NVIDIA); Jason Li (NVIDIA);
Boris Ginsburg (NVIDIA)

277: A Simple yet Effective Approach to Structured Knowledge Distillation

Wenye Lin (Tsinghua Shenzhen International Graduate School, Tsinghua University)*; Yangming Li
(Tencent AI Lab); Lemao Liu (Tencent AI Lab); Shuming Shi (Tsinghua University); Hai-Tao Zheng
(Tsinghua University)

298: Contrastive Learning at the Relation and Event Level for Rumor Detection
Yingrui Xu (Institute of Information Engineering, Chinese Academy of Sciences;School of Cyber Security,
University of Chinese Academy of Sciences); Jingyuan Hu (Institute of Information Engineering, Chinese
Academy of Sciences)*; jingguo ge (iie，cas); Yulei Wu (University Of Exeter); Hui Li (Institute of
Information Engineering, Chinese Academy of Sciences); Tong Li (Institute of Information Engineering,
Chinese Academy of Sciences)

179
303: Parameter Efficient Transfer Learning for Various Speech Processing Tasks
Shinta Otake (Tokyo Institute of Technology)*; Rei Kawakami (Tokyo Institute of Technology); Nakamasa
Inoue (Tokyo Institute of Technology)

381: CommDRE:Document-level Relation Extraction with Self-supervised Commonsense Learning

Rongzhen Li (Chongqing University)*; Jiang Zhong (); Zhongxuan Xue (Chongqing University); Qizhu Dai
(Chongqing University); Chen Wang (Chongqing University); Xue Li (University of Queensland)

390: Contrastive Learning of Functionality-aware Code Embedding

Yiyang Li (Shanghai Jiao Tong University)*

392: From English to More Languages: Parameter-Efficient Model Reprogramming for Cross-
Lingual Speech Recognition
Chao-Han Huck Yang (Georgia Institute of Technology )*; Bo Li (Google); Yu Zhang (Google); Nanxin
Chen (John Hopkins Universoty); Rohit Prabhavalkar (Google); Tara Sainath (Google); Trevor Strohman
(Google)

393: VarArray Meets t-SOT: Advancing the State of the Art of Streaming Distant Conversational
Speech Recognition
Naoyuki Kanda (Microsoft)*; Jian Wu (Microsoft); Xiaofei Wang (Microsoft); Zhuo Chen (Microsoft); Jinyu
Li (Microsoft); Takuya Yoshioka (Microsoft)

400: From Easy to Hard: Two-stage Selector and Reader for Multi-hop Question Answering
Xin-Yi Li (State Key Laboratory for Novel Software Technology, Nanjing University); Wei-Jun Lei (State
Key Laboratory for Novel Software Technology, Nanjing University); Yu-Bin Yang (State Key Laboratory
for Novel Software Technology, Nanjing University)*

401: Joint unsupervised and supervised learning for context-aware language identification
Jinseok Park (42dot)*; Hyung Yong Kim (42dot); Jihwan Park (42dot Inc.); Byeong-Yeol Kim (42dot);
Shukjae Choi (Hyundai Motor Company); Yunkyu Lim (42dot)

404: UNSUPERVISED PRE-TRAINING FOR DATA-EFFICIENT TEXT-TO-SPEECH ON LOW

RESOURCE LANGUAGES
Seongyeon Park (Seoul National University)*; Myungseo Song (CNAI); bohyung kim (CNAI); Tae-Hyun
Oh (POSTECH)

421: SPEECH EMOTION RECOGNITION BASED ON LOW-LEVEL AUTO-EXTRACTED TIME-

FREQUENCY FEATURES
Ke Liu (Northwest University)*; Jingzhao Hu (Northwest University); Jun Feng (Northwest University)

442: Improving the Out-Of-Distribution Generalization Capability of Language Models:

Counterfactually-Augmented Data is not Enough
Caoyun Fan (Shanghai Jiao Tong University)*; Wenqing Chen (Sun Yat-sen University); Jidong Tian
(Shanghai Jiao Tong University); Yitian Li (Shanghai Jiao Tong University); Hao He (Shanghai Jiao Tong
University); Yaohui Jin (Shanghai Jiao Tong University)

443: Tell Model Where to Attend: Improving Interpretability of Aspect-Based Sentiment

Classification via Small Explanation Annotations
Zhenxiao Cheng (East China Normal University)*; Jie Zhou (Fudan University); Wen Wu (East China
Normal University); Qin Chen (East China Normal University); Liang He (ECNU)

457: A Generalized Subspace Distribution Adaptation Framework for Cross-Corpus Speech

Emotion Recognition
Shaokai Li (Yaitai University); Peng Song (Yantai University)*; Liang Ji (Yantai University); Yun Jin
(Jiangsu Normal University); Wenming Zheng (Southeast University)

180
462: LightGrad: Lightweight Diffusion Probabilistic Model for Text-to-Speech
Jie Chen (Shenzhen International Graduate School, Tsinghua University)*; Xingchen Song (Horizon
Robotics, Beijing, China); Zhendong Peng ( Horizon Robotics, Beijing, China); Binbin Zhang (
Horizon Robotics, Beijing, China); Fuping Pan ( Horizon Robotics, Beijing, China); Zhiyong Wu (Tsinghua
University)

466: Papez: Resource-efficient Speech Separation with Auditory Working Memory

Hyunseok Oh (Seoul National University)*; Juheon Yi (Seoul National University); Youngki Lee (Seoul
National University)

486: EfficientSpeech: An On-Device Text to Speech Model

Rowel O Atienza (University of the Philippines)*

505: SAN: a robust end-to-end ASR model architecture

Zeping Min (Peking University)*; Qian Ge (Peking University); Guanhua Huang (USTC)

510: WeSinger 2: Fully Parallel Singing Voice Synthesis via Multi-Singer Conditional Adversarial
Training
Zewang Zhang (Tencent Inc.)*; Yibin Zheng (Tencent Inc, China); Xinhui Li (Tencent Inc); Li Lu (Tencent
Inc)

531: A Reality Check and A Practical Baseline for Semantic Speech Embedding
Guangyu Chen (Renmin University of China)*; Yuanyuan Cao (Renmin University of China)

540: Mingling or Misalignment? Temporal Shift for Speech Emotion Recognition with Pre-trained
Representations
Siyuan Shen (East China Normal University)*; Feng Liu (East China Normal University); Aimin Zhou (East
China Normal University)

563: Emotion Recognition in Conversation from Variable-Length Context

Mian Zhang (Soochow University)*; Xiabing Zhou (soochow university); Wenliang Chen (Soochow
University); Min Zhang (Soochow University)

565: StreamSpeech: Low-Latency Neural Architecture for High-Quality On-Device Speech

Synthesis
Georgi S Shopov (IICT-BAS)*; Stefan Gerdjikov (FMI, Sofia University); Stoyan Mihov (IICT-BAS)

567: Cross-Modal Mutual Learning for Cued Speech Recognition

Lei Liu (The Chinese University of Hong Kong, Shenzhen)*; Li Liu (Shenzhen Research Institute of Big
Data, the chinese university of hong kong shenzhen)

578: LiteG2P: A fast, light and high accuracy model for Grapheme-to-Phoneme conversion
Chunfeng Wang (Bytedance Inc)*; Peisong Huang (ByteDance Inc.); Yuxiang Zou (Bytedance); Haoyu
Zhang (Bytedance); Shichao Liu (ByteDance); Xiang Yin (ByteDance AI LAB); Zejun Ma (Bytedance)

595: Jeffreys divergence-based regularization of neural network output distribution applied to

speaker recognition
Pierre-Michel Bousquet (Avignon University)*; Mickael Rouvier (LIA - Avignon University)

597: Phonetic RNN-Transducer for Mispronunciation Diagnosis

Daniel Yue Zhang (Amazon)*; Soumya Saha (Amazon); Sarah Campbell (Amazon)

610: SELF-HEALING THROUGH ERROR DETECTION, ATTRIBUTION, AND RETRAINING

Ansel MacLaughlin (Amazon); Anna Rumshisky (University of Massachusetts Lowell); Rinat Khaziev
(Amazon Alexa AI); Anil K Ramakrishna (Amazon); Yuval Merhav (Amazon); Rahul Gupta (Amazon)*

181
611: Question Answering system with Sparse and Noisy Feedback
Djallel Bouneffouf (IBM)*; Oznur Alkan (Optum); Raphael Feraud (Orange Labs); Baihan Lin (Columbia
University)

629: Group Personalized Federated Learning

Zhe Liu (Meta)*; Yue Hui (Meta); Fuchun Peng (Facebook)

636: HAG: Hierarchical Attention with Graph Network for Dialogue Act Classification in
Conversation
Changzeng Fu (Osaka University)*; Zhenghan Chen (Peking University); Jiaqi Shi (Osaka University;
RIKEN); Bowen Wu (Osaka Univeristy); Chaoran Liu (Advanced Telecommunications Research Institute
International); Carlos Toshinori Ishi (Advanced Telecommunications Research Institute International);
Hiroshi Ishiguro (Osaka University)

640: LED: Label Correlation Enhanced Decoder for Multi-Label Text Classification
Kefan Ma (Shanghai Jiao Tong University)*; Zheng Huang (Shanghai Jiao Tong University); Xinrui Deng
(Shanghai Jiao Tong University); Jie Guo (Shanghai Jiao Tong University); Weidong Qiu (Shanghai
Jiaotong University)

663: Evaluating Speech–Phoneme Alignment and Its Impact on Neural Text-To-Speech Synthesis
Frank Zalkow (Fraunhofer IIS)*; Prachi Govalkar (Fraunhofer IIS); Meinard Müller (International Audio
Laboratories Erlangen); Emanuel Habets (Fraunhofer IIS); Christian Dittmar (Fraunhofer IIS)

672: DELIVERING SPEAKING STYLE IN LOW-RESOURCE VOICE CONVERSION WITH MULTI-

FACTOR CONSTRAINTS
Zhichao Wang (Northwestern Polytechnical University)*; Xinsheng Wang (Northwestern Polytechnical
University); Lei Xie (NWPU); yuanzhe chen (Bytedance); qiao tian (ByteDance); wang yuping (bytedance)

683: Improving Speech-to-Speech Translation Through Unlabeled Text

Xuan-Phi Nguyen (Nanyang Technological University)*; Sravya Popuri (Facebook Inc); Changhan Wang
(Facebook AI Research); Yun Tang (Facebook); Ilia Kulikov (Meta AI); Hongyu Gong (Meta AI)

690: DE’HUBERT: DISENTANGLING NOISE IN A SELF-SUPERVISED MODEL FOR ROBUST

SPEECH RECOGNITION
Dianwen Ng (Alibaba Group/Nanyang Technological University)*; Ruixi Zhang (National University of
Singapore); Jia Qi Yip (Alibaba Group); Zhao Yang (Xi'an Jiaotong University); Jinjie Ni (Nanyang
Technological University); Chong Zhang (Alibaba Group); Yukun Ma (Alibaba Group); Chongjia Ni
(Alibaba); Eng Siong Chng (Nanyang Technological University); Bin Ma ("Alibaba, Singapore R&D
Center")

691: Real-time Speech Interruption Analysis: From Cloud to Client Deployment

Quchen Fu (Vanderbilt University)*; Szu-Wei Fu (Microsoft Corporation); Yaran Fan (Microsoft
Corporation); Yu Wu (Microsoft Research Asia); Zhuo Chen (Microsoft); Jayant Gupchup (Microsoft);
Ross Cutler ( Microsoft Corporation)

700: PhaseAug: A Differentiable Augmentation for Speech Synthesis to Simulate One-to-Many

Mapping
Junhyeok Lee (MINDsLab Inc.)*; Seungu Han (MINDsLab Inc.,); Hyunjae Cho (MINDsLab Inc.); Wonbin
Jung (MINDs Lab Inc.)

720: Improving Sentence Similarity Estimation for Unsupervised Extractive Summarization

Shichao Sun (The Hong Kong Polytechnic University)*; Ruifeng Yuan (The Hong Kong Polytechnic
University); Wenjie Li (Department of Computing, the Hong Kong Polytechnic University); Sujian Li
(Peking University)

182
766: Time-domain Speech Enhancement Assisted by Multi-resolution Frequency Encoder and
Decoder
Hao Shi (Kyoto University)*; Masato Mimura (Kyoto University); Longbiao Wang (Tianjin University);
Jianwu Dang (Tianjin University); Tatsuya Kawahara (Kyoto University)

767: Contextual Similarity is More Valuable than Character Similarity: An Empirical Study for
Chinese Spell Checking
Ding Zhang (Tsinghua University); Yinghui Li (Tsinghua University)*; Qingyu Zhou (OPPO Research
Institute); Shirong Ma (Tsinghua University); Li Yangning (Tsinghua Shenzhen International Graduate
School); Yunbo Cao (Tencent); Hai-Tao Zheng (Tsinghua University)

770: Prompt-Distiller: Few-shot Knowledge Distillation for Prompt-based Language Learners with
Dual Contrastive Learning
Boyu Hou (Chongqing University); Chengyu Wang (Alibaba)*; Xiaoqing Chen (Chongqing University);
Minghui Qiu (Alibaba); Liang Feng (Chongqing University, China); Jun Huang (Alibaba Group)

779: Dialogue System with Missing Observation

Djallel Bouneffouf (IBM)*; mayank agarwal (ibm); Irina Rish (university of montreal)

785: Stabilising and accelerating light gated recurrent units for automatic speech recognition
Adel Moumen (Avignon University)*; Titouan Parcollet (Samsung AI Research)

797: Cocktail HuBERT: Generalized Self-Supervised Pre-training for Mixture and Single-Source
Speech
Maryam Fazel-Zarandi (Meta); Wei-Ning Hsu (Massachusetts Institute of Technology)*

821: Coarse-to-Fine Knowledge Selection for Document Grounded Dialogs

Yeqin Zhang (Nanjing University)*; Haomin Fu (Nanjing University ); Cheng Fu (Alibaba); Haiyang Yu
(Alibaba); Yongbin Li (Alibaba Group ); Cam-Tu Nguyen (Nanjing University)

823: SADE: A Self-adaptive Expert for Multi-dataset Question Answering

Yixing Peng (State Key Laboratory of Communication Content Cognition, University of Science and
Technology of China)*; Quan Wang (Beijing University of Posts and Telecommunications); Zhendong Mao
(University of Science and Technology of China); Yongdong Zhang (University of Science and Technology
of China)

826: Advancing the dimensionality reduction of speaker embeddings for speaker diarisation:
disentangling noise and informing speech activity
You Jin Kim (Naver Corporation)*; Heesoo Heo (Naver Corp.); Jee-weon Jung (Naver Corporation);
Youngki Kwon (Naver Corporation); Bong-Jin Lee (Naver Corporation); Joon Son Chung (KAIST)

831: Matching-based Term Semantics Pre-training for Spoken Patient Query Understanding
Zefa Hu (Institute of Automation，Chinese Academy of Sciences)*; Xiuyi Chen (Institute of
Automation,Chinese Academy of Science); Haoran Wu (Institute of Automation，Chinese Academy of
Sciences); Minglun Han (Institute of Automation, Chinese Academy of Sciences); Ni Ziyi (CASIA); Jing
Shi (Institute of Automation Chinese Academy of Sciences); Shuang Xu (casia); Bo Xu (Institute of
Automation, Chinese Academy of Sciences)

836: Keyword-Specific Acoustic Model Pruning for Open Vocabulary Keyword Spotting
Yujie Yang (Tsinghua University)*; Kun Zhang (The Chinese University of Hong Kong); Zhiyong Wu
(Tsinghua University); Helen Meng (The Chinese University of Hong Kong)

845: Boosting Prompt-based Few-shot Learners through Out-of-domain Knowledge Distillation

Xiaoqing Chen (Chongqing University); Chengyu Wang (Alibaba)*; junwei dong (Chongqing university);
Minghui Qiu (Alibaba); Liang Feng (Chongqing University, China); Jun Huang (Alibaba Group)

183
865: Towards A Unified Training for Levenshtein Transformer
Kangjie Zheng (Peking University)*; Longyue Wang (Tencent AI Lab); Zhihao Wang (Xiamen University);
Chen Binqi (Peking University); Ming Zhang (Peking University); Zhaopeng Tu (Tencent AI Lab)

876: A Comparison of Semi-Supervised Learning Techniques for Streaming ASR at Scale

Charles C Peyser (Google Inc.)*; Michael Picheny (NYU); Kyunghyun Cho (New York University); Tara
Sainath (Google); W. Ronny Huang (Google); Rohit Prabhavalkar (Google)

900: Multi-blank Transducers for Speech Recognition

Hainan Xu (NVIDIA)*; Fei Jia (NVIDIA Corporation); Somshubra Majumdar (NVIDIA); Shinji Watanabe
(Carnegie Mellon University); Boris Ginsburg (NVIDIA)

901: E2E Segmentation in a Two-Pass Cascaded Encoder ASR Model

W. Ronny Huang (Google)*; Shuo-yiin Chang (Google); Tara Sainath (Google); Yanzhang He (Google);
David Rybach (Google); Robert David (Google); Rohit Prabhavalkar (Google); Cyril Allauzen (Google);
Charles C Peyser (Google Inc.); Trevor Strohman (Google)

915: PERCEIVE AND PREDICT: SELF SUPERVISED SPEECH REPRESENTATION BASED LOSS
FUNCTIONS FOR SPEECH ENHANCEMENT
George L Close (University of Sheffield)*; William Ravenscroft (The University of Sheffield); Thomas Hain
(University of Sheffield); Stefan Goetze (University of Sheffield)

930: Learning Cross-modal Audiovisual Representations with Ladder Networks for Emotion
Recognition
Lucas Goncalves (The University of Texas at Dallas)*; Carlos Busso (University of Texas at Dallas)

934: Simulating realistic speech overlaps improves multi-talker ASR

Muqiao Yang (Carnegie Mellon University)*; Naoyuki Kanda (Microsoft); Xiaofei Wang (Microsoft Corp.);
Jian Wu (Microsoft); Sunit Sivasankaran (Microsoft); Zhuo Chen (Microsoft); Jinyu Li (Microsoft); Takuya
Yoshioka (Microsoft)

935: PAAPLoss: A Phonetic-Aligned Acoustic Parameter Loss for Speech Enhancement

Muqiao Yang (Carnegie Mellon University)*; Joseph Konan (Carnegie Mellon University); David Bick
(Carnegie Mellon University); Yunyang Zeng (Carnegie Mellon University); Shuo Han (Carnegie Mellon
University); Anurag Kumar (Facebook Research); Shinji Watanabe (Carnegie Mellon University); Bhiksha
Raj (Carnegie Mellon University)

958: D2Former: A Fully Complex Dual-Path Dual-Decoder Conformer Network using Joint
Complex Masking and Complex Spectral Mapping for Monaural Speech Enhancement
Shengkui Zhao (Alibaba Group)*; Bin Ma ("Alibaba, Singapore R&D Center")

959: MossFormer: Pushing the Performance Limit of Monaural Speech Separation using Gated
Single-head Transformer with Convolution-augmented Joint Self-Attentions
Shengkui Zhao (Alibaba Group)*; Bin Ma ("Alibaba, Singapore R&D Center")

963: Target Speaker Voice Activity Detection with Transformers and Its Integration with End-to-
End Neural Diarization
Dongmei Wang (Microsoft)*; Xiong Xiao (Microsoft); Naoyuki Kanda (Microsoft); Takuya Yoshioka
(Microsoft); Jian Wu (Microsoft)

971: Mitigating Unintended Memorization in Language Models via Alternating Teaching

Zhe Liu (Meta)*; Xuedong Zhang (Meta); Fuchun Peng (Facebook)

975: Acoustically-Driven Phoneme Removal That Preserves Vocal Affect Cues

Camille Noufi (Stanford University)*; Jonathan Berger (Stanford University); Karen Parker (Stanford
University); Daniel L Bowling (Stanford University)

184
1007: AdapITN: A FAST, RELIABLE, AND DYNAMIC ADAPTIVE INVERSE TEXT NORMALIZATION
Binh Thai Nguyen (Karlsruhe Institute of Technology)*; Duc Minh Nhat Le (Vietnam Artificial Intelligence
Solutions); Quang Minh Nguyen (Vietnam Artificial Intelligence Solutions); Quoc Truong Do (Vietnam
Artificial Intelligence Solutions); Chi-Mai Luong (ICTLab, University of Science and Technology of Hanoi,
Vietnam Academy of Science and Technology, 18 Hoang Quoc Viet, Cau Giay, Hanoi, Vietnam.);
Alexander Waibel (Karlsruhe Institute of Technology)

1025: Improving Prosody for Cross-Speaker Style Transfer by Semi-Supervised Style Extractor
and Hierarchical Modeling in Speech Synthesis
Chunyu Qiang (Kwai)*; Peng Yang (Kwai); Hao Che (Kwai); Ying Zhang (Kwai); Xiaorui Wang (Kwai);
Zhongyuan Wang (Kwai)

1027: CYFI-TTS: CYCLIC NORMALIZING FLOW WITH FINE-GRAINED REPRESENTATION FOR

END-TO-END TEXT-TO-SPEECH
Insun Hwang (LG Uplus)*; Youngsub Han (LG Uplus); Byoung-Ki Jeon (LG Uplus)

1059: A CONTRASTIVE FRAMEWORK TO ENHANCE UNSUPERVISED SENTENCE

REPRESENTATION LEARNING
Haoyang Ma (North China Institute of Computing Technology)*; Zeyu Li (Communication university of
China); Hongyu Guo (North China Institute of Computing Technology)

1081: Database-Aware ASR Error Correction for Speech-to-SQL Parsing

Yutong Shao (University of California San Diego)*; Arun Kumar (University of California, San Diego);
Ndapa Nakashole (University of California, San Diego)

1114: Permutation Invariant Training for Paraphrase Identification

Jun Bai (Beihang University)*; Chuantao Yin (Beihang University); Hanhua Hong (Beihang University);
Jianfei zhang (Beihang University); Chen Li (Beihang University); Yanmeng Wang (Ping An Technology);
Wenge Rong (Beihang University)

1158: PREFIX TUNING FOR AUTOMATED AUDIO CAPTIONING

Minkyu Kim (POSTECH); Kim Sung-Bin (POSTECH)*; Tae-Hyun Oh (POSTECH)

1195: MULTIPLE ACOUSTIC FEATURES SPEECH EMOTION RECOGNITION USING CROSS-

ATTENTION TRANSFORMER
Yurun He (The University of Tokyo)*; Nobuaki Minematsu (The University of Tokyo); Daisuke Saito (The
University of Tokyo)

1213: UNSUPERVISED EXTRACTIVE SUMMARIZATION WITH HETEROGENEOUS GRAPH

EMBEDDINGS FOR CHINESE DOCUMENTS
Chen Lin (Tencent)*; Ye Liu (Tencent); Siyu An (Tencent); Di Yin (Tencent)

1230: CTCBERT: ADVANCING HIDDEN-UNIT BERT WITH CTC OBJECTIVES

Ruchao Fan (University of California, Los Angeles)*; Yiming Wang (Microsoft Corporation); Yashesh Gaur
(Microsoft); Jinyu Li (Microsoft)

1240: Hierarchical Diffusion Models for Singing Voice Neural Vocoder

Naoya Takahashi (Sony Group)*; Mayank Kumar Singh (Sony Research India); Yuki Mitsufuji (Sony
Group Corporation)

1241: PERIOD VITS: VARIATIONAL INFERENCE WITH EXPLICIT PITCH MODELING FOR END-TO-
END EMOTIONAL SPEECH SYNTHESIS
Yuma Shirahata (LINE Corp.)*; Ryuichi Yamamoto (LINE Corp.); Eunwoo Song (Naver Corporation); Ryo
Terashima (LINE Corp.); Jae-Min Kim (NAVER Cloud Corp.); Kentaro Tachibana (LINE Corp.)

185
1253: AN ASR-FREE FLUENCY SCORING APPROACH WITH SELF-SUPERVISED LEARNING
Wei Liu (The Chinese University of Hong Kong)*; Kaiqi Fu (Bytedance); Xiaohai Tian (ByteDance); Shuju
Shi (ByteDance); Wei Li (Bytedance); Zejun Ma (Bytedance); Tan Lee (The Chinese University of Hong
Kong)

1273: Semi-supervised speech enhancement based on speech purity

Zihao Cui (China Mobile Research Institute)*; Shilei Zhang (China Mobile Research Institute); Yanan
Chen (China Mobile Research Institute); Yingying Gao (China Mobile Research Institute); Chao Deng
(China Mobile Research Institute); Junlan Feng (China Mobile Research)

1286: LEVERAGING PHONE-LEVEL LINGUISTIC-ACOUSTIC SIMILARITY FOR UTTERANCE-LEVEL

PRONUNCIATION SCORING
Wei Liu (The Chinese University of Hong Kong)*; Kaiqi Fu (Bytedance); Xiaohai Tian (ByteDance); Shuju
Shi (ByteDance); Wei Li (Bytedance); Zejun Ma (Bytedance); Tan Lee (The Chinese University of Hong
Kong)

1290: In search of strong embedding extractors for speaker diarisation

Jee-weon Jung (Naver Corp.)*; Heesoo Heo (Naver Corp.); Bong-Jin Lee (Naver Corporation); Jaesung
Huh (University of Oxford); Andrew Brown (University of Oxford); Youngki Kwon (Naver Corporation);
Shinji Watanabe (Carnegie Mellon University); Joon Son Chung (KAIST)

1298: Raw Ultrasound-based Phonetic Segments Classification Via Mask Modeling

kang you (Shanghai Jiao Tong University); Bo Liu (National University of Defense Technology); Kele Xu
(National Key Laboratory of Parallel and Distributed Processing (PDL))*; Yunsheng Xiong (National
University of Defense Technology); Qisheng Xu (National University of Defense Technology); Ming Feng
(Tongji University); Tamás G Csapó (Budapest University of Technology and Economics); Boqing Zhu
(National University of Defense Technology)

1313: ESCL: EQUIVARIANT SELF-CONTRASTIVE LEARNING FOR SENTENCE

REPRESENTATIONS
Jie Liu (China Mobile Research)*; Yixuan Liu (Beijing University of Posts and Telecommunications); Xue
Han (China Mobile Research); Chao Deng (China Mobile Research Institute); Junlan Feng (China Mobile
Research)

1336: Extreme bandwidth extension network applied to speech signals captured with noise-
resilient body-conduction microphones
Julien Hauret (Conservatoire national des arts et métiers)*; Thomas Joubaud (ISL); Véronique Zimpfer
(Department of Acoustics and Soldier Protection, French-German Research Institute of Saint-Louis (ISL));
Éric BAVU (Conservatoire National des Arts et Métiers)

1356: Improving Contextual Biasing with Text Injection

Tara Sainath (Google)*; Rohit Prabhavalkar (Google); Diamantino Caseiro (Google, Inc.); Pat Rondon
(Google, Inc.); Cyril Allauzen (Google)

1373: Fast and accurate factorized neural transducer for text adaption of end-to-end speech
recognition models
Rui Zhao (Microsoft)*; JIAN XUE (Microsoft Corporation); Partha Parthasarathy (Microsoft); Veljko
Miljanic (Microsoft); Jinyu Li (Microsoft)

1378: Unified Keyword Spotting and Audio Tagging on Mobile Devices with Transformers
Heinrich Dinkel (Xiaomi Techonology)*; Yongqing Wang (Xiaomi); Zhiyong Yan (Xiaomi); Junbo Zhang
(Xiaomi); Yujun Wang (xiaomi)

186
1398: Streaming Voice Conversion Via Intermediate Bottleneck Features And Non-streaming
Teacher Guidance
yuanzhe chen (Bytedance)*; Ming Tu (ByteDance AI Lab); Tang Li (ByteDance Ltd); Xin Li (ByteDance);
Qiuqiang Kong (Byte Dance); Jiaxin Li (ByteDance); Zhichao Wang (ByteDance); qiao tian (ByteDance);
wang yuping (bytedance); Yuxuan Wang (ByteDance AI Lab)

1423: Knowledge-Aware Graph Convolutional Network with Utterance-Specific Window Search for
Emotion Recognition in Conversations
Xiaotong Zhang (School of Software, Dalian University of Technology)*; Peng He (School of
Software,Dalian University of Technology); Han Liu (Dalian University of Technology); Zhengxi Yin
(Huawei Technologies Co. Ltd); Xinyue Liu (School of Software, Dalian University of Technology);
Xianchao Zhang (School of Software, Dalian University of Technology)

1457: Optimal Transport with a Diversified Memory Bank for Cross-Domain Speaker Verification
Ruiteng Zhang (Tianjin University)*; Jianguo Wei (School of Computer Software, Tianjin University,
Tianjin, China); Xugang Lu (NICT); Wenhuan Lu (Tianjin University); Di Jin (Tianjin University); Lin Zhang
(National Institute of Informatics); Junnhai Xu (Tianjin Key Laboratory of Cognitive Computing and
Application, College of Intelligence and Computing, Tianjin University)

1484: Mid-attribute Speaker Generation using Optimal-Transport-based Interpolation of Gaussian

Mixture Models
Aya Watanabe (The University of Tokyo)*; Shinnosuke Takamichi (The University of Tokyo); Yuki Saito
("The University of Tokyo, Japan"); Detai Xin (The University of Tokyo); Hiroshi Saruwatari (The University
of Tokyo)

1487: M2-CTTS: End-to-End Multi-scale Multi-modal Conversational Text-to-Speech Synthesis

Jinlong Xue (Beijing University of Posts and Telecommunications)*; Yayue Deng (Beijing University of
Posts and Telecommunications); Fengping Wang (Beijing University of Posts and Telecommunications);
Ya Li (Beijing University of Posts and Telecommunications); Yingming Gao (Beijing University of Posts
and Telecommunications); Jianhua Tao ("National Laboratory of Pattern Recognition, Institute of
Automation, Chinese Academy of Sciences"); Jianqing Sun (Unisound AI Technology Co.,Ltd); Jiaen
Liang (Unisound)

1499: Neural Transducer Training: Reduced Memory Consumption with Sample-wise Computation
Stefan Braun (Apple)*; Erik McDermott (Apple); Roger Hsiao (Apple)

1512: Do Prosody Transfer Models Transfer Prosody?

Atli Thor Sigurgeirsson (University of Edinburgh)*; Simon King (University of Edinburgh)

1518: Continual Learning for On-Device Speech Recognition using Disentangled Conformers
Anuj Diwan (University of Texas at Austin)*; Ching-Feng Yeh (Facebook); Wei-Ning Hsu (Massachusetts
Institute of Technology); Paden Tomasello (Meta); Eunsol Choi (University of Texas at Austin); David
Harwath (The University of Texas at Austin); Abdelrahman Mohamed (Rembrand Inc)

1524: Multi-output RNN-T Joint Networks for Multi-task Learning of {ASR} and Auxiliary Tasks
Weiran Wang (Google)*; Ding Zhao (Google); Shaojin Ding (Google); Hao Zhang (Google); Shuo-yiin
Chang (Google); David Rybach (Google); Tara Sainath (Google); Yanzhang He (Google); Ian McGraw ();
Shankar Kumar (Google)

1593: CrossSpeech: Speaker-independent Acoustic Representation for Cross-lingual Speech

Synthesis
Ji-Hoon Kim (42dot)*; Hong-Sun Yang (42dot Inc); Yooncheol Ju (AIRS Company, Hyundai Motor Group,
Seoul, Republic of Korea); ILHWAN KIM (42dot); Byeong-Yeol Kim (42dot)

187
1604: Explanations for Automatic Speech Recognition
Xiaoliang Wu (University of Edinburgh)*; Peter Bell (University of Edinburgh); Ajitha Rajan (University of
Edinburgh)

1611: Masking speech contents by random splicing: Is emotional expression preserved?

Felix Burkhardt (audEERING GmbH)*; Anna Derington (audEERING GmbH); Matthias Kahlau
(audEERING GmbH); Klaus Scherer (University of Geneva); Florian Eyben (audEERING); Bjoern
Schuller (audEERING)

1616: Improving Scheduled Sampling for Neural Transducer-based ASR

Takafumi Moriya (NTT Corporation)*; Takanori Ashihara (NTT Corp.); Hiroshi Sato (NTT Corporation);
Kohei Matsuura (NTT); Tomohiro Tanaka (NTT Corporation); Ryo Masumura (NTT Corporation)

1628: EFFECTIVE TRAINING OF RNN TRANSDUCER MODELS ON DIVERSE SOURCES OF

SPEECH AND TEXT DATA
Takashi Fukuda (IBM Research)*; Samuel Thomas (IBM Research AI)

1638: Spoofed training data for speech spoofing countermeasure can be efficiently created using
neural vocoders
Xin Wang (National Institute of Informatics)*; Junichi Yamagishi (National Institute of Informatics)

1639: Multi-speaker Data Augmentation for Improved End-to-end Automatic Speech Recognition
Samuel Thomas (IBM Research AI)*; Jeff Kuo (IBM); George Saon (IBM); Brian Kingsbury (IBM
Research)

1642: DIAGONAL STATE SPACE AUGMENTED TRANSFORMERS FOR SPEECH RECOGNITION

George Saon (IBM)*; Ankit Gupta (IBM Research); Xiaodong Cui (IBM T. J. Watson Research Center)

1647: Named Entity Detection and Injection for Direct Speech Translation
Marco Gaido (Fondazione Bruno Kessler)*; Yun Tang (Meta); Ilia Kulikov (Meta); Rongqing Huang (Meta);
Hongyu Gong (Meta); HIrofumi Inaguma (Meta)

1648: C2KD: Cross-Lingual Cross-Modal Knowledge Distillation for Multilingual Text-Video

Retrieval
Andrew Rouditchenko (MIT CSAIL)*; Yung-Sung Chuang (MIT); Nina Shvetsova (Goethe University
Frankfurt); Samuel Thomas (IBM Research AI); Rogerio Feris (MIT-IBM Watson AI Lab, IBM Research);
Brian Kingsbury (IBM Research); Leonid Karlinsky (IBM-Research); David Harwath (The University of
Texas at Austin); Hilde Kuehne (Goethe University Frankfurt); James Glass (Massachusetts Institute of
Technology)

1655: STRUCTURED STATE SPACE DECODER FOR SPEECH RECOGNITION AND SYNTHESIS
Koichi Miyazaki (CyberAgent, Inc.)*; Masato Murata (CyberAgent, Inc.); Tomoki Koriyama (CyberAgent,
Inc.)

1661: TrimTail: Low-Latency Streaming ASR with Simple but Effective Spectrogram-Level Length
Penalty
Xingchen Song (Tsinghua University)*; Di Wu (horizon); Zhiyong Wu (Tsinghua University); Binbin Zhang
(horizon); Yuekai Zhang (Wenet Open Source Community); Zhendong Peng (horizon); Wenpeng Li
(horizon); Fuping Pan (horizon); Changbao Zhu (horizon)

1672: Text is All You Need: Personalizing ASR Models using Controllable Speech Synthesis
Karren D Yang (Apple)*; Ting-Yao Hu (Carnegie Mellon University); Jen-Hao Rick Chang (Apple); Hema
Koppula (Apple); Oncel Tuzel (Apple)

188
1674: On-the-fly Text Retrieval for End-to-End ASR Adaptation
Bolaji Yusuf (Bogazici University)*; Aditya Gourav (Amazon); Ankur Gandhe (Amazon Alexa); Ivan Bulyko
(Amazon)

1687: Analyzing Acoustic Word Embeddings from Pre-trained Self-supervised Models

Ramon R Sanabria (The University Of Edinburgh)*; Hao Tang (The University of Edinburgh); Sharon
Goldwater (University of Edinburgh)

1688: Probabilistic back-ends for online speaker recognition and clustering

Alexey Sholokhov (Huawei Technologies Co., Ltd.)*; Nikita Kuzmin (NTU); Kong Aik Lee (Institute for
Infocomm Research, A*STAR); Eng Siong Chng (Nanyang Technological University)

1695: Toward a Multimodal Approach for Disfluency Detection and Categorization

Amrit Romana (University of Michigan)*; Kazuhito Koishida (Microsoft)

1699: On Using the UA-Speech and TORGO Databases to Validate Automatic Dysarthric Speech
Classification Approaches
Guilherme Schu (Idiap)*; Parvaneh janbakhshi (Bayer AG); Ina Kodrasi (Idiap Research Institute)

1702: CONTEXT-AWARE END-TO-END ASR USING SELF-ATTENTIVE EMBEDDING AND TENSOR

FUSION
Shuo-yiin Chang (Google)*; Chao Zhang (Cambridge University); Tara Sainath (Google); Bo Li (Google);
Trevor Strohman (Google)

1713: SQuId: Measuring Speech Naturalness in Many Languages

Thibault Sellam (Google)*; Ankur Bapna (Google Research); Joshua Camp (Google); Diana Mackinnon
(Google); Ankur Parikh (Google); Jason Riesa (Google)

1733: CONTRASTIVE LEARNING WITH DIALOGUE ATTRIBUTES FOR NEURAL DIALOGUE

GENERATION
Jie Tan (The Chinese University of Hong Kong)*; Hengyi Cai (Baidu Inc.); Hongshen Chen (JD.com);
Hong Cheng (Chinese University of Hong Kong); Helen Meng (The Chinese University of Hong Kong);
Zhuoye Ding (JD.com)

1792: Time-Aware Multiway Adaptive Fusion Network for Temporal Knowledge Graph Question
Answering
Yonghao Liu (Centre for Natural Language Processing, Meituan Inc., Beijing, China); Di Liang (Centre for
Natural Language Processing, Meituan Inc., Beijing, China)*; Fang Fang (Department of Automation,
Tsinghua University, Beijing, China); Sirui Wang (Centre for Natural Language Processing, Meituan Inc.,
Beijing, China); Wei Wu (Centre for Natural Language Processing, Meituan Inc., Beijing, China); Rui
Jiang (Department of Automation, Tsinghua University, Beijing, China)

1815: Adaptive Large Margin Fine-tuning for Robust Speaker Verification

Leying Zhang (Shanghai Jiao Tong University)*; Zhengyang Chen (Shanghai Jiao Tong University);
Yanmin Qian (Shanghai Jiao Tong University)

1826: EGAN: A Neural Excitation Generation Model based on Generative Adversarial Networks
with Harmonics and Noise Input
Yen-Ting Lin (National Taipei University)*; Chen Yu CHIANG (National Taipei University)

1848: Disentangled Training with Adversarial Examples For Robust Small-footprint Keyword
Spotting
ZHENYU WANG (UTD); Li Wan (Meta); Biqiao Zhang (Meta); Yiteng Huang (Meta Platforms); Shang-
Wen Li (Meta); Ming Sun (Meta); Xin Lei (Meta); Zhaojun Yang (Meta)*

189
1850: Anchored Speech Recognition with Neural Transducers
Desh Raj (Johns Hopkins University)*; Junteng Jia (Meta AI); Jay Mahadeokar (Meta AI); Chunyang Wu
(Meta AI); Niko Moritz (Meta); Xiaohui Zhang (Meta); Ozlem Kalinli (Meta AI)

1858: SPEECH EMOTION RECOGNITION VIA TWO-STREAM POOLING ATTENTION WITH

DISCRIMINATIVE CHANNEL WEIGHTING
Ke Liu (Northwest University)*; Dekui Wang (Northwest University); Dongya Wu (Northwest University);
Jun Feng (Northwest University)

1859: Identifying Entrainment in Task-oriented Conversations

Run Chen (Columbia University)*; Seokhwan Kim (Amazon Alexa AI); Alexandros Papangelis (Amazon
Alexa AI); Julia Hirschberg (Columbia University); Yang Liu (Amazon, Alexa AI); Dilek Z Hakkani-Tur
(Amazon Alexa AI)

1867: A Holistic Cascade System, Benchmark, and Human Evaluation Protocol for Expressive
Speech-to-Speech Translation
Wen-Chin Huang (Nagoya University)*; Benjamin Peloquin (Meta AI); Justine Kao (Meta AI); Changhan
Wang (Facebook AI Research); Hongyu Gong (Meta AI); Elizabeth Salesky (Johns Hopkins University);
Yossi Adi (Facebook AI Research ); Ann Lee (Facebook, Inc.); Peng-Jen Chen (Meta AI)

1875: Role of Bias Terms in Dot-Product Attention

Mahdi Namazifar (Amazon Alexa AI)*; Devamanyu Hazarika (Amazon Alexa AI); Dilek Z Hakkani-Tur
(Amazon Alexa AI)

1883: Supervised Hierarchical Clustering using Graph Neural Networks for Speaker Diarization
Prachi Singh (Indian Institute of Science, Bangalore)*; Amrit Kaul ( Indian Institute of Science,
Bangalore); Sriram Ganapathy (Indian Institute of Science, Bangalore, India, 560012)

1886: SLBERT: A NOVEL PRE-TRAINING FRAMEWORK FOR JOINT SPEECH AND LANGUAGE
MODELING
Onkar Susladkar (Natter Labs)*; Prajwal Gatti (Dayananda Sagar College of Engineering); Santosh
Kumar Yadav (Natter Labs)

1890: A Study on Bias and Fairness In Deep Speaker Recognition

Amirhossein Hajavi (Queen's University)*; Ali Etemad (Queen's University)

1897: ON WORD ERROR RATE DEFINITIONS AND THEIR EFFICIENT COMPUTATION FOR MULTI-
SPEAKER SPEECH RECOGNITION SYSTEMS
Thilo von Neumann (Paderborn University)*; Christoph B Boeddeker (Paderborn University); Keisuke
Kinoshita (Google); Marc Delcroix (NTT); Reinhold Haeb-Umbach (University of Paderborn)

1905: ``Prediction of Sleepiness Ratings from Voice by Man and Machine": a perceptual
experiment replication study
Vincent P. Martin (Université de Bordeaux)*; Aymeric Ferron (INRIA Bordeaux); Jean-Luc Rouas (CNRS);
Pierre Philip (Université de Bordeaux)

1916: Unsupervised Word Segmentation Using Temporal Gradient Pseudo-Labels

Tzeviya S Fuchs (Bar-Ilan University)*; Yedid Hoshen (The Hebrew University of Jerusalem)

1919: Gradient Remedy for Multi-Task Learning in End-to-End Noise-Robust Speech Recognition
Yuchen Hu (Nanyang Technological University)*; Chen Chen (Nanyang Technological University); Ruizhe
Li (University of Aberdeen); Qiu-Shi Zhu (University of Science and Technology of China); Eng Siong
Chng (Nanyang Technological University)

190
1929: MADI: Inter-domain Matching and Intra-domain Discrimination for Cross-domain Speech
Recognition
Jiaming Zhou (Nankai University)*; Shiwan Zhao (Independent Researcher); Ning Jiang (Mashang
Consumer Finance Co., Ltd.); Guoqing Zhao (Mashang Consumer Finance Co., Ltd); Yong Qin (Nankai
University)

1943: Empathetic Response Generation via Emotion Cause Transition Graph

Yushan Qian (Tianjin University)*; Bo Wang (Tianjin University); Ting-En Lin (Alibaba Group); Yinhe
Zheng (Lingxin AI); Ying Zhu (Tianjin University); Dongming Zhao (China Mobile Communication Group
Tianjin Co., Ltd); Yuexian Hou (Tianjin University); Yuchuan Wu (Alibaba); Yongbin Li (Alibaba Group)

1948: Masked Token Similarity Transfer for Compressing Transformer-Based ASR Models
Euntae Choi (Seoul National University)*; Youshin Lim (42dot); Byeong-Yeol Kim (42dot); Hyung Yong
Kim (42dot); Hanbin Lee (42dot); Yunkyu Lim (42dot); Seung Woo Yu (42dot); Sungjoo Yoo (Seoul
National University)

1971: ROBUST DATA2VEC: NOISE-ROBUST SPEECH REPRESENTATION LEARNING FOR ASR BY

COMBINING REGRESSION AND IMPROVED CONTRASTIVE LEARNING
Qiu-Shi Zhu (University of Science and Technology of China)*; Long Zhou (Microsoft Research Asia); Jie
Zhang (University of Science and Technology of China); Shujie Liu (Microsoft Research Asia); Yuchen Hu
(Nanyang Technological University); Lirong Dai (University of Science and Technology of China)

1981: Pitch Mark Detection from Noisy Speech Waveform using Wave-U-Net
Hyun-Joon Nam (Pohang University of Science and Technology)*; Hong-June Park (Pohang University of
Science and Technology)

1982: A Framework for Unified Real-time Personalized and Non-Personalized Speech

Enhancement
Zhepei Wang (University of Illinois at Urbana-Champaign)*; Ritwik Giri (Amazon); Devansh Shah
(Amazon Web Services); Jean-Marc Valin (Amazon); Michael M Goodwin (AWS ); Paris Smaragdis
(University of Illinois at Urbana-Champaign)

1986: Filterbank Learning for Noise-Robust Small-Footprint Keyword Spotting

Iván López-Espejo (Aalborg University)*; RAM CHARAN M CHANDRA SHEKAR (University of Texas at
Dallas); Zheng-Hua Tan (Aalborg University); Jesper Jensen (Aalborg University); John H Hansen (Univ.
of Texas at Dallas)

1993: NEURAL SPEECH PHASE PREDICTION BASED ON PARALLEL ESTIMATION

ARCHITECTURE AND ANTI-WRAPPING LOSSES
Yang Ai (University of Science and Technology of China)*; Zhen-Hua Ling (University of Science and
Technology of China)

2003: ImagineNET: Target Speaker Extraction with Intermittent Visual Cue through Embedding
Inpainting
Zexu Pan (National University of Singapore)*; Wupeng Wang (NUS); Marvin Borsdorf (University of
Bremen); Haizhou Li (The Chinese University of Hong Kong (Shenzhen))

2005: Audio-to-Intent Using Acoustic-Textual Subword Representations from End-to-End ASR

Pranay Dighe (Apple)*; Prateeth Nayak (Apple); Ognjen Rudovic (Apple); Erik Marchi (Apple); Xiaochuan
Niu (Apple); Ahmed Tewfik (Apple)

2006: Data2vec-SG: Improving Self-supervised Learning Representations for Speech Generation

Tasks
Heming Wang (The Ohio State University)*; Yao Qian (Microsoft); Hemin Yang (Microsoft); Naoyuki
Kanda (Microsoft); Peidong Wang (Microsoft); Takuya Yoshioka (Microsoft); Xiaofei Wang (Microsoft);

191
Yiming Wang (Microsoft Corporation); Shujie Liu (Microsoft Research Asia); Zhuo Chen (Microsoft);
DeLiang Wang (Ohio State University); Michael Zeng (Microsoft)

2040: Robust Audio-Visual ASR with Unified Cross-modal Attention

Jiahong Li (Shanghai Jiao Tong University)*; Chenda Li (Shanghai Jiao Tong University); Yifei Wu
(Shanghai Jiao Tong University); Yanmin Qian (Shanghai Jiao Tong University)

2056: Relational Representation Learning for Zero-shot Relation Extraction with Instance
Prompting and Prototype Rectification
Bin Duan (Beijing University of Posts and Telecommunications); Xingxian Liu (Beijing University of Posts
and Telecommunications); Shusen Wang (Beijing University of Posts and Telecommunications); Yajing Xu
(Beijing University of Posts and Telecommunications)*; Bo Xiao (Beijing University of Posts and
Telecommunications)

2074: Self-supervised representations in speech-based depression detection

Wen Wu (University of Cambridge)*; Chao Zhang (University of Cambridge); Phil Woodland (Machine
Intelligence Laboratory, Cambridge University Department of Engineering)

2096: The Edinburgh International Accents of English Corpus: Towards the Democratization of
English ASR
Ramon R Sanabria (The University Of Edinburgh)*; Nikolay Bogoychev (The University Of Edinburgh);
Nina Markl (University of Edinburgh); Andrea Carmantini (University of Edinburgh); Ondrej Klejch
(University of Edinburgh); Peter Bell (University of Edinburgh)

2108: PAGE: A POSITION-AWARE GRAPH-BASED FRAMEWORK FOR EMOTION CAUSE

ENTAILMENT IN CONVERSATION
Xiaojie Gu (Hangzhou City University); Renze Lou (Pennsylvania State University); Lin Sun (Hangzhou
City University)*; Shangxin Li (Hangzhou City University)

2123: Exploring Self-supervised Pre-trained ASR Models For Dysarthric and Elderly Speech
Recognition
Shujie HU (The Chinese University of Hong Kong)*; Xurong Xie (Institute of Software, Chinese Academy
of Sciences); Zengrui Jin (The Chinese University of Hong Kong); Mengzhe GENG (The Chinese
University of Hong Kong); Yi Wang (The Chinese University of Hong Kong); Mingyu Cui (The Chinese
University of Hong Kong); Jiajun Deng (The Chinese University of HongKong); Xunying Liu (The Chinese
University of Hong Kong); Helen Meng (The Chinese University of Hong Kong)

2151: PRE-TRAINED MODEL REPRESENTATIONS AND THEIR ROBUSTNESS AGAINST NOISE

FOR SPEECH EMOTION ANALYSIS
Vikramjit Mitra (Apple Inc.)*; Vasudha Kowtha (Apple); Hsiang-Yun Sherry Chien (Apple); Erdrin Azemi
(Apple); Carlos Avendano (Apple)

2167: Contrastive Learning of Sentence Embeddings in Product Search

Bo-Wen Zhang (Beijing Academy of Artificial Intelligence)*; Yan Yan (CUMTB); Jiapei Yu (Alibaba Group)

2168: Boosting BERT Subnets with Neural Grafting

Ting Hu (Hasso Plattner Institute)*; Christoph Meinel (Hasso Plattner Institute); Haojin Yang (Hasso-
Plattner-Institut für Digital Engineering gGmbH)

2179: Automatic Severity Classification of Dysarthric speech by using Self-supervised Model with
Multi-task Learning
Eun Jung Yeo (Seoul National University)*; Kwanghee Choi (Sogang University); Sunhee Kim (Seoul
National University); Minhwa Chung (Seoul National University)

192
2181: A Slot-shared Span Prediction-based Neural Network for Multi-Domain Dialogue State
Tracking
Abibulla Atawulla (University of Chinese Academy of Sciences)*; Xi Zhou (Xinjiang Technical Institute of
Physics & Chemistry, Chinese Academy of Sciences); Yating Yang (Xinjiang Technical Institute of Physics
& Chemistry, Chinese Academy of Sciences); Bo Ma (Xinjiang Technical Institute of Physics & Chemistry,
Chinese Academy of Sciences); Fengyi Yang (University of Chinese Academy of Sciences)

2190: CROSS-MODAL ADVERSARIAL CONTRASTIVE LEARNING FOR MULTI-MODAL RUMOR

DETECTION
Ting Zou (Soochow University)*; Zhong Qian (Soochow University); Peifeng Li (Soochow University);
Qiaoming Zhu (Soochow University)

2201: Towards Zero-Shot Personalized Table-to-Text Generation with Contrastive Persona

Distillation
Haolan Zhan (Monash University)*; Shaobo Cui (Tsinghua University); Xuming Lin (Alibaba Group);
Zhongzhou Zhao (Alibaba Group); Wei Zhou (Alibaba Group); Haiqing Chen (Alibaba Inc. )

2210: BECTRA: Transducer-based End-to-End ASR with BERT-Enhanced Encoder

Yosuke Higuchi (Waseda University)*; Tetsuji Ogawa (Waseda University); Tetsunori Kobayashi (Waseda
University); Shinji Watanabe (Carnegie Mellon University)

2212: InterMPL: Momentum Pseudo-Labeling with Intermediate CTC Loss

Yosuke Higuchi (Waseda University)*; Tetsuji Ogawa (Waseda University); Tetsunori Kobayashi (Waseda
University); Shinji Watanabe (Carnegie Mellon University)

2233: EmoDiff: Intensity Controllable Emotional Text-to-Speech with Soft-Label Guidance

Yiwei Guo (Shanghai Jiao Tong University)*; Chenpeng Du (Shanghai Jiao Tong University); Xie Chen
(Shanghai Jiaotong University); Kai Yu (Shanghai Jiao Tong University)

2237: Lego-Features: Exporting modular encoder features for streaming and deliberation ASR
Rami Botros (Google)*; Rohit Prabhavalkar (Google); Johan Schalkwyk (Google); Ciprian Chelba (Google
Research); Tara Sainath (Google); Françoise Beaufays (Google)

2240: SELF-SUPERVISED LEARNING WITH BI-LABEL MASKED SPEECH PREDICTION FOR

STREAMING MULTI-TALKER SPEECH RECOGNITION
Zili Huang (Johns Hopkins University)*; Zhuo Chen (Microsoft); Naoyuki Kanda (Microsoft); Jian Wu
(Microsoft); Yiming Wang (Microsoft Corporation); Jinyu Li (Microsoft); Takuya Yoshioka (Microsoft);
Xiaofei Wang (Microsoft Corp.); Peidong Wang (Microsoft)

2243: Cascading and Direct Approaches to Unsupervised Constituency Parsing on Spoken

Sentences
Yuan Tseng (National Taiwan University)*; Cheng-I Lai (MIT); Hung-yi Lee (National Taiwan University)

2255: TERMINOLOGY-AWARE MEDICAL DIALOGUE GENERATION

Chen Tang (University of Surrey)*; Hongbo Zhang (University of Sheffield); Tyler Loakman (The University
of Sheffield); Chenghua Lin (University of Sheffield); Frank Guerin (University of Surrey)

2267: Towards trustworthy phoneme boundary detection with autoregressive model and improved
evaluation metric
Hyeongju Kim (Supertone, Inc.)*; Hyeong-Seok Choi (Seoul National University)

2280: SHIFT TO YOUR DEVICE: DATA AUGMENTATION FOR DEVICE-INDEPENDENT SPEAKER

VERIFICATION ANTI-SPOOFING
Junhao Wang (Zhejiang University); Li Lu (Zhejiang University)*; Zhongjie Ba (Zhejiang University); Feng
Lin (Zhejiang University); Kui Ren (Zhejiang University)

193
2314: A FEW SHOT LEARNING OF SINGING TECHNIQUE CONVERSION BASED ON CYCLE
CONSISTENCY GENERATIVE ADVERSARIAL NETWORKS
Po-Wei Chen (National Tsing Hua University)*; Von-Wun Soo (nthu)

2342: Dual Path Modeling for Semantic Matching by Perceiving Subtle Conflicts
Chao Xue (Beihang University); Di Liang (Centre for Natural Language Processing, Meituan Inc., Beijing,
China)*; Sirui Wang (Centre for Natural Language Processing, Meituan Inc., Beijing, China); Jing Zhang
(Beihang University); Wei Wu (Centre for Natural Language Processing, Meituan Inc., Beijing, China)

2352: ITERATIVE SHALLOW FUSION OF BACKWARD LANGUAGE MODEL FOR END-TO-END

SPEECH RECOGNITION
Atsunori Ogawa (NTT Corporation)*; Takafumi Moriya (NTT); Naoyuki Kamo (NTT Corporation); Naohiro
Tawara (NTT); Marc Delcroix (NTT)

2372: SOURCE-FREE UNSUPERVISED DOMAIN ADAPTATION FOR QUESTION ANSWERING

Zishuo Zhao (Sun Yat-Sen University)*; Yuexiang Xie (Alibaba Group); Jingyou Xie (Sun Yat-sen
University); Zhenzhou Lin (Sun Yat-sen University); Yaliang Li (Alibaba Group); Ying Shen (Sun Yat-Sen
University)

2397: Unsupervised model-based speaker adaptation of end-to-end lattice-free MMI model for
speech recognition
Xurong Xie (Institute of Software, Chinese Academy of Sciences)*; Xunying Liu (The Chinese University
of Hong Kong); Hui Chen (Institute of Software, Chinese Academy of Sciences); Hongan Wang (Institute
of Software, Chinese Academy of Sciences)

2400: Query-Utterance Attention with Joint modeling for Query-Focused Meeting Summarization
Xingxian Liu (Beijing University of Posts and Telecommunications); Bin Duan (Beijing University of Posts
and Telecommunications); Bo Xiao (Beijing University of Posts and Telecommunications); Yajing Xu
(Beijing University of Posts and Telecommunications)*

2409: SLOT-TRIGGERED CONTEXTUAL BIASING FOR PERSONALIZED SPEECH RECOGNITION

USING NEURAL TRANSDUCERS
Sibo Tong (Amazon)*; Philip Harding (Amazon Alexa); Simon Wiesler (Amazon)

2417: Hierarchical Softmax for End-to-End Low-resource Multilingual Speech Recognition

Qianying Liu (Kyoto University)*; Zhuo Gong (The University of Tokyo); Zhengdong Yang (Kyoto
University); Yuhang Yang (School of Information Science and Engineering, Xinjiang University, China);
Sheng Li (National Institute of Information & Communications Technology (NICT)); Chenchen Ding ();
Nobuaki Minematsu (The University of Tokyo); Hao Huang (Xinjiang University); Fei Cheng (Kyoto
University); Chenhui Chu (Kyoto University); Sadao Kurohashi (Kyoto University)

2423: Parameter-efficient Transfer Learning of Pre-trained Transformer Models for Speaker

Verification using Adapters
Junyi Peng (Brno University of Technology)*; Themos Stafylakis (Omilia - Conversational Intelligence);
rongzhi gu (Tencent); Oldrich Plchot (Brno University of Technology ); Ladislav Mosner (Brno
University of Technology); Lukas Burget (Brno University of Technology); Jan Cernocky (Brno University
of Technology)

2426: A Dynamic Graph Interactive Framework with Label-Semantic Injection for Spoken
Language Understanding
Zhihong Zhu (Peking University)*; Weiyuan Xu (Peking University); Xuxin Cheng (Peking University);
Tengtao Song (Peking University); Yuexian Zou (Peking University)

194
2433: TOWARDS DOMAIN GENERALISATION IN ASR WITH ELITIST SAMPLING AND ENSEMBLE
KNOWLEDGE DISTILLATION
Rehan Ahmad (University of Sheffield)*; Md Asif Jalal (Samsung Research UK); Muhammad Umar
Farooq (University of Sheffield); Anna L Ollerenshaw (University of Sheffield); Thomas Hain (University of
Sheffield)

2456: Adversarial Data Augmentation Using VAE-GAN for Disordered Speech Recognition
Zengrui Jin (The Chinese University of Hong Kong)*; Xurong Xie (Institute of Software, Chinese Academy
of Sciences); Mengzhe GENG (The Chinese University of Hong Kong); Tianzi Wang (The Chinese
University of HongKong); Shujie HU (The Chinese University of Hong Kong); Jiajun Deng (The Chinese
University of HongKong); Guinan Li (Chinese University of HongKong); Xunying Liu (The Chinese
University of Hong Kong)

2478: CUMULATIVE ATTENTION BASED STREAMING TRANSFORMER ASR WITH INTERNAL

LANGUAGE MODEL JOINT TRAINING AND RESCORING
Mohan LI (Toshiba Europe Ltd)*; Cong-Thanh Do (Toshiba Research Europe Ltd.); Rama S Doddipatla
(Toshiba Europe LTD)

2485: Cross-Modal Audio-Visual Co-learning for Text-independent Speaker Verification

Meng Liu (Tianjin University); Kong Aik Lee (Institute for Infocomm Research, A*STAR); Longbiao Wang
(Tianjin University)*; Hanyi Zhang (Tianjin University); Chang Zeng (National Institute of Informatics);
Jianwu Dang (School of Computer Science and Technology, Tianjin University, Tianjin, China; School of
Information Science, Japan Advanced Institute of Science and Technology, Ishikawa, Japan)

2490: Multi-Scale Receptive Field Graph Model for Emotion Recognition in Conversations
JIE WEI (Xi'an Jiaotong University)*; Guanyu Hu (Xi'an Jiaotong University); Anh Tuan Luu (Nanyang
Technological University); Xinyu Yang (Xi'an Jiaotong University); WenJing Zhu (DXM)

2499: LA-VocE: Low-SNR Audio-visual Speech Enhancement using Neural Vocoders

Rodrigo Mira (Imperial College London)*; Buye Xu (Meta Reality Labs Research ); Jacob Donley
(Facebook); Anurag Kumar (Meta Reality Labs Research); Stavros Petridis (Imperial College London /
Meta); Vamsi Krishna Ithapu (Meta Reality Labs Research); Maja Pantic (Imperial College London / Meta)

2508: Cross-speaker Emotion Transfer by Manipulating Speech Style Latents

Suhee Jo (Neosapience, Inc.)*; Younggun Lee (Neosapience); Yookyung Shin (Neosapience, Inc.);
Yeongtae Hwang (Neosapience, Inc.); Taesu Kim (Neosapience, Inc.)

2522: Privacy-preserving Automatic Speaker Diarization

Francisco Teixeira (INESC-ID/IST, University of Lisbon)*; Alberto Abad (INESC-ID); Bhiksha Raj
(Carnegie Mellon University); Isabel Trancoso (INESC ID)

2552: PROMPT MAKES MASK LANGUAGE MODELS BETTER ADVERSARIAL ATTACKERS

He Zhu (Institute of Information Engineering,Chinese Academy of Sciences)*; Ce Li (Institute of
Information Engineering,Chinese Academy of Sciences); haitian yang (Institute of Information
Engineering,Chinese Academy of Sciences); Yan Wang (Institute of Information Engineering,Chinese
Academy of Sciences); Weiqing Huang (Institute of Information Engineering, Chinese Academy of
Sciences)

2566: Towards Polymorphic Adversarial Examples Generation for Short Text

Yuhang Liang (University of Chinese Academy of Science)*; Zheng Lin (iie); Fengcheng Yuan
(UCAS,IIE); Hanwen Zhang (UCAS, IIE); Lei Wang (Institute of Information Engineering, Chinese
Academy of Sciences); Weiping Wang (Institute of Information Engineering, CAS, China)

195
2573: LEARNING ROBUST SELF-ATTENTION FEATURES FOR SPEECH EMOTION RECOGNITION
WITH LABEL-ADAPTIVE MIXUP
Lei Kang (Shantou University)*; Lichao Zhang (Air Force Engineering University); Dazhi Jiang (Shantou
University)

2575: AN ANALYSIS OF DEGENERATING SPEECH DUE TO PROGRESSIVE DYSARTHRIA ON ASR

PERFORMANCE
Katrin Tomanek (Google)*; Katie Seaver (Google); Pan-Pan Jiang (Google); RIchard Cave (Google);
Lauren Harrell (Google); Jordan Green (MGH Institute of Health Professions)

2594: Cross-domain Diffusion based Speech Enhancement for Very Noisy Speech
Heming Wang (The Ohio State University)*; DeLiang Wang (Ohio State University)

2608: Spectral Clustering-aware Learning of Embeddings for Speaker Diarisation

Evonne Lee (University of Cambridge); Guangzhi Sun (University of Cambridge Department of
Engineering)*; Chao Zhang (Tsinghua University); Phil Woodland (Machine Intelligence Laboratory,
Cambridge University Department of Engineering)

2609: IMPROVEMENTS TO EMBEDDING-MATCHING ACOUSTIC-TO-WORD ASR USING MULTIPLE-

HYPOTHESIS PRONUNCIATION-BASED EMBEDDINGS
Hao Yen (Georgia Institute of Technology); Woojay Jeon (Apple)*

2615: Adaptive End-pointing with Deep Contextual Multi-armed Bandits

Do June Min (University of Michigan)*; Andreas Stolcke (Amazon); Anirudh Raju (Amazon Alexa); Colin
Vaz (Amazon); Di He (Amazon Alexa); Venkatesh Ravichandran (Amazon); Viet Anh Trinh (Amazon)

2616: DYNAMIC SPEECH ENDPOINT DETECTION WITH REGRESSION TARGETS

Dawei Liang (UT Austin)*; Hang Su (Meta Platforms Inc); Tarun Singh (Meta Platforms Inc); Jay
Mahadeokar (Meta Platforms Inc); Shanil Puri (Meta Platforms Inc); Jiedan Zhu (Meta Platforms Inc);
Edison Thomaz (The University of Texas at Austin); Mike Seltzer (Meta Platforms Inc)

2619: nVOC-22: A low cost Mel Spectrogram vocoder for mobile devices
Rakesh Iyer (Google Inc)*

2621: Training Large-Vocabulary Neural Language Models by Private Federated Learning for
Resource-Constrained Devices
Mingbin Xu (Apple); Congzheng Song (Apple)*; Ye Tian (Apple); Neha Agrawal (Apple); Filip Granqvist
(Apple); Rogier C van Dalen (Samsung AI Center, Cambridge, UK); Xiao Zhang (Apple); Arturo Argueta
(Apple); Shiyi Han (Apple); Yaqiao Deng (Apple); Leo Liu (Apple); Anmol Walia (Apple); Alex Jin (Apple)

2624: Self-supervised Representations for Singing Voice Conversion

Tejas Jayashankar (MIT)*; Jilong Wu (Meta Platforms Inc.); Leda Sari (Meta Platforms Inc.); David Kant
(Meta Platforms Inc.); Vimal Manohar (Meta Platforms Inc. ); Qing He (Meta)

2625: Improving Speech Prosody of Audiobook Text-to-Speech Synthesis with Acoustic and
Textual Contexts
Detai Xin (The University of Tokyo)*; Sharath Adavanne (Rakuten Inc.); Federico Ang (Rakuten Inc.);
Ashish Kulkarni (Rakuten); Shinnosuke Takamichi (The University of Tokyo); Hiroshi Saruwatari (The
University of Tokyo)

2640: A UNIFIED ONE-SHOT PROSODY AND SPEAKER CONVERSION SYSTEM WITH SELF-
SUPERVISED DISCRETE SPEECH UNITS
Li-Wei Chen (Carnegie Mellon University)*; Shinji Watanabe (Carnegie Mellon University); Alexander I.
Rudnicky (Carnegie Mellon University)

196
2642: Phoneme-Level BERT for Enhanced Prosody of Text-to-Speech with Grapheme Predictions
Yinghao A Li (Columbia University)*; Cong Han (Columbia Univeristy); Xilin Jiang (Columbia University);
Nima Mesgarani (Columbia University)

2643: Conformer-based Target-Speaker Automatic Speech Recognition for Single-Channel Audio

Yang Zhang (NVIDIA)*; Krishna C Puvvada (NVIDIA); Vitaly Lavrukhin (NVIDIA); Boris Ginsburg (NVIDIA)

2661: QUANTITATIVE EVIDENCE ON OVERLOOKED ASPECTS OF ENROLLMENT SPEAKER

EMBEDDINGS FOR TARGET SPEAKER SEPARATION
Xiaoyu Liu (Dolby Laboratories)*; Xu Li (Dolby Laboratories); Joan Serra (Dolby Laboratories)

2665: Speaker Change Detection for Transformer Transducer ASR

Jian Wu (Microsoft)*; Zhuo Chen (Microsoft); Min Hu (Microsoft); Xiong Xiao (Microsoft); Jinyu Li
(Microsoft)

2671: Bridging Speech and Text Pre-trained Models with Unsupervised ASR
Jiatong Shi (Carnegie Mellon University)*; Chan-Jan Hsu (National Taiwan University); ho lam Chung
(National Taiwan University); Dongji Gao (Johns Hopkins University); Paola Garcia (Johns Hopkins
University); Shinji Watanabe (Carnegie Mellon University); Ann Lee (Meta, lnc.); Hung-yi Lee (National
Taiwan University)

2676: Improving BERT Fine-tuning via Stabilizing Cross-layer Mutual Information

Jicun Li (1. Key Laboratory of Intelligent Information Processing, Institute of Computing Technology,
Chinese Academy of Sciences (ICT/CAS) 2. University of Chinese Academy of Sciences, Beijing, China);
Xingjian Li (1. Big Data Lab, Baidu Research; 2. State Key Lab of IOTSC, University of Macau); Tianyang
Wang (University of Alabama at Birmingham); Shi Wang (* 1. Key Laboratory of Intelligent Information
Processing, Institute of Computing Technology, Chinese Academy of Sciences (ICT/CAS) * 2. University
of Chinese Academy of Sciences, Beijing, China)*; Yanan Cao (Institute of Information Engineering,
Chinese Academy of Sciences); Cheng-Zhong Xu (University of Macau); Dejing Dou (Baidu)

2677: Accelerating RNN-T Training and Inference Using CTC guidance

Yongqiang Wang (Google)*; Zhehuai Chen (Google); Chengjian Zheng (Google); Yu Zhang (Google); Wei
Han (Google); Parisa Haghani (Google)

2679: Virtuoso: Massive Multilingual Speech-Text Joint Semi-Supervised Learning for Text-to-
Speech
Takaaki Saeki (The University of Tokyo)*; Heiga Zen (Google); Zhehuai Chen (Google); Nobuyuki
Morioka (Google); Yuan Wang (Google); Yu Zhang (Google); Ankur Bapna (Google Research); Andrew
Rosenberg (Google LLC); Bhuvana Ramabhadran (Google)

2681: DASA: Difficulty-Aware Semantic Augmentation for Speaker Verification

Yuanyuan Wang (Tsinghua University)*; Yang Zhang (Tsinghua University); Zhiyong Wu (Tsinghua
University); Zhihan Yang (tsinghua); Tao Wei (Ping An Technology); Kun Zou (Ping An Technology );
Helen Meng (The Chinese University of Hong Kong)

2687: Augmenting Transformer-Transducer Based Speaker Change Detection With Token-Level

Training Loss
Guanlong Zhao (Google)*; Quan Wang (Google); Han Lu (Google); Yiling Huang (Google); Ignacio Lopez
Moreno (Google)

2693: TAPLoss: A Temporal Acoustic Parameter Loss for Speech Enhancement

Yunyang Zeng (Carnegie Mellon University)*; Joseph Konan (Carnegie Mellon University); Shuo Han
(Carnegie Mellon University); Muqiao Yang (Carnegie Mellon University); David Bick (Carnegie Mellon
University); Anurag Kumar (Facebook Research); Shinji Watanabe (Carnegie Mellon University); Bhiksha
Raj (Carnegie Mellon University)

197
2700: Improving CTC-based ASR Models with Gated Interlayer Collaboration
Yuting Yang (NetEase Yidun AI Lab)*; Yuke Li (NetEase Yidun AI Lab); Binbin Du (NetEase Yidun AI Lab)

2702: Reducing Language Confusion for Code-switching Speech Recognition with Token-level
Language Diarization
Hexin Liu (Nanyang Technological University)*; Haihua Xu (Temasek Laboratories, Nanyang
Technological University, Singapore); Paola Garcia (Johns Hopkins University); Andy W H Khong
(Nanyang Technological University); Yi He (Bytedance); Sanjeev Khudanpur (Johns Hopkins University)

2712: HIERARCHICAL NETWORK WITH DECOUPLED KNOWLEDGE DISTILLATION FOR SPEECH

EMOTION RECOGNITION
Ziping Zhao (Tianjin Normal University); Huan Wang (Tianjin Normal University)*; Haishuai Wang
(Zhejiang University); Prof. Dr. Bjoern Schuller (Imperial College London)

2715: ZERO-SHOT PERSONALIZED LIP-TO-SPEECH SYNTHESIS WITH FACE IMAGE BASED

VOICE CONTROL
Zheng-Yan Sheng (University of Science and Technology of China)*; Yang Ai (University of Science and
Technology of China); Zhen-Hua Ling (University of Science and Technology of China)

2721: Speech reconstruction from silent tongue and lip articulation by pseudo target generation
and domain adversarial training
Rui-Chen Zheng (University of Science and Technology of China)*; Yang Ai (University of Science and
Technology of China); Zhen-Hua Ling (University of Science and Technology of China)

2729: PROSODY-AWARE SPEECHT5 FOR EXPRESSIVE NEURAL TTS

Yan Deng (Microsoft)*; Long Zhou (Microsoft Research Asia); Yuanhao Yi (Microsoft); Shujie Liu
(Microsoft Research Asia); Lei He (Microsoft Cloud and AI)

2756: Auxiliary Pooling Layer For Spoken Language Understanding

Yukun Ma (Alibaba Group)*; Trung Hieu Nguyen (Alibaba Group); Jinjie Ni (Nanyang Technological
University); Wen Wang (Alibaba Group); Qian Chen (Speech Lab, DAMO Academy, Alibaba Group);
Chong Zhang (Alibaba Group); Bin Ma ("Alibaba, Singapore R&D Center")

2768: Adaptive Knowledge Distillation between Text and Speech Pre-trained Models
Jinjie Ni (Nanyang Technological University)*; Yukun Ma (Alibaba Group); Wen Wang (Alibaba Group);
Qian Chen (Speech Lab, DAMO Academy, Alibaba Group); Dianwen Ng (Alibaba Group/Nanyang
Technological University); HAN LEI (Nanyang Technological University); Trung Hieu Nguyen (Alibaba
Group); Chong Zhang (Alibaba Group); Bin Ma ("Alibaba, Singapore R&D Center"); Erik Cambria
(Nanyang Technological University, Singapore)

2772: Picking the Underused Heads: A Network Pruning Perspective of Attention Head Selection
for Fusing Dialogue Coreference Information
Zhengyuan Liu (A*STAR)*; Nancy Chen (Institute for Infocomm Research)

2775: LIMI-VC: A LIGHT WEIGHT VOICE CONVERSION MODEL WITH MUTUAL INFORMATION
DISENTANGLEMENT
Liangjie Huang (Beijing Language and Culture University); Tian Yuan (Baidu (China) Co., Ltd); Yunming
Liang (Baidu (China) Co., Ltd); Zeyu Chen (Baidu, Inc.); Can Wen (Baidu (China) Co., Ltd); Yanlu Xie
(Beijing Language and Culture University); Jinsong Zhang (Beijing Language and Culture University);
dengfeng ke (blcu.edu.cn)*

2778: SELECTIVE FILM CONDITIONING WITH CTC-BASED ASR PROBABILITY FOR SPEECH
ENHANCEMENT
Da-Hee Yang (Hanyang University); Joon-Hyuk Chang (Hanyang University)*

198
2788: CLICKER: Attention-Based Cross-Lingual Commonsense Knowledge Transfer
Ruolin Su (Georgia Institute of Technology)*; Zhongkai Sun (Amazon Alexa AI); Sixing Lu (Amazon);
chengyuan ma (amazon); Chenlei Guo (Amazon)

2793: SPTEAE: A SOFT PROMPT TRANSFER MODEL FOR ZERO-SHOT CROSS-LINGUAL EVENT
ARGUMENT EXTRACTION
Huipeng Ma (National Computer System Engineering Research Institute of China)*; qiu tang (National
Computer System Engineering Research Institute of China); ni zhang (National Computer System
Engineering Research Institute of China ); Rui Xu (National Computer System Engineering Research
Institute of China); Yanhua Shao (National Computer System Engineering Research Institute of China);
Wei Yan (National Computer System Engineering Research Institute of China); Yaojun Wang (China
Agricultural University)

2803: CONVOLUTION-BASED CHANNEL-FREQUENCY ATTENTION FOR TEXT-INDEPENDENT

SPEAKER VERIFICATION
Jingyu Li (The Chinese University of Hong Kong)*; Yusheng Tian (The Chinese University of Hong Kong);
Tan Lee (The Chinese University of Hong Kong)

2832: MULTI-SPEAKER EXPRESSIVE SPEECH SYNTHESIS VIA MULTIPLE FACTORS

DECOUPLING
Xinfa Zhu (Northwestern Polytechnical University)*; Yi Lei (Northwestern Polytechnical University); Kun
Song (Northwestern Polytechnical University); yongmao zhang (Audio, Speech and Language Processing
Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University, Xi’an, China);
Tao Li (School of Computer Science, Northwestern Polytechnical University, Xi’an); Lei Xie (NWPU)

2833: MULTI-SPEAKER AND WIDE-BAND SIMULATED CONVERSATIONS AS TRAINING DATA FOR

END-TO-END NEURAL DIARIZATION
Federico Landini (Brno University of Technology)*; Mireia Diez (Brno University of Technology); Alicia
Lozano-Diez (Universidad Autonoma de Madrid); Lukáš Burget (Brno University of Technology)

2840: PROCTER: PRONUNCIATION-AWARE CONTEXTUAL ADAPTER FOR PERSONALIZED

SPEECH RECOGNITION IN NEURAL TRANSDUCERS
Rahul Pandey (George Mason University); Roger Ren (Amazon)*; Qi Luo (Amazon.com Inc.); Jing Liu
(Amazon.com); Ariya Rastrow (Amazon Alexa); Ankur Gandhe (Amazon Alexa); Denis Filimonov
(Amazon); Grant Strimel (Amazon); Andreas Stolcke (Amazon); Ivan Bulyko (Amazon)

2842: BEBERT: Efficient and Robust Binary Ensemble BERT

Jiayi Tian (Nanjing University)*; Chao Fang (Nanjing University); Haonan Wang (University of Southern
California); Zhongfeng Wang (Nanjing University)

2850: ATTENTION LOCALNESS IN SHARED ENCODER-DECODER MODEL FOR TEXT

SUMMARIZATION
Li Huang (Southwestern University of Finance and Economics)*; Hongmei Wu (Southwestern University
of Finance and Economics); Qiang Gao (Southwestern University of Finance and Economics); Guisong
Liu (Southwestern University of Finance and Economics)

2862: Improving learning objectives for speaker verification from the perspective of score
comparison
Min Hyun Han (Seoul National University)*; Sung Hwan Mun (Seoul National University); Minchan Kim
(Seoul National University); Myeonghun Jeong (Seoul National University); Sunghwan Ahn (Seoul
National University); Nam Soo Kim (Seoul National University)

2864: ADAPTER TUNING WITH TASK-AWARE ATTENTION MECHANISM

Jinliang Lu (Institute of Automation，Chinese Academy of Sciences)*; Feihu Jin (Institute of Automation
，Chinese Academy of Sciences); Jiajun Zhang (Institute of Automation Chinese Academy of Sciences)

199
2865: Twitter Stance Detection via Neural Production Systems
Bowen Zhang (Shenzhen Technology University)*; Daijun Ding (Shenzhen Technology University);
Guangning Xu (Harbin Institute of Technology, Shenzhen ▲); Jinjin Guo (JD Intelligent Cities Research);
Zhichao Huang (JD Intelligent Cities Research); Xu Huang (Harbin Institute of Technology, Shenzhen)

2884: MULTIPLE CONTRASTIVE LEARNING FOR MULTIMODAL SENTIMENT ANALYSIS

Xiaocui Yang (Northeastern University)*; Shi Feng (Northeastern University); Daling Wang (Northeastern
University); Pengfei Hong (Singapore University of Technology and Design); Soujanya Poria (Singapore
University of Technology and Design)

2888: Unsupervised Fine-Tuning Data Selection for ASR Using Self-Supervised Speech Models
Reem A Gody (The University of Texas at Austin)*; David Harwath (The University of Texas at Austin)

2889: PCF: ECAPA-TDNN with Progressive Channel Fusion for Speaker Verification
Zhenduo Zhao (Institute of Acoustics, Chinese Academy of Sciences)*; Zhuo Li (Key Laboratory of
Speech Acoustics and Content Understanding,Institute of Acoustics, Chinese Academy of Sciences);
Wenchao Wang (Key Laboratory of Speech Acoustics and Content Understanding, Institute of Acoustics,
Chinese Academy of Sciences, Beijing, China); pengyuan zhang (Institute of Acoustics, Chinese
Academy of Sciences)

2892: Short-segment speaker verification using ECAPA-TDNN with multi-resolution encoder

Sangwook Han (GIST)*; Youngdo Ahn (GIST); Kyeognmuk Kang (GIST); Jong Won Shin (Gwangju
Institute of Science and Technology)

2899: Inter-SubNet: Speech Enhancement with Subband Interaction

Jun Chen (Tsinghua University)*; Wei Rao (Tencent); Zilin Wang (Tsinghua University); Jiuxin Lin
(Tsinghua University); Zhiyong Wu (Tsinghua University); Yannan Wang (Tencent); Shi-dong Shang
(tencent); Helen Meng (The Chinese University of Hong Kong)

2945: AutoTTS: End-to-End Text-to-Speech Synthesis through Differentiable Duration Modeling

Bac Nguyen (Sony Europe B.V.)*; Fabien Cardinaux (Sony European Technology Center); Stefan Uhlich
(Sony European Technology Center)

2963: CROSS-MODAL FUSION TECHNIQUES FOR UTTERANCE-LEVEL EMOTION RECOGNITION

FROM TEXT AND SPEECH
JIACHEN LUO (Queen Mary University of London)*; Huy Phan (Amazon Alexa); Joshua D. Reiss (Queen
Mary University of London)

2977: Integrating Syntactic and Semantic Knowledge in AMR Parsing with Heterogeneous Graph
Attention Network
Yikemaiti Sataer (Southeast University)*; Chuanqi Shi (Southeast University); Miao Gao (Southeast
University); Yunlong Fan (Southeast University); Bin Li (Southeast University); Zhiqiang Gao (Southeast
University)

2982: Multitask Detection of Speaker Changes, Overlapping Speech and Voice Activity Using
wav2vec 2.0
Marie Kunešová (University of West Bohemia)*; Zbyněk Zajíc ( University of West Bohemia)

2990: Using Auxiliary Tasks In Multimodal Fusion Of Wav2vec 2.0 And BERT For Multimodal
Emotion Recognition
Dekai Sun (Harbin Institute of Technology)*; yancheng He (Harbin Institute of Technology); jiqing Han
(Harbin Institute of Technology)

200
3001: Towards Reducing Patient Effort for the Automatic Prediction of Speech Intelligibility in
Head and Neck Cancers
Sebastião Quintas (IRIT, Université de Toulouse, CNRS, Toulouse, France)*; Alberto Abad (INESC-ID);
Julie Mauclair (IRIT); Virginie Woisard (Hospitals of Toulouse); Julien Pinquier (IRIT)

3017: SkillNet-NLG: General-Purpose Natural Language Generation with a Sparsely Activated

Approach
Junwei Liao (University of Electronic Science and Technology of China)*; Duyu Tang (Tencent); Fan
Zhang (Tianjin University); Shuming Shi (Tsinghua University)

3023: Multi-task Transformer with Relation-attention and Type-attention for Named Entity
Recognition
Ying Mo (Beihang University)*; Hongyin Tang (Meituan); Jiahao Liu (Meituan); Qifan Wang (Meta AI);
Zenglin Xu (Harbin Institute of Technology, Shenzhen); Jingang Wang (Meituan); Wei Wu (Meituan);
Zhoujun Li (Beihang University)

3026: DECOUPLED NON-PARAMETRIC KNOWLEDGE DISTILLATION FOR END-TO-END SPEECH

TRANSLATION
Hao Zhang (University of Information Engineering)*; Nianwen Si (University of Information Engineering);
Yaqi Chen (Information Engineering University); Wen-Lin Zhang (National Digital Switching System
Engineering and Technological R&D Center); Xukui Yang (ZZ Institute of Advance Technology); Dan Qu
(National Digital Switching System Engineering and Technological R&D Center); Zhen Li (University of
Information Engineering)

3033: UFO2: A unified pre-training framework for online and offline speech recognition
Li Fu (JD)*; Siqi Li (JD Technology); Qingtao Li (JD Technology); Liping Deng (JD Technology); Fangzhu
Li (JD Technology); fan lu (JD); Meng Chen (JD AI); Xiaodong He (JDT)

3035: LIGHTWEIGHT AND HIGH-FIDELITY END-TO-END TEXT-TO-SPEECH WITH MULTI-BAND

GENERATION AND INVERSE SHORT-TIME FOURIER TRANSFORM
Masaya Kawamura (The University of Tokyo)*; Yuma Shirahata (LINE Corp.); Ryuichi Yamamoto (LINE
Corp.); Kentaro Tachibana (LINE Corp.)

3038: Self-adaptive Incremental Machine Speech Chain for Lombard TTS with High-granularity
ASR Feedback in Dynamic Noise Condition
Sashi Novitasari (Nara Institute of Science and Technology)*; Sakriani Sakti (Japan Advanced Institute of
Science and Technology); Satoshi Nakamura (Nara Institute of Science and Technology, Japan)

3042: LongFNT: Long-form Speech Recognition with Factorized Neural Transducer

Xun Gong (Shanghai Jiaotong University)*; Yu Wu (Microsoft Research Asia); Jinyu Li (Microsoft); Shujie
Liu (Microsoft Research Asia); Rui Zhao (Microsoft); Xie Chen (Shanghai Jiaotong University); Yanmin
Qian (Shanghai Jiao Tong University)

3059: PUSHING THE LIMITS OF SELF-SUPERVISED SPEAKER VERIFICATION USING

REGULARIZED DISTILLATION FRAMEWORK
Yafeng Chen (Speech Lab, Alibaba Group)*; Siqi Zheng (Alibaba Group); Hui Wang (Speech Lab, Alibaba
Group); Luyao Cheng (Speech Lab, Alibaba Group); Qian Chen (Speech Lab, DAMO Academy, Alibaba
Group)

3063: A MULTI-SCALE FEATURE AGGREGATION BASED LIGHTWEIGHT NETWORK FOR AUDIO-

VISUAL SPEECH ENHANCEMENT
Haitao Xu ( University of Science and Technology of China)*; Liangfa Wei (Tencent); Jie Zhang
(University of Science and Technology of China); Jianming Yang (Tsinghua University); Yannan Wang
(Tencent); Tian Gao (University of Science and Technology of China); Xin Fang (iFlytek Research); Lirong
Dai (University of Science and Technology of China)

201
3066: Multi-lingual pronunciation assessment with unified phoneme set and language-specific
embeddings
Binghuai Lin (MIG, Tencent Science and Technology Ltd.); Liyuan wang (Tencent Technology Co., Ltd)*

3072: Robust multi-modal speech emotion recognition with ASR error adaptation
Binghuai Lin (MIG, Tencent Science and Technology Ltd.); Liyuan wang (Tencent Technology Co., Ltd)*

3083: Narrow Down Before Selection: A Dynamic Exclusion Model For Multiple-Choice QA
Xiyan Liu (Beijing University of Posts and Telecommunications); Yidong Shi (Beijing University of Posts
and Telecommunications); Ruifang Liu (Beijing University of Posts and Telecommunications)*; Ge Bai
(Beijing University of Posts and Telecommunications); Yanyi Chen (Beijing University of Posts and
Telecommunications)

3092: Multi-modal ASR error correction with joint ASR error detection
Binghuai Lin (MIG, Tencent Science and Technology Ltd.); Liyuan wang (Tencent Technology Co., Ltd)*

3093: Joint Modeling for ASR Correction and Dialog State Tracking
Deyuan Wang (Beijing University of Posts and Telecommunications)*; Tiantian Zhang (Beijing University
of Posts and Telecommunications); Caixia Yuan (Beijing University of Posts and Telecommunications);
Xiaojie Wang (Beijing University of Posts and Telecommunications)

3099: UNIFIED PROMPT LEARNING MAKES PRE-TRAINED LANGUAGE MODELS BETTER FEW-
SHOT LEARNERS
Feihu Jin (Institute of Automation ，Chinese Academy of Sciences)*; Jinliang Lu (Institute of Automation
，Chinese Academy of Sciences); Jiajun Zhang (Institute of Automation Chinese Academy of Sciences)

3129: Multi-Local Attention for Speech-based Depression Detection

Fuxiang Tao (University of Glasgow)*; Xuri Ge (University of Glasgow); Wei Ma (University of Glasgow);
Anna Esposito (Università di Napol (Italy)); Alessandro. Vinciarelli (UNiversity of Glasgow)

3130: DAILY MENTAL HEALTH MONITORING FROM SPEECH: A REAL-WORLD JAPANESE

DATASET AND MULTITASK LEARNING ANALYSIS
Meishu Song (University of Augsburg)*; Andreas Triantafyllopoulos (University of Augsburg); Zijiang Yang
(University of Augsburg); Hiroki Takeuchi (University of Tokyo); Toru Nakamura (Osaka University );
Akifumi Kishi (University of Tokyo); Tetsro Ishizawa (University of Tokyo); Kazuhiro Yoshiuchi (University
of Tokyo); Xin Jing (Universität Augsburg); Zhonghao Zhao (Beijing Institute of Technology); Vincent
Karas (University of Augsburg); Kun Qian (Beijing Institute of Technology); Bin Hu (Beijing Institute of
Technology); Bjorn W. Schuller (Imperial College London); Yamamoto Yoshiharu (University of Tokyo)

3135: JOINT PRE-TRAINING WITH SPEECH AND BILINGUAL TEXT FOR DIRECT SPEECH TO
SPEECH TRANSLATION
Kun Wei (School of Computer Science, Northwestern Polytechnical University)*; Long Zhou (Microsoft
Research Asia); Ziqiang Zhang (University of Science and Technology of China); LIPING CHEN
(Microsoft); Shujie Liu (Microsoft Research Asia); Lei He (Microsoft Cloud and AI); Jinyu Li (Microsoft);
Furu Wei (Microsoft Research Asia)

3151: FINE-GRAINED EMOTIONAL CONTROL OF TEXT-TO-SPEECH: LEARNING TO RANK INTER-

AND INTRA-CLASS EMOTION INTENSITIES
Shijun Wang (University of St. Gallen)*; Jon Gudnason (Reykjavik University); Damian Borth (University
of St. Gallen)

3153: Sharing Low Rank Conformer Weights for Tiny Always-On Ambient Speech Recognition
Models
Steven M. Hernandez (Virginia Commonwealth University)*; Ding Zhao (Google); Shaojin Ding (Google);
Antoine Bruguier (Google); Rohit Prabhavalkar (Google); Tara Sainath (Google); Yanzhang He (Google);
Ian McGraw ()

202
3169: Improving Spoken Language Identification with Map-Mix
Shangeth Rajaa (skit.ai)*; Kriti Anandan (skit.ai); Swaraj Dalmia (skit.ai); Tarun Gupta (IIT Indore); Eng
Siong Chng (Nanyang Technological University)

3175: Unifying Speech Enhancement and Separation with Gradient Modulation for End-to-End
Noise-Robust Speech Separation
Yuchen Hu (Nanyang Technological University)*; Chen Chen (Nanyang Technological University); Heqing
Zou (Nanyang Technological University); Xionghu Zhong (Hunan University); Eng Siong Chng (Nanyang
Technological University)

3179: Speaker recognition with two-step multi-modal deep cleansing

Ruijie Tao (National University of Singapore)*; Kong Aik Lee (Institute for Infocomm Research, A*STAR);
Zhan Shi (Chinese University of Hong Kong, Shenzhen); Haizhou Li (The Chinese University of Hong
Kong, Shenzhen)

3189: TableIE: Capturing the Interactions among Sub-tasks in Information Extraction via Double
Tables
jiaxing lin (peking university)*; Runxin Xu (Peking University); Baobao Chang (Peking University)

3191: NNSVS: A Neural Network-Based Singing Voice Synthesis Toolkit

Ryuichi Yamamoto (LINE Corp.)*; Reo Yoneyama (Nagoya University); Tomoki Toda (Nagoya University)

3210: Frame-wise and overlap-robust speaker embeddings for meeting diarization

Tobias Cord-Landwehr (Paderborn University)*; Christoph B Boeddeker (Paderborn University); Catalin
Zorila (Toshiba Cambridge Research Laboratory); Rama S Doddipatla (Toshiba Europe LTD); Reinhold
Haeb-Umbach (University of Paderborn)

3227: STYLE MODELING FOR MULTI-SPEAKER ARTICULATION-TO-SPEECH

Miseul Kim (Yonsei University)*; Zhenyu Piao (Yonsei University); Jihyun Lee (yonsei university); Hong-
Goo Kang (Yonsei University)

3239: Multi-speaker Speech Synthesis from Electromyographic Signals by Soft Speech Unit
Prediction
Kevin Scheck (University of Bremen)*; Tanja Schultz (University of Bremen)

3241: Deep Subband Network for Joint Suppression of Echo, Noise and Reverberation in Real-
Time Fullband Speech Communication
Feifei Xiong (Alibaba Group)*; Minya Dong (Alibaba Group); Kechenying Zhou (Alibaba Group); Houwei
Zhu (Alibaba Group); Jinwei Feng (Alibaba Group)

3250: CB-Conformer: Contextual Biasing Conformer for Biased Word Recognition

Yaoxun Xu (Tsinghua University)*; 刘 柏基 (XVerse); Qiaochu Huang (Tsinghua University); Xingchen
Song (Tsinghua University); Zhiyong Wu (Tsinghua University); Shiyin Kang (XVerse Inc.); Helen Meng
(The Chinese University of Hong Kong)

3252: SENER: Sentiment Element Named Entity Recognition for Aspect-based Sentiment Analysis
Sun-Kyung Lee (KAIST)*; Jong-Hwan Kim (KAIST)

3258: Domain Adaptation with External Off-Policy Acoustic Catalogs for Scalable Contextual End-
To-End Automated Speech Recognition
David Chan (University of California, Berkeley)*; Shalini Ghosh (Amazon Alexa AI); Ariya Rastrow
(Amazon Alexa); Bjorn Hoffmeister (Amazon)

3275: Adaptive Multi-Corpora Language Model Training for Speech Recognition

Yingyi Ma (Meta)*; Zhe Liu (Meta); Xuedong Zhang (Meta)

203
3286: An End-to-End Neural Network for Image-to-Audio Transformation
Chen Liu (Oregon Health & Science University); Michael Deisher (Intel Corporation)*; Munir Georges
(Intel Corporation); Munir Georges (THI)

3292: HuBERT-AGG: Aggregated Representation Distillation of Hidden-unit BERT for Robust

Speech Recognition
wei wang (Shanghai Jiao Tong University)*; Yanmin Qian (Shanghai Jiao Tong University)

3303: Can spoofing countermeasure and speaker verification systems be jointly optimised?
Wanying Ge (EURECOM)*; Hemlata Tak (EURECOM); Massimiliano Todisco (EURECOM); Nicholas
Evans (EURECOM)

3343: Speech separation with large-scale self-supervised learning

Zhuo Chen (Microsoft)*; Naoyuki Kanda (Microsoft); Jian Wu (Microsoft); Yu Wu (Microsoft Research
Asia); Xiaofei Wang (Microsoft); Takuya Yoshioka (Microsoft); Jinyu Li (Microsoft); Sunit Sivasankaran
(Microsoft); Sefik Emre Eskimez (Microsoft)

3355: Fine-grained Textual Knowledge Transfer to Improve RNN Transducers for Speech
Recognition and Understanding
Vishal Sunder (The Ohio State University)*; Samuel Thomas (IBM Research AI); Jeff Kuo (IBM); Brian
Kingsbury (IBM Research); Eric Fosler-Lussier (Ohio State)

3365: JEIT: JOINT END-TO-END MODEL AND INTERNAL LANGUAGE MODEL TRAINING FOR
SPEECH RECOGNITION
Zhong Meng (Google LLC)*; Weiran Wang (Google); Rohit Prabhavalkar (Google); Tara Sainath
(Google); Tongzhou Chen (Google); Ehsan Variani (Google); Yu Zhang (Google); Bo Li (Google); Andrew
Rosenberg (Google LLC); Bhuvana Ramabhadran (Google)

3368: Variable Attention Masking for Configurable Transformer Transducer Speech Recognition
Pawel Swietojanski (Apple)*; Stefan Braun (Apple); Dogan Can (Apple); Thiago Fraga da Silva (Apple);
Arnab Ghoshal (Apple); Takaaki Hori (Apple); Roger Hsiao (Apple); Henry Mason (Apple); Erik
McDermott (Apple); Jan Silovsky (Apple); Ruchir Travadi (Apple); Xiaodan Zhuang (Apple)

3379: STUDY ON THE FAIRNESS OF SPEAKER VERIFICATION SYSTEMS ACROSS ACCENT AND
GENDER GROUPS
Mariel Estevez (CONICET / Universidad de Buenos Aires)*; Luciana Ferrer (CONICET / Universidad de
Buenos Aires)

3382: Resource-Efficient Transfer Learning From Speech Foundation Model Using Hierarchical
Feature Fusion
Zhouyuan Huo (Google )*; Khe C Sim (Google Inc.); Bo Li (Google); Dongseong Hwang (Google); Tara
Sainath (Google); Trevor Strohman (Google)

3385: Towards Accurate and Real-time End-of-speech Estimation

Yifeng Fan (University of Illinois at Urbana-Champaign)*; Colin Vaz (Amazon); Di He (Amazon); Jahn
Heymann (Amazon); Viet Anh Trinh (Amazon); Zhe Zhang (Amazon); Venkatesh Ravichandran (Amazon)

3390: Locale Encoding for scalable multilingual keyword spotting models

Pai Zhu (Google)*; Hyun Jin Park (Google Inc.); Alex Park (Google); Angelo Scorza Scarpati (Google);
Ignacio Lopez Moreno (Google)

3398: Adapting a self-supervised speech representation for noisy speech emotion recognition by
using contrastive teacher-student learning
Seong-Gyun Leem (University of Texas at Dallas); Daniel Fulford (Boston University); JP Onnela (T.H.
Chan School of Public Health Harvard University); David Gard (San Francisco State University); Carlos
Busso (University of Texas at Dallas)*

204
3399: Evidence of Vocal Tract Articulation in Self-Supervised Learning of Speech
Cheol Jun Cho (UC Berkeley)*; Peter Wu (UC Berkeley); Abdelrahman Mohamed (Meta); Gopala Krishna
Anumanchipalli (UC Berkeley)

3410: A Synthetic Corpus Generation Method for Neural Vocoder Training

Zilin Wang (Tsinghua University)*; peng liu (transsion); Jun Chen (Tsinghua University); Sipan Li
(Tsinghua University); Baijin Feng (TAL Education Group); He Gang (TAL Education Group); Zhiyong Wu
(Tsinghua University); Helen Meng (The Chinese University of Hong Kong)

3417: Accidental Learners: Spoken Language Identification in Multilingual Self-Supervised Models

Travis M Bartley (NVIDIA; CUNY)*; Fei Jia (NVIDIA Corporation); Krishna C Puvvada (NVIDIA); Samuel
Kriman (NVIDIA); Boris Ginsburg (NVIDIA)

3423: Leveraging Multiple Sources in Automatic African American English Dialect Detection for
Adults and Children
Alexander Johnson (UCLA)*; Vishwas Shetty (UCLA); Mari Ostendorf (University of Washington); Abeer
Alwan (UCLA)

3440: Text-to-speech synthesis based on latent variable conversion using diffusion probabilistic
model and variational autoencoder
Yusuke Yasuda (Nagoya university)*; Tomoki Toda (Nagoya University)

3453: Cross-Training: A Semi-Supervised Training Scheme for Speech Recognition

Soheil Khorram (Google Inc. USA)*; Anshuman Tripathi (Google); Jaeyoung Kim (Google); Han Lu
(Google Inc. USA); Qian Zhang (Google Inc. USA); Rohit Prabhavalkar (Google); Hasim Sak (Google)

3461: A mutual implicit sentiment analysis model with bundle-aware contrastive learning
siqi cai (Wuhan University of Technology)*; Jingling Yuan (Wuhan University of Technology); Lin Li
(Wuhan University of Technology)

3462: T5lephone: Bridging Speech and Text Self-supervised Models for Spoken Language
Understanding via Phoneme level T5
Chan-Jan Hsu (National Taiwan University)*; ho lam Chung (National Taiwan University); Hung-yi Lee
(National Taiwan University); Yu Tsao (Academia Sinica)

3463: Speech summarization of long spoken document: Improving memory efficiency of

speech/text encoders
Takatomo Kano (NTT Corporation)*; Atsunori Ogawa (NTT Corporation); Marc Delcroix (NTT); Roshan S
Sharma (Carnegie Mellon University); Kohei Matsuura (NTT); Shinji Watanabe (Carnegie Mellon
University)

3486: Framewise WaveGAN: High Speed Adversarial Vocoder in Time Domain with Very Low
Computational Complexity
Ahmed Mustafa (Amazon )*; Jean-Marc Valin (Amazon); Jan Büthe (Amazon); Paris Smaragdis
(Amazon); Michael M Goodwin (AWS )

3487: PROMPTTTS: CONTROLLABLE TEXT-TO-SPEECH WITH TEXT DESCRIPTIONS

Zhifang Guo (University of Chinese Academy of Sciences)*; Yichong Leng (University of Science and
Technology of China); Yihan Wu (Renmin University of China); sheng zhao (microsoft); Xu Tan (Microsoft
Research Asia)

3488: INTERMEDIATE FINE-TUNING USING IMPERFECT SYNTHETIC SPEECH FOR IMPROVING

ELECTROLARYNGEAL SPEECH RECOGNITION
Lester Phillip G Violeta (Nagoya University)*; Ding Ma (Nagoya University); Wen-Chin Huang (Nagoya
University); Tomoki Toda (Nagoya University)

205
3499: Factorized Blank Thresholding for Improved Runtime Efficiency of Neural Transducers
Duc Le (Meta)*; Frank Seide (Meta); Yuhao Wang (Meta); Yang Li (Meta); Kjell Schubert (Meta); Ozlem
Kalinli (Meta); Mike Seltzer (Meta)

3500: NONPARALLEL EMOTIONAL VOICE CONVERSION FOR UNSEEN SPEAKER-EMOTION

PAIRS USING DUAL DOMAIN ADVERSARIAL NETWORK & VIRTUAL DOMAIN PAIRING
Nirmesh J Shah (Sony Research India)*; Mayank Kumar Singh (Sony Research India); Naoya Takahashi
(Sony Group); Naoyuki Onoe (Sony)

3507: SELF-ADAPTIVE REASONING ON SUB-QUESTIONS FOR MULTI-HOP QUESTION

ANSWERING
ZeKai Li (National University of Singapore)*; Wei Peng (Institute of Information Engineering, Chinese
Academy of Sciences)

3511: Self-Supervised Learning-Based Source Separation for Meeting Data

Yuang Li (University of Cambridge)*; Xianrui Zheng (University of Cambridge); Phil Woodland (Machine
Intelligence Laboratory, Cambridge University Department of Engineering)

3522: Nonparallel High-Quality Audio Super Resolution with Domain Adaptation and Resampling
CycleGANs
Reo Yoneyama (Nagoya University)*; Ryuichi Yamamoto (LINE Corp.); Kentaro Tachibana (LINE Corp.)

3531: SMALL-FOOTPRINT SLIMMABLE NETWORKS FOR KEYWORD SPOTTING

Zuhaib Akhtar (Amazon )*; Mohammad Omar Khursheed (Amazon); Dongsu Du (AMAZON); Yuzong Liu
(Amazon)

3539: Does human speech follow Benford's Law?

Leo Hsu (Arizona State University); Visar Berisha (Arizona State University)*

3562: On Unsupervised Uncertainty-Driven Speech Pseudo-Label Filtering and Model Calibration

Nauman Dawalatabad (Massachusetts Institute of Technology)*; Sameer Khurana (Massachusetts
Institute of Technology); Antoine Laurent (Le Mans University); James Glass (Massachusetts Institute of
Technology)

3578: Dual-Attention Neural Transducers for Efficient Wake Word Spotting in Speech Recognition
Saumya Yashmohini Sahai (Amazon); Jing Liu (Amazon.com)*; Thejaswi Muniyappa (Amazon);
Kanthashree Mysore Sathyendra (Amazon); Anastasios Alexandridis (Amazon.com); Grant Strimel
(Amazon); Ross McGowan (Amazon); Ariya Rastrow (Amazon Alexa); Athanasios Mouchtaris (Amazon
Alexa); Feng-Ju Chang (Amazon); Siegfried Kunzmann (Amazon)

3600: Comparison of Soft and Hard Target RNN-T Distillation for Large-scale ASR
Dongseong Hwang (Google)*; Khe C Sim (Google Inc.); Yu Zhang (Google); Trevor Strohman (Google)

3613: LEVERAGING HETEROSCEDASTIC UNCERTAINTY IN LEARNING COMPLEX SPECTRAL

MAPPING FOR SINGLE-CHANNEL SPEECH ENHANCEMENT
Kuan-Lin Chen (University of California San Diego); Daniel D.E. Wong (Meta Platforms Inc.)*; Ke Tan
(Meta Platforms, Inc.); Buye Xu (Work); Anurag Kumar (Facebook Research); Vamsi Krishna K Ithapu
(Facebook Reality Labs)

3615: METRIC LEARNING FOR USER-DEFINED KEYWORD SPOTTING

Jaemin Jung (KAIST)*; Youkyum Kim (KAIST); Jihwan Park (42dot Inc.); Youshin Lim (42dot); Byeong-
Yeol Kim (42dot); Youngjoon Jang (KAIST); Joon Son Chung (KAIST)

3632: Hierarchical Pronunciation Assessment with Multi-Aspect Attention

Heejin Do (POSTECH)*; Yunsu Kim (POSTECH); Gary Geunbae Lee (Postech)

206
3633: Generic Dependency Modeling for Multi-Party Conversation
Weizhou Shen (Sun Yat-sen University); Xiaojun Quan (Sun Yat-sen University)*; Ke Yang (Sun Yat-sen
University)

3635: STATISTICAL ANALYSIS OF SPEECH DISORDER SPECIFIC FEATURES TO CHARACTERISE

DYSARTHRIA SEVERITY LEVEL
AMLU ANNA JOSHY (COLLEGE OF ENGINEERING TRIVANDRUM)*; P. N. PARAMESWARAN
(COLLEGE OF ENGINEERING TRIVANDRUM); Siddharth R. Nair (College of Engineering Trivandrum);
Rajeev Rajan (Government Engineering College, Barton Hill, Trivandrum)

3643: SRTNet: Time Domain Speech Enhancement Via Stochastic Refinement

Zhibin Qiu (XinJiang University)*; Mengfan Fu (XinJiang University); Yinfeng Yu (Department of Computer
Science and Technology, State Key Lab on Intelligent Technology and Systems, Tsinghua University,
Beijing, China;Xinjiang University); Lili Yin ( Xinjiang University); Fuchun Sun (Tsinghua University); Hao
Huang (Xinjiang University)

3648: {NASE: A Chinese Benchmark for Evaluating Robustness of Spoken Language

Understanding Models in Slot Filling
Meizheng Peng (Wuhan University)*; Xu Jia (Wuhan University); Min Peng (Wuhan University)

3656: Selecting Language Models Features via Software-Hardware Co-Design

Vlad Pandelea (Nanyang Technological University)*; Edoardo Ragusa (University of Genova); Paolo
Gastaldo (University of Genova); Erik Cambria (Nanyang Technological University, Singapore)

3666: token2vec: A Joint Self-Supervised Pre-training Framework Using Unpaired Speech and
Text
Xianghu Yue (National University of Singapore )*; Junyi Ao (The Chinese University of Hong Kong
(Shenzhen)); Xiaoxue Gao (National University of Singapore); Haizhou Li (The Chinese University of
Hong Kong (Shenzhen))

3687: NSV-TTS: NON-SPEECH VOCALIZATION MODELING AND TRANSFER IN EMOTIONAL TEXT-

TO-SPEECH
Haitong Zhang (Netease Games AI Lab)*; Xinyuan Yu (Netease Games AI Lab); Yue Lin (NetEase
Games AI Lab)

3692: Mitigating Domain Dependency for Improved Speech Enhancement via SNR Loss Boosting
Lili Yin ( Xinjiang University)*; Di Wu (Xinjiangdaxue); Zhibin Qiu (XinJiang University); Hao Huang
(Xinjiang University)

3695: A Topic-Enhanced Approach for Emotion Distribution Forecasting in Conversations

Xin Lu (Harbin Institute of Technology)*; Weixiang Zhao (Harbin Institute of Technology); Yanyan Zhao
(Harbin Institute of Technology); Bing Qin (Harbin Institute of Technology); Zhentao Zhang (CMB NT);
wen junjie (China Merchants Bank)

3712: Context-aware Fine-tuning of Self-supervised speech models

Suwon Shon (ASAPP)*; Felix Wu (ASAPP); Kwangyoun Kim (ASAPP); Prashant Sridhar (ASAPP); Karen
Livescu (TTI-Chicago); Shinji Watanabe (Carnegie Mellon University)

3714: DAIS: THE DELFT DATABASE OF EEG RECORDINGS OF DUTCH ARTICULATED AND
IMAGINED SPEECH
Bo Dekker (Department of Biomechanical Engineering, Delft University of Technology); Alfred Schouten
(Department of Biomechanical Engineering, Delft University of Technology); Odette Scharenborg
(Multimedia Computing Group, Delft University of Technology)*

207
3725: MHLAT: Multi-hop Label-wise Attention Model for Automatic ICD Coding
Junwen Duan (Central South University)*; Han Jiang (Central South University); Ying Yu (Central South
University)

3731: Weight Averaging: A Simple Yet Effective Method to Overcome Catastrophic Forgetting in
Automatic Speech Recognition
Steven Vander Eeckt (KU Leuven)*; Hugo Van hamme (KU LEUVEN)

3755: Fast Yet Effective Speech Emotion Recognition with Self-Distillation

Zhao Ren (L3S Research Center)*; Thanh Tam Nguyen (Griffith University); Yi Chang (Imperial College
London); Bjoern W. Schuller (Imperial College London)

3760: A Context-Aware Computational Approach for Measuring Vocal Entrainment in Dyadic

Conversations
Rimita Lahiri (University of Southern California)*; Md Nasir (Microsoft); Catherine Lord (UCLA); So Hyun
Kim (Korea University); Shrikanth Narayanan (USC)

3785: Disentangled and Robust Representation Learning for Bragging Classification in Social
Media
Xiang Li (Tianjin university)*; Yucheng Zhou (University of Technology Sydney)

3796: Hybrid Neural Network With Cross- and Self-Module Attention Pooling for Text-Independent
Speaker Verification
Jahangir Alam (Computer Research Institute of Montreal (CRIM), Montreal (Quebec) Canada)*;
Woohyun Kang (Amazon Web Services); Abderrahim Fathan (Computer Research Institute of Montreal
(CRIM), Montreal, Quebec, Canada)

3815: A BIDIRECTIONAL JOINT MODEL FOR SPOKEN LANGUAGE UNDERSTANDING

Nguyen Anh Tu (Posts and Telecommunications Institute of Technology); Duong Xuan Hieu (Posts and
Telecommunications Institute of Technology); Tu Minh Phuong (Posts and Telecommunications Institute of
Technology, Ha Noi, Vietnam); Ngo Xuan Bach (Posts and Telecommunications Institute of Technology,
Vietnam)*

3822: LEAPT: Learning Adaptive Prefix-to-prefix Translation For Simultaneous Machine

Translation
Lei Lin (Xiamen University)*; Shuangtao Li (Xiamen University); xiaodong shi (xiamen university)

3825: Discriminative Speaker Representation via Contrastive Learning with Class-Aware Attention
in Angular Space
Zhe LI (Hong Kong Polytechnic University)*; Man-Wai MAK (The Hong Kong Polytechnic University);
Helen Meng (The Chinese University of Hong Kong)

3830: SDTN: SPEAKER DYNAMICS TRACKING NETWORK FOR EMOTION RECOGNITION IN

CONVERSATION
Jiawei Chen (South China Agricultural University)*; Peijie Huang (South China Agricultural University);
Guotai Huang (South China Agricultural University); Qianer Li (South China Agricultural University);
Yuhong Xu (South China Agricultural University)

3840: Neural Diarization with Non-autoregressive Intermediate Attractors

Yusuke Fujita (LINE Corporation)*; Tatsuya Komatsu (LINE Corporation); Robin Scheibler (LINE
Corporation); Yusuke Kida (LINE Corp); Tetsuji Ogawa (Waseda University)

3852: DOMAIN AND LANGUAGE ADAPTATION USING HETEROGENEOUS DATASETS FOR

WAV2VEC2.0-BASED SPEECH RECOGNITION OF LOW-RESOURCE LANGUAGE
Kak Soky (Kyoto University)*; Sheng Li (National Institute of Information & Communications Technology
(NICT)); Chenhui Chu (Kyoto University); Tatsuya Kawahara (Kyoto University)

208
3859: MULTILEVEL TRANSFORMER FOR MULTIMODAL EMOTION RECOGNITION
Junyi He (360 DigiTech)*; Meimei Wu (360DigiTech); Meng Li (360 DigitalTech); Xiaobo Zhu
(360DigiTech); Feng Ye (360DigiTech, Inc.)

3864: Speaker-aware Hierarchical Transformer for Personality Recognition in Multiparty Dialogues

Wenjing Han (South China University of Technology)*; Yirong Chen (South China University of
Technology); Xiaofen Xing (South China University of Technology); Guohua Zhou (iFlytek South China AI
Institute(Guangzhou) Co.,Ltd ); Xiangmin Xu (South China University of Technology)

3866: Ensemble knowledge distillation of self-supervised speech models

Kuan-Po Huang (National Taiwan University)*; Tzu-hsun Feng (National Taiwan University); YU-KUAN
FU (NTU); Tsu-Yuan Hsu (National Taiwan University); Po-Chieh Yen (National Taiwan University); Wei-
Cheng Tseng (National Taiwan University); Kai-Wei Chang (National Taiwan University); Hung-yi Lee
(National Taiwan University)

3867: Enhancing and Adversarial: Improve ASR with Speaker Labels

Wei Zhou (RWTH Aachen University)*; Haotian Wu (RWTH Aachen University); Jingjing Xu (RWTH i6);
Mohammad Zeineldeen (RWTH Aachen University / AppTek); Christoph M. Lüscher (Informatik 6, RWTH
Aachen University); Ralf Schlüter (RWTH Aachen University); Hermann Ney ( RWTH Aachen
University)

3872: Lexicon-injected Semantic Parsing for Task-Oriented Dialog

Xiaojun Meng (Noah's Ark Lab, Huawei Technologies)*; Wenlin Dai (Tsinghua University); Yasheng Wang
(NoahArk Lab, Huawei); Baojun wang (Noah's Ark Lab of Huawei); Zhiyong Wu (Tsinghua University); Xin
Jiang (Huawei Noah's Ark Lab); Qun Liu (Huawei Noah's Ark Lab)

3881: Leveraging Large Text Corpora for End-to-End Speech Summarization

Kohei Matsuura (NTT)*; Takanori Ashihara (NTT Corp.); Takafumi Moriya (NTT); Tomohiro Tanaka (NTT);
Marc Delcroix (NTT); Atsunori Ogawa (NTT Corporation); Ryo Masumura (NTT Corporation)

3889: ENHANCING SPEECH-TO-SPEECH TRANSLATION WITH MULTIPLE TTS TARGETS

Jiatong Shi (Carnegie Mellon University)*; Yun Tang (Facebook); Ann Lee (Facebook, Inc.); Hirofumi
Inaguma (Meta AI); Changhan Wang (Facebook AI Research); Juan Miguel Pino (Facebook); Shinji
Watanabe (Carnegie Mellon University)

3896: Dynamic TF-TDNN: Dynamic Time Delay Neural Network based on Temporal-Frequency
Attention for Dialect Recognition
Chao Liao (Kuaishou)*; Jinwen Huang (Kuaishou Technology); Huan Yuan (Kuaishou Technology); Peng
Yao (Kuaishou Inc.); Jianchao Tan (Kwai Inc.); zhang dawei (Kuaishou Technology); Feng Deng
(Kuaishou); Xiaorui Wang (Kwai); Chengru Song (Kuaishou)

3917: Robust Knowledge Distillation from RNN-T Models With Noisy Training Labels Using Full-
Sum Loss
Mohammad Zeineldeen (RWTH Aachen University / AppTek)*; Kartik Audhkhasi (Google); Murali Karthick
Baskar (Google); Bhuvana Ramabhadran (Google)

3918: MGAT: Multi-granularity Attention based Transformers for Multi-modal Emotion Recognition
Weiquan Fan (South China University of Technology)*; Xiaofen Xing ( South China University of
Technology); Bolun Cai (Shopee); Xiangmin Xu (South China University of Technology)

3926: Fast-U2++: Fast and Accurate End-to-End Speech Recognition in Joint CTC/Attention
Frames
Chengdong Liang (Northwestern Polytechnical University)*; Zhang XiaoLei (Northwestern Polytechnical
University); Binbin Zhang (Horizon Robotics); Di Wu (Horizon Robotics); Shengqiang Li (Horizon
Robotics); Xingchen Song (Horizon Robotics); Zhendong Peng (Horizon Robotics); Fuping Pan (Horizon
Robotics)

209
3928: WeKws: A production first small-footprint end-to-end Keyword Spotting Toolkit
Jie Wang (School of Marine Science and Technology, Northwestern Polytechnical University, Xi’an,
China)*; Menglong Xu (Horizon Robotics); Jingyong Hou (Northwestern Polytechnical University); Binbin
Zhang (Horizon Robotics); Zhang XiaoLei (Northwestern Polytechnical University); Lei Xie (NWPU);
Fuping Pan (Horizon Robotics)

3930: META LEARNING WITH ADAPTIVE LOSS WEIGHT FOR LOW-RESOURCE SPEECH
RECOGNITION
Qiulin Wang (Xiamen University); Wenxuan Hu (Xiamen University); Lin Li (Xiamen University); Qingyang
Hong (Xiamen University)*

3933: An Asynchronous Updating Reinforcement Learning Framework for Task-oriented Dialog

System
Sai Zhang (Beijing University of Posts and Telecommunications); Yuwei Hu (Beijing University of Posts
and Telecommunications); Xiaojie Wang (Beijing University of Posts and Telecommunications)*; Caixia
Yuan (Beijing University of Posts and Telecommunications)

3935: WAVE-U-NET DISCRIMINATOR: FAST AND LIGHTWEIGHT DISCRIMINATOR FOR

GENERATIVE ADVERSARIAL NETWORK-BASED SPEECH SYNTHESIS
Takuhiro Kaneko (NTT Corporation)*; Hirokazu Kameoka (NTT Communication Science Laboratories,
NTT Corporation); Kou Tanaka (NTT corpration); Shogo Seki (NTT Corporation)

3953: TOLD: A Novel Two-stage Overlap-aware Framework for Speaker Diarization

Jiaming Wang (Alibaba Group)*; Zhihao Du (Speech Lab, Alibaba Group); Shiliang Zhang (Alibaba
Group)

3954: DOMAIN ADAPTATION WITHOUT CATASTROPHIC FORGETTING ON A SMALL-SCALE

PARTIALLY-LABELED CORPUS FOR SPEECH EMOTION RECOGNITION
Zhi Zhu (Fairy Devices Inc.)*; Yoshinao Sato (Fairy Devices Inc.)

3963: SPEECH-BASED EMOTION RECOGNITION WITH SELF-SUPERVISED MODELS USING

ATTENTIVE CHANNEL-WISE CORRELATIONS AND LABEL SMOOTHING
Sofoklis Kakouros (University of Helsinki)*; Themos Stafylakis (Omilia - Conversational Intelligence);
Ladislav Mošner (Brno University of Technology); Lukáš Burget (Brno University of Technology)

3966: JSV-VC: JOINTLY TRAINED SPEAKER VERIFICATION AND VOICE CONVERSION MODELS
Shogo Seki (NTT Corporation)*; Hirokazu Kameoka (NTT Communication Science Laboratories, NTT
Corporation); Kou Tanaka (NTT corpration); Takuhiro Kaneko (NTT Corporation)

3971: HOW TO PUSH THE FASTEST MODEL 50X FASTER: STREAMING NON-AUTOREGRESSIVE
SPEECH SYNTHESIS ON RESOUCE-LIMITED DEVICES
Thinh Van Nguyen (VinBigdata)*; Cuong H Pham (VinBigdata JSC); Dang-Khoa MAC (VinBigdata)

3973: WeavSpeech: Data Augmentation Strategy for Automatic Speech Recognition via Semantic-
Aware Weaving
Kyusung Seo (KAIST)*; Joonhyung Park (KAIST); Jaeyun Song (KAIST); Eunho Yang (KAIST)

3984: Real-Time MRI Video synthesis from time aligned phonemes with sequence-to-sequence
networks
Sathvik Udupa (Indian Institute of Science)*; Prasanta Dr Ghosh (Indian Institute of Science (IISc),
Bangalore)

3992: Improved acoustic-to-articulatory inversion using representations from pretrained self-

supervised learning models
Sathvik Udupa (Indian Institute of Science)*; Siddarth C (Robert Bosch Centre for Data Science and AI,
Indian Institute of Technology Madras); Prasanta Dr Ghosh (Indian Institute of Science (IISc), Bangalore)

210
3999: Peak-First CTC: Reducing the Peak Latency of CTC Models by Applying Peak-First
Regularization
Zhengkun Tian (Meituan Inc.)*; Hongyu Xiang (Meituan Inc.); Min Li (Meituan Inc.); Feifei Lin (Meituan
Inc.); Ke Ding (Meituan Inc.); Guanglu Wan (Meituan)

4016: Adapted Multimodal BERT with Layer-wise Fusion for Sentiment Analysis
Odysseas S Chlapanis (National Technical University of Athens)*; Georgios Paraskevopoulos (National
Technical University of Athens); Alexandros Potamianos (National Technical University of Athens)

4017: Knowledge-augmented Frame Semantic Parsing with Hybrid Prompt-tuning

Rui Zhang (Artificial Intelligence Application Research Center, Huawei Technologies)*; yajing sun
(huawei); JINGYUAN YANG (Artificial Intelligence Application Research Center,Huawei Technologies);
Wei Peng (Huawei Technlogies)

4058: Duration-aware pause insertion using pre-trained language model for multi-speaker text-to-
speech
Dong Yang (The University of Tokyo)*; Tomoki Koriyama (CyberAgent, Inc.); Yuki Saito ("The University of
Tokyo, Japan"); Takaaki Saeki (The University of Tokyo); Detai Xin (The University of Tokyo); Hiroshi
Saruwatari (The University of Tokyo)

4063: Two-stage UNet with multi-axis gated multilayer perceptron for monaural noisy-reverberant
speech enhancement
Zehua Zhang (Harbin Institute of Technology(Shenzhen))*; Shiyun Xu (Harbin Institute of
Technology(Shenzhen)); Xuyi Zhuang (Harbin Institute of Technology(Shenzhen)); Lianyu Zhou (Harbin
Institute of Technology(Shenzhen)); Heng Li (Harbin Institute of Technology(Shenzhen)); Mingjiang Wang
(Harbin Institute of Technology Shenzhen)

4065: Temporal Modeling Matters: A Novel Temporal Emotional Modeling Approach for Speech
Emotion Recognition
JiaXin Ye (Fudan University); Xin-Cheng Wen (Harbin Institute of Technology (Shenzhen)); Yujie Wei
(Fudan University); Yong Xu (Fujian University of Technology); KunHong Liu (Xiamen University);
Hongming Shan (Fudan University)*

4066: Once-for-All Sequence Compression for Self-Supervised Speech Models

Hsuan-Jui Chen (National Taiwan University)*; Yen Meng (National Taiwan University); Hung-yi Lee
(National Taiwan University)

4083: Prosody-controllable spontaneous TTS with neural HMMs

Harm Lameris (KTH Royal Institute of Technology)*; Shivam Mehta (KTH Royal Institute of Technology);
Gustav Eje Henter (KTH Royal Institute of Technology); Joakim Gustafson (KTH Royal Institute of
Technology); Eva Szekely (KTH Royal Institute of Technology)

4087: Noise-Disentanglement Metric Learning for Robust Speaker Verification

Yao Sun (Tianjin University)*; Hanyi zhang (tianjin university); Longbiao Wang (Tianjin University); Kong
Aik Lee (Institute for Infocomm Research, A*STAR); Meng Liu (Tianjin University); Jianwu Dang (Tianjin
University)

4092: Self-Supervised Audio-Visual Speaker Representation with Co-Meta Learning

Hui Chen (Tianjin university)*; Hanyi Zhang (Tianjin university); Longbiao Wang (Tianjin University); Kong
Aik Lee (Institute for Infocomm Research, A*STAR); Meng Liu (Tianjin University); Jianwu Dang (Tianjin
University)

211
4097: DialogMI: A Dialogue Model Based on Enhancing Dialogue Mutual Information
Yibo Zhang (Beijing University of Posts and Telecommunications)*; Ping Gong (Beijing University of Posts
and Telecommunications); Zelin Wang (Beijing University of Posts and Telecommunications); Zhe Li
(Beijing University of Posts and Telecommunications); Xuanyuan Yang (Beijing University of Posts and
Telecommunications)

4104: Autovocoder: Fast Waveform Generation from a Learned Speech Representation using
Differentiable Digital Signal Processing
Jacob J Webber (The Centre for Speech Technology Research, University of Edinburgh)*; Cassia
Valentini (University of Edinburgh); Evelyn Williams (University of Edinburgh); Gustav Eje Henter (KTH
Royal Institute of Technology); Simon King (University of Edinburgh)

4107: Feature Selection and Text Embedding For Detecting Dementia from Spontaneous
Cantonese
Xiaoquan Ke (The Hong Kong Polytechnic University)*; Man-Wai MAK (The Hong Kong Polytechnic
University); Mei Ling MENG (The Chinese University of Hong Kong)

4115: Meeting Action Item Detection with Regularized Context Modeling

Jiaqing Liu (Speech Lab, Alibaba Group); Chong Deng (Alibaba inc); Qinglin Zhang (Speech Lab, Alibaba
Group); Qian Chen (Speech Lab, DAMO Academy, Alibaba Group); Wen Wang (Alibaba Group)*

4124: SPEECH AND NOISE DUAL-STREAM SPECTROGRAM REFINE NETWORK WITH SPEECH
DISTORTION LOSS FOR ROBUST SPEECH RECOGNITION
Haoyu Lu (Tianjin University)*; Nan Li (Tianjin University); Tongtong Song (Tianjin University); Longbiao
Wang (Tianjin University); Jianwu Dang (Tianjin University); Xiaobao Wang (Tianjin Univerisity); Shiliang
Zhang (Alibaba Group)

4135: Knowledge Transfer For On-Device Speech Emotion Recognition with Neural Structured
Learning
Yi Chang (Imperial College London)*; Zhao Ren (L3S Research Center); Thanh Tam Nguyen (Griffith
University); Kun Qian (Beijing Institute of Technology); Bjoern W. Schuller (Imperial College London)

4139: Joint Discriminator and Transfer Based Fast Domain Adaptation for End-to-End Speech
Recognition
Hang Shao (Shanghai Jiao Tong University)*; Tian Tan (Aispeech Ltd.); wei wang (Shanghai Jiao Tong
University); Xun Gong (Shanghai Jiaotong University); Yanmin Qian (Shanghai Jiao Tong University)

4154: SYNTACC : Synthesizing multi-accent speech by weight factorization

Tuan-Nam Nguyen (Karlsruhe Institute of Technology)*; Quan Pham (Karlsruhe Institute of Technology);
Alexander Waibel (Karlsruhe Institute of Technology (KIT))

4155: Mutually Guided Few-shot Learning for Relational Triple Extraction

Chengmei Yang (Tongji University)*; shuai jiang (tongji university); Bowei He (City University of Hong
Kong); Chen Ma (City University of Hong Kong); 何 良华 (同济大学)

4166: Modelling low-resource accents without accent-specific TTS frontend

Georgi Tinchev (Amazon)*; Marta Czarnowska (Amazon); Kamil Deja (Warsaw University of Technology);
Kayoko Yanagisawa (Amazon); Marius Cotescu (Amazon)

4178: F-PABEE: Flexible-patience-based Early Exiting for Single-label and Multi-label text
Classification Tasks
Xiangxiang Gao (Shanghai Jiaotong University); Wei Zhu (East China Normal University)*; Jiasheng Gao
(Shenzhen University); Congrui Yin (Nanchang University)

212
4186: MoLE : MIXTURE OF LANGUAGE EXPERTS FOR MULTI-LINGUAL AUTOMATIC SPEECH
RECOGNITION
Yoohwan Kwon (Naver corperation)*; Soo-Whan Chung (Naver Corporation)

4189: Source-Filter HiFi-GAN: Fast and Pitch Controllable High-Fidelity Neural Vocoder
Reo Yoneyama (Nagoya University)*; Yi-Chiao Wu (META); Tomoki Toda (Nagoya University)

4196: Rethinking the Reasonability of the Test Set for Simultaneous Machine Translation
Mengge Liu (Beijing Institute of Technology)*; Wen Zhang (Xiaomi AI Lab); Xiang Li (Xiaomi AI Lab); Jian
Luan (Xiaomi AI Lab); Bin Wang (Xiaomi AI Lab); Yuhang Guo (Beijing Engineering Research Center of
High Volume Language Information Processing and Cloud Computing Applications, Department of
Computer Science and Technology, Beijing Institute of technology); Shuoying Chen (Beijing Institute of
Technology)

4197: STREAMING JOINT SPEECH RECOGNITION AND DISFLUENCY DETECTION

Hayato Futami (Sony Group Corporation)*; Emiru Tsunoo (Sony Group Corporation); Kentaro Shibata
(Sony); Yosuke Kashiwagi (Sony); Takao Okuda (Sony); Siddhant Arora (Carnegie Mellon University);
Shinji Watanabe (Carnegie Mellon University)

4212: X-SepFormer: End-to-end Speaker Extraction Network with Explicit Optimization on Speaker
Confusion
KAI LIU (Huawei Technologies Co., Ltd.)*; Ziqing Du (Huawei Technologies Co., Ltd.); Xucheng Wan
(Huawei Technologies Co., Ltd.); zhou huan (AARC, Huawei Technologies Co., Ltd.)

4242: Hiding speaker's sex in speech using zero-evidence speaker representation in an

analysis/synthesis pipeline
Paul-Gauthier Noé (Avignon University)*; Xiaoxiao Miao (national institute of informatics); Xin Wang
(National Institute of Informatics); Junichi Yamagishi (National Institute of Informatics); Jean-Francois
Bonastre (Université d’Avignon); Driss Matrouf (Avignon University)

4278: A Sidecar Separator Can Convert a Single-Talker Speech Recognition System to a Multi-
Talker One
Lingwei Meng (The Chinese University of Hong Kong)*; Jiawen Kang (The Chinese University of Hong
Kong); Mingyu Cui (The Chinese University of Hong Kong); Yuejiao Wang (The Chinese University of
Hong Kong); Xixin Wu (The Chinese University of Hong Kong); Helen Meng (The Chinese University of
Hong Kong)

4281: LABEL-GUIDED CONTRASTIVE LEARNING FOR OUT-OF-DOMAIN DETECTION

Shun Zhang (Beihang University)*; Tongliang Li (Beihang University); Jiaqi Bai (Beihang University);
Zhoujun Li (Beihang University)

4305: Target Speaker Extraction with Ultra-Short Reference Speech by VE-VE Framework
Lei Yang (Samsung)*; Wei Liu (Samsung); Lufen Tan (Samsung); Jaemo Yang (Samsung); Han-gil Moon
(Samsung)

4312: An Interpretable model using evidence information for Multi-hop Question Answering over
Long texts
Yanyi Chen (Beijing University of Posts and Telecommunications); Ruifang Liu (Beijing University of Posts
and Telecommunications)*; Xiyan Liu (Beijing University of Posts and Telecommunications); Yidong Shi
(Beijing University of Posts and Telecommunications); Ge Bai (Beijing University of Posts and
Telecommunications)

4313: Self-Convolution for Automatic Speech Recognition

Tian-Hao Zhang (University of Science and Technology Beijing)*; Qi Liu (University of Science and
Technology Beijing); Xinyuan Qian (USTB); Song-Lu Chen (University of Science and Technology); Feng
Chen (EEasy Technology Co. LTD); Xu-Cheng Yin (University of Science and Technology Beijing)

213
4328: VF-TACO2: TOWARDS FAST AND LIGHTWEIGHT SYNTHESIS FOR AUTOREGRESSIVE
MODELS WITH VARIATION AUTOENCODER AND FEATURE DISTILLATION
Yuhao Liu ( Tianjin University)*; Cheng Gong (Tianjin University); Longbiao Wang (Tianjin University);
Xixin Wu (The Chinese University of Hong Kong); Qiuyu Liu (Tianjin University); Jianwu Dang (Tianjin
University)

4330: EVALUATING PARAMETER-EFFICIENT TRANSFER LEARNING APPROACHES ON SURE

BENCHMARK FOR SPEECH UNDERSTANDING
Li Yingting (Beijing University of Posts and Telecommunications); Ambuj Mehrish (SUTD); RISHABH
BHARDWAJ (Singapore University of Technology and Design); Navonil Majumder (SUTD); Bo Cheng
(Beijing University of Posts and Telecommunications); Shuai Zhao (Beijing University of Posts and
Telecommunications); Amri Zadeh (Amazon Science); Rada Mihalcea (University of Michigan); Soujanya
Poria (Singapore University of Technology and Design)*

4340: Phase-Aware Spoof Speech Detection Based on Res2Net with Phase Network
Juntae Kim (SK Telecom)*; Sung Min Ban (SK Telecom)

4348: Gaussian Prior Reinforcement Learning for Nested Named Entity Recognition
Yawen Yang (Tsinghua University)*; Xuming Hu (Tsinghua University); Fukun Ma (Tsinghua University);
Shuang Li (Tsinghua University); Aiwei Liu (Tsinghua University); Lijie Wen (Tsinghua University); Philip S
Yu (UIC)

4354: Role of Lexical Boundary Information in Chunk-Level Segmentation for Speech Emotion
Recognition
Wei-Cheng Lin (The University of Texas at Dallas)*; Carlos Busso (University of Texas at Dallas)

4355: TOWARDS ZERO-SHOT CODE-SWITCHED SPEECH RECOGNITION

Brian Yan (Carnegie Mellon University)*; Matthew S Wiesner (Johns Hopkins University); Ondrej Klejch
(University of Edinburgh); Preethi Jyothi (Indian Institute of Technology Bombay); Shinji Watanabe
(Carnegie Mellon University)

4364: Exploring Binary Classification Loss for Speaker Verification

Bing Han (Shanghai Jiao Tong University)*; Zhengyang Chen (Shanghai Jiao Tong University); Yanmin
Qian (Shanghai Jiao Tong University)

4365: Understanding Shared Speech-Text Representations

Yuan Wang (Google)*; Kyle Kastner (Google); Zhehuai Chen (Google); Ankur Bapna (Google Research);
Andrew Rosenberg (Google LLC); Bhuvana Ramabhadran (Google); Yu Zhang (Google)

4371: SUFFIX RETRIEVAL-AUGMENTED LANGUAGE MODELING

Zecheng Wang (New York University Shanghai); Yik-Cheung Tam (NYU Shanghai)*

4378: Low-latency electrolaryngeal speech enhancement based on FastSpeech2-based voice

conversion and self-supervised speech representation
Kazuhiro Kobayashi (Nagoya University)*; Tomoki Hayashi (Nagoya University); Tomoki Toda (Nagoya
University)

4387: Align, Write, Re-order: Explainable End-to-End Speech Translation via Operation Sequence
Generation
Motoi Omachi (Yahoo Japan Corporation)*; Brian Yan (Carnegie Mellon University); Siddharth Dalmia
(Carnegie Mellon University); Yuya Fujita (Yahoo Japan Corporation); Shinji Watanabe (Carnegie Mellon
University)

214
4409: A Token-level Contrastive Framework for Sign Language Translation
Biao Fu (Xiamen University); Peigen Ye (Xiamen University); liang zhang (Xiamen University); Pei Yu
(Xiamen University); Cong Hu (Xiamen University); xiaodong shi (xiamen university); Yidong Chen
(Xiamen University)*

4412: Knowledge-aware Bayesian Co-attention for Multimodal Emotion Recognition

Zihan Zhao (Shanghai Jiao Tong University)*; Yu Wang (Shanghai Jiao Tong University); Yan-Feng Wang
(Cooperative medianet innovation center of Shanghai Jiao Tong University)

4421: Audio-visual Speech Enhancement with a Deep Kalman Filter Generative Model
Ali Golmakani (Inria Nancy Grand ); Mostafa Sadeghi (INRIA)*; romain serizel (Université de Lorraine)

4427: End-to-End word-level disfluency detection and classification in children's reading

assessment
Lavanya Venkatasubramaniam (Ohio State University); Vishal Sunder (The Ohio State University)*; Eric
Fosler-Lussier (Ohio State)

4441: Wespeaker: A Research and Production oriented Speaker Embedding Learning Toolkit
Hongji Wang (None); Chengdong Liang (Northwestern Polytechnical University); Shuai Wang (Shanghai
Jiao Tong University)*; Binbin Zhang (Horizon Robotics); Zhengyang Chen (Shanghai Jiao Tong
University); Xu Xiang (AISpeech Ltd); Slyne Deng (NVIDIA); Yanmin Qian (Shanghai Jiao Tong
University)

4451: A Protypical Semantic Decoupling Method via Joint Contrastive Learning for Few-Shot
Named Entity Recognition
Guanting Dong (Beijing University of Posts and Telecommunications)*; Zechen Wang (Beijing University
of Posts and Telecommunications); Liwen Wang (Beijing University of Posts and Telecommunications);
Daichi Guo (Beijing University of Posts and Telecommunications); Dayuan Fu (Beijing University of Posts
and Telecommunications); yuxiang wu (Beijing University of Posts and Telecommunications); Chen Zeng
(Beijing University of Posts and Telecommunications); Xuefeng Li (Beijing University of Posts and
Telecommunications); Tingfeng Hui (Beijing University of Posts and Telecommunications); Keqing He
(Beijing University of Posts and Telecommunications); Xinyue Cui (Beijing University of Posts and
Telecommunications); QiXiang Gao (Beijing University of Posts and Telecommunications); Weiran Xu
(Beijng University of Posts and Telecommunications)

4452: Revisit Out-of-vocabulary Problem for Slot Filling: A Unified Contrastive Framework with
Multi-level Data Augmentations
Daichi Guo (Beijing University of Posts and Telecommunications)*; Guanting Dong (Beijing University of
Posts and Telecommunications); Dayuan Fu (Beijing University of Posts and Telecommunications);
yuxiang wu (Beijing University of Posts and Telecommunications); Chen Zeng (Beijing University of Posts
and Telecommunications); Tingfeng Hui (Beijing University of Posts and Telecommunications); Liwen
Wang (Beijing University of Posts and Telecommunications); Xuefeng Li (Beijing University of Posts and
Telecommunications); Zechen Wang (Beijing University of Posts and Telecommunications); Keqing He
(Beijing University of Posts and Telecommunications); Xinyue Cui (Beijing University of Posts and
Telecommunications); Weiran Xu (Beijng University of Posts and Telecommunications)

4456: AN ADAPTER BASED MULTI-LABEL PRE-TRAINING FOR SPEECH SEPARATION AND

ENHANCEMENT
Tianrui Wang (Beijing Jiaotong University)*; Xie Chen (Shanghai Jiaotong University); Zhuo Chen
(Microsoft); Shu Yu (SJTU); Weibin Zhu (Beijing Jiaotong University(China))

4458: Large-scale Language Model Rescoring on Long-form Data

Tongzhou Chen (Google)*; Cyril Allauzen (Google); Yinghui Huang (Google); Daniel S Park (Google
Brain); David Rybach (Google); W. Ronny Huang (Google); Rodrigo Cabrera (Google); Kartik Audhkhasi
(Google); Bhuvana Ramabhadran (Google); Pedro J Moreno (Google); Michael Riley (Google)

215
4480: TEXT-TO-SPEECH SYNTHESIS FROM DARK DATA WITH EVALUATION-IN-THE-LOOP DATA
SELECTION
Kentaro Seki (The University of Tokyo)*; Shinnosuke Takamichi (The University of Tokyo); Takaaki Saeki
(The University of Tokyo); Hiroshi Saruwatari (The University of Tokyo)

4499: Covariance Regularization for Probabilistic Linear Discriminant Analysis

ZHIYUAN PENG (CUHK)*; Mingjie Shao (The Chinese University of Hong Kong, Shandong University );
Xuanji He (meituan); Xu Li (ARC Lab, Tencent); Tan Lee (The Chinese University of Hong Kong); Ke Ding
(meituan); Guanglu Wan (Meituan)

4502: GRAPH-BASED SPECTRO-TEMPORAL DEPENDENCY MODELING FOR ANTI-SPOOFING

Feng Chen (Harbin Institute of Technology)*; Shiwen Deng (Harbin Normal University); 铁然 郑 (哈尔滨工
业大学 ); 勇军 何 (50+); jiqing Han (Harbin Institute of Technology)

4507: Leveraging Positional-Related Local-Global Dependency for Synthetic Speech Detection

Xiaohui Liu (Tianjin University, Tianjin, China); Meng Liu (Tianjin University); Longbiao Wang (Tianjin
University)*; Kong Aik Lee (Institute for Infocomm Research, A*STAR); Hanyi Zhang (Tianjin University);
Jianwu Dang (Tianjin University)

4508: Improving Disfluency Detection with Multi-scale Self Attention and Contrastive Learning
Peiying Wang (JD AI); Chaoqun Duan (JD AI Research); Meng Chen (JD AI)*; Xiaodong He (JDT)

4510: Improving Massively Multilingual ASR With Auxiliary CTC Objectives

William Chen (Carnegie Mellon University)*; Brian Yan (Carnegie Mellon University); Jiatong Shi
(Carnegie Mellon University); Yifan Peng (Carnegie Mellon University); Soumi Maiti (CMU); Shinji
Watanabe (Carnegie Mellon University)

4523: ACHIEVING FAIR SPEECH EMOTION RECOGNITION VIA PERCEPTUAL FAIRNESS

Woan-Shiuan Chien (Department of Electrical Engineering, National Tsing Hua University ); Chi-Chun Lee
(National Tsing Hua University)*

4534: Front-End Adapter: Adapting Front-End Input of Speech based Self-Supervised Learning for
Speech Recognition
Xie Chen (Shanghai Jiaotong University)*; Ziyang Ma (Shanghai Jiao Tong University); Changli Tang
(Tsinghua University); Yujin Wang (Tsinghua University); Zhisheng Zheng (Shanghai Jiao Tong University
)

4537: Target-Speaker Voice Activity Detection via Sequence-to-Sequence Prediction

Ming Cheng (Duke Kunshan University)*; Weiqing Wang (Duke University); Yucong Zhang (Duke
Kunshan University); Xiaoyi Qin (Dukekunshan University); Ming Li (Duke Kunshan University)

4546: USING MODIFIED ADULT SPEECH AS DATA AUGMENTATION FOR CHILD SPEECH
RECOGNITION
Zijian Fan (Norwegian University of Science and Technology)*; Xinwei Cao (NTNU); Giampiero Salvi
(NTNU); Torbjørn Svendsen (NTNU)

4547: PHONETIC ANCHOR-BASED TRANSFER LEARNING TO FACILITATE UNSUPERVISED

CROSS-LINGUAL SPEECH EMOTION RECOGNITION
Shreya G Upadhyay (National Tsing Hua University); Luz Martinez-Lucas (Department of Electrical and
Computer Engineering, University of Texas at Dallas); Bo-Hao Su (Department of Electrical Engineering,
National Tsing Hua University); Wei-Cheng Lin (The University of Texas at Dallas); Woan-Shiuan Chien
(Department of Electrical Engineering, National Tsing Hua University ); Ya-Tse Wu (Department of
Electrical Engineering, National Tsing Hua University); William F Katz (UT Dallas); Carlos Busso
(University of Texas at Dallas); Chi-Chun Lee (National Tsing Hua University)*

216
4548: Improving Retrieval-based Dialogue System via Syntax-Informed Attention
Tengtao Song (Peking University)*; Nuo Chen (Peking University); Ji Jiang (Peking University); Zhihong
Zhu (Peking University); Yuexian Zou (Peking University)

4559: Zero-Shot Speech Emotion Recognition Using Generative Learning with Reconstructed
Prototypes
Xinzhou Xu (Nanjing University of Posts and Telecommunications)*; Jun Deng (Agile Robots AG); Zixing
Zhang (Imperial College London); Zhen Yang (Nanjing University of Posts and Telecommunication); Bjorn
W. Schuller (Imperial College London)
4584: Improved Training of Mixture-of-Experts Language GANs
Yekun Chai (Baidu Inc.)*; Qiyue Yin (Institute of Automation, Chinese Academy of Sciences); Junge
Zhang (CASIA)

4592: Dynamic Chunk Convolution for Unified Streaming and Non-Streaming Conformer ASR
Xilai Li (Amazon)*; Goeric Huybrechts (Amazon); Srikanth Ronanki (Amazon); Jeff Farris (Amazon);
Sravan Babu Bodapati (Amazon)

4608: SynGen: A Syntactic Plug-and-play Module for Generative Aspect-based Sentiment Analysis
Chengze Yu (Tsinghua University); Taiqiang Wu (Tsinghua University); Jiayi Li (Tsinghua University);
Xingyu Bai (Tsinghua University); Yujiu Yang (Tsinghua University)*

4612: Gated contextual adapters for selective contextual biasing in neural transducers
Anastasios Alexandridis (Amazon.com)*; Kanthashree Mysore Sathyendra (Amazon); Grant Strimel
(Amazon.com); Feng-Ju Chang (Amazon); Ariya Rastrow (Amazon Alexa); Nathan Susanj
(Amazon.com); Athanasios Mouchtaris (Amazon Alexa)

4623: Distance-based Weight Transfer for Fine-tuning from Near-field to Far-field Speaker
Verification
Li Zhang (Northwestern Polytechnical University)*; Qing Wang (Northwestern Polytechnical University);
Hongji Wang (None); Yue Li (Northwestern Polytechnical University); Wei Rao (Tencent); Yannan Wang
(Tencent); Lei Xie (NWPU)

4626: Utilizing Wav2vec in Database-independent Voice Disorder Detection

Saska Tirronen (Aalto University)*; Farhad Javanmardi (Aalto University); Manila Kodali (Aalto
University); Sudarsana Reddy Kadiri (Aalto University); Paavo Alku (Aalto University)

4629: MULTIMODAL EMOTION RECOGNITION BASED ON DEEP TEMPORAL FEATURES USING

CROSS-MODAL TRANSFORMER AND SELF-ATTENTION
Bubai Maji (Indian Institute of Technology Kharagpur)*; Monorama Swain (Silicon Institute of Technology,
Bhubaneswar); Rajlakshmi Guha (IIT Kharagpur); Aurobinda Routray (IIT Kharagpur)

4646: Modeling Global Latent Semantic in Multi-Turn Conversations with Random Context
Reconstruction
Chengwen Zhang (Beijing University of Posts & Telecommunications); Danqin Wu (Beijing University of
Posts & Telecommunications)*

4651: UNIVERSAL SPEAKER RECOGNITION ENCODERS FOR DIFFERENT SPEECH SEGMENTS

DURATION
Sergey Novoselov (ITMO University)*; Vladimir Volokhov (STC-innovations Ltd., ITMO University); Galina
Lavrentyeva (ITMO University)

4652: UNSUPERVISED SPEAKER VERIFICATION USING PRE-TRAINED MODEL AND LABEL

CORRECTION
Zhicong Chen (Xiamen University); Jie Wang (Xiamen University); Wenxuan Hu (Xiamen University); Lin
Li (Xiamen University)*; Qingyang Hong (Xiamen University)

217
4655: High-resolution embedding extractor for speaker diarisation
Heesoo Heo (Naver Corp.)*; Youngki Kwon (Naver Corporation); Bong-Jin Lee (Naver Corporation); You
Jin Kim (Naver Corporation); Jee-weon Jung (Naver Corp.)

4657: Targeted Adversarial Attacks against Neural Machine Translation

Sahar Sadrizadeh (EPFL)*; AmirHossein Dabiri Aghdam (University of Tehran); Ljiljana Dolamic
(armasuisse); Pascal Frossard (EPFL)

4662: COMMUNITY DETECTION GRAPH CONVOLUTIONAL NETWORK FOR OVERLAP-AWARE

SPEAKER DIARIZATION
Jie Wang (Xiamen University); Zhicong Chen (Xiamen University); Haodong Zhou (Xiamen University);
Lin Li (Xiamen University)*; Qingyang Hong (Xiamen University)

4671: DIFFUSION-BASED GENERATIVE SPEECH SOURCE SEPARATION

Robin Scheibler (LINE Corporation)*; Youna Ji (NAVER Corperation); Soo-Whan Chung (Naver
Corporation); Jaeuk Byun (Naver Corporation); Soyeon Choe (NAVER Corporation); Min-Seok Choi
(NAVER)

4673: Lost In Translation: Generating Adversarial Examples Robust to Round-Trip Translation

Neel Bhandari (RV College of Engineering)*; Pin-Yu Chen (IBM Research)

4680: RobustDistiller: Compressing Universal Speech Representations for Enhanced Environment

Robustness
Heitor R Guimarães (Institut National de la Recherche Scientifique)*; Arthur S Pimentel (Institut National
de la Recherche Scientifique (INRS)); Anderson R Avila (INRS-EMT); Mehdi Rezagholizadeh (Huawei
Technologies); Boxing Chen (Huawei Technologies); Tiago H Falk (INRS-EMT)

4711: Dialog act guided contextual adapter for personalized speech recognition
Feng-Ju Chang (Amazon)*; Thejaswi Muniyappa (Amazon); Kanthashree Mysore Sathyendra (Amazon);
Kai Wei (Amazon); Grant Strimel (Amazon); Ross McGowan (Amazon)

4716: SEPDIFF: SPEECH SEPARATION BASED ON DENOISING DIFFUSION MODEL

Bo Chen (Huawei Technologies)*; Chao Wu (Huawei Technologies); Wenbin Zhao (Huawei Technologies)

4738: Analysis and transformation of voice level in singing voice

Frederik Bous (STMS - IRCAM, Sorbonne Université, CNRS)*; Axel Roebel (Ircam)

4747: Make More of Your Data: Minimal Effort Data Augmentation for Automatic Speech
Recognition and Translation
Tsz Kin Lam (Heidelberg University); Shigehiko Schamoni (Heidelberg University)*; Stefan Riezler
(Heidelberg University)

4756: On Batching Variable Size Inputs for Training End-to-End Speech Enhancement Systems
Philippe Gonzalez (Technical University of Denmark)*; Tommy Sonne Alstrøm (Technical University of
Denmark); Tobias May (Technical University of Denmark)

4760: TEXTLESS DIRECT SPEECH-TO-SPEECH TRANSLATION WITH DISCRETE SPEECH

REPRESENTATION
Xinjian Li (Carnegie Mellon University)*; Ye Jia (Tomato AI); Chung-Cheng Chiu (Google)

4768: Context-aware Coherent Speaking Style Prediction with Hierarchical Transformers for
Audiobook Speech Synthesis
Shun Lei (Tsinghua University)*; Yixuan Zhou (Tsinghua University); Liyang Chen (Tsinghua University);
Zhiyong Wu (Tsinghua University); Shiyin Kang (XVerse Inc.); Helen Meng (The Chinese University of
Hong Kong)

218
4769: Less is more: A unified architecture for device-directed speech detection with multiple
invocation types
Ognjen Rudovic (Apple)*; Wonil Chang (Apple); Vineet Garg (Apple); Pranay Dighe (Apple); Pramod Jaya
Simha (Apple Inc); John Berkowitz (Apple); Ahmed Hussen Abdelaziz (Apple); Erik Marchi (Apple);
Sachin Kajarekar (Apple); Saurabh Adya (Apple)

4776: Ensemble prosody prediction for expressive speech synthesis

Tian Huey Teh (Papercup); Vivian Hu (Papercup)*; Devang Mohan (Papercup); Zack Hodari (Papercup);
Christopher Wallis (Papercup); Tomás Gómez Ibarrondo (Papercup); Alexandra Torresquintero
(Papercup); James Leoni (Papercup); Mark Gales (University of Cambridge ); Simon King (University of
Edinburgh)

4777: Massively Multilingual Shallow Fusion with Large Language Models

Ke Hu (Google)*; Tara Sainath (Google); Bo Li (Google); Nan Du (Google Brain); Yanping Huang (Google
Brain); Andrew M Dai (Google Brain); Yu Zhang (Google); Rodrigo Cabrera (Google); Zhifeng Chen
(Google); Trevor Strohman (Google)

4780: Pyramid Dynamic Inference: Encouraging Faster Inference via Early Exit Boosting
Ershad Banijamali (Amazon Inc.)*; Pegah Kharazmi (Amazon); Sepehr Eghbali (Amazon); Jixuan Wang
(Amazon); Clement Chung (Amazon); Samridhi Choudhary (Amazon)

4789: Egocentric Audio-Visual Noise Suppression

Roshan S Sharma (Carnegie Mellon University)*; Weipeng He (Idiap Research Institute); Egor Lakomkin
(Meta); Ju Lin (Meta); Yang Liu (Meta); Kaustubh Kalgaonkar (Meta )

4792: A knowledge-driven vowel-based approach of depression classification from speech using

data augmentation
Kexin Feng (Texas A&M University); Theodora Chaspari (Texas A&M University)*

4798: Conversational Text-to-SQL: An Odyssey into State-of-the-Art and Challenges Ahead

Sree Hari Krishnan Parthasarathi (Amazon); Lu Zeng (Amazon)*; Dilek Z Hakkani-Tur (Amazon Alexa AI)

4801: SIGN LANGUAGE RECOGNITION VIA DEFORMABLE 3D CONVOLUTIONS AND MODULATED

GRAPH CONVOLUTIONAL NETWORKS
Katerina Papadimitriou (University of Thessaly)*; Gerasimos Potamianos (ECE, University of Thessaly)

4805: Deformable Temporal Convolutional Networks for Monaural Noisy Reverberant Speech
Separation
William Ravenscroft (The University of Sheffield)*; Stefan Goetze (University of Sheffield); Thomas Hain
(University of Sheffield)

4818: Analysing Discrete Self Supervised Speech Representation for Spoken Language Modeling
Amitay Sicherman (The Hebrew University of Jerusalem); Yossi Adi (Facebook AI Research )*

4819: End-to-end Spoken Language Understanding with Tree-constrained Pointer Generator

Guangzhi Sun (University of Cambridge Department of Engineering)*; Chao Zhang (Tsinghua University);
Phil Woodland (Machine Intelligence Laboratory, Cambridge University Department of Engineering)

4822: Exploring Sequence-to-Sequence Transformer-Transducer Models for Keyword Spotting

Beltrán Labrador (Audias - Universidad Autónoma de Madrid); Guanlong Zhao (Google)*; Ignacio Lopez
Moreno (Google); Angelo Scorza Scarpati (Google); Liam Fowl (Google); Quan Wang (Google)

4823: Performance comparison of TTS models for Brazilian Portuguese to establish a baseline
Wilmer Johan Lobato (Alana AI)*; Felipe Farias (Alana AI); William Cruz (Alana AI); Marcellus Amadeus
(Alana AI)

219
4829: The 2nd Clarity Enhancement Challenge for hearing aid speech intelligibility enhancement:
Overview and Outcomes
Michael Akeroyd (University of Nottingham); Will Bailey (University of Sheffield); Jon Barker (Professor)*;
Trevor Cox (University of Salford); John F Culling (Cardiff University); Simone Graetzer (University of
Salford); Graham Naylor (University of Nottingham); Zuzanna Podwinska (University of Salford); Zehai Tu
(University of Sheffield)

4830: Internal Language Model Estimation based Adaptive Language Model Fusion for Domain
Adaptation
Rao Ma (University of Cambridge)*; Xiaobo Wu (ByteDance); Jin Qiu (ByteDance); Yanan Qin
(ByteDance); Haihua Xu (ByteDance); Peihao Wu (Bytedance); Zejun Ma (Bytedance)

4837: LAST: Scalable Lattice-Based Speech Modelling in JAX

Ke Wu (Google)*; Ehsan Variani (Google); Tom Bagby (Google); Michael Riley (Google)

4842: Multilingual end-to-end spoken language understanding for ultra-low footprint applications
Markus Mueller (Amazon Alexa)*; Anastasios Alexandridis (Amazon.com); Zach Trozenski (Amazon
Alexa); Joel Whiteman (Amazon Alexa); Grant Strimel (Amazon Alexa); Nathan Susanj (Amazon Alexa);
Athanasios Mouchtaris (Amazon Alexa); Siegfried Kunzmann (Amazon Alexa)

4850: Investigating Content-Aware Neural Text-To-Speech MOS Prediction Using Prosodic and
Linguistic Features
Alexandra Vioni (Innoetics, Samsung Electronics)*; Georgia Maniati (Samsung Electronics); Nikolaos
Ellinas (Innoetics, Samsung Electronics); June Sig Sung (Samsung Electronics); Inchul Hwang (Samsung
Research); Aimilios Chalamandaris (Samsung Electronics); Pirros Tsiakoulis (Samsung )

4854: LEARNING DEPENDENCIES OF DISCRETE SPEECH REPRESENTATIONS WITH NEURAL

HIDDEN MARKOV MODELS
Sung-Lin Yeh (University of Edinburgh)*; Hao Tang (The University of Edinburgh)

4855: SUPERVISED CONTRASTIVE LEARNING AS MULTI-OBJECTIVE OPTIMIZATION FOR FINE-

TUNING LARGE PRE-TRAINED LANGUAGE MODELS
youness moukafih (International University of Rabat)*; Mounir Ghogho (Université Internationale de
Rabat); Kamel Smaïli (University of Lorraine)

4858: Unsupervised domain adaptation for preference learning based speech emotion recognition
Abinay Reddy Naini (The University of Texas at Dallas); Mary Kohler (Laboratory for Analytic Sciences,
North Carolina State University); Carlos Busso (University of Texas at Dallas)*

4865: SG-VAD: STOCHASTIC GATES BASED SPEECH ACTIVITY DETECTION

Jonathan Svirsky (Bar Ilan University)*; Ofir Lindenbaum (Yale )

4868: End-to-end spoken language understanding using joint CTC loss and self-supervised,
pretrained acoustic encoders
Jixuan Wang (Amazon)*; Martin Radfar (Amazon); Kai Wei (Amazon); Clement Chung (Amazon)

4876: Abstract Representation for Multi-Intent Spoken Language Understanding

Rim Abrougui (Orange Innovation Lannion); Geraldine Damnati (Orange Innovation ); Johannes Heinecke
(Orange Innovation); FREDERIC BECHET (Aix Marseille University)*

4882: Waveform Boundary Detection for Partially Spoofed Audio

Zexin Cai (Duke University)*; Weiqing Wang (Duke University); Ming Li (Duke Kunshan University)

220
4889: DISTILL-QUANTIZE-TUNE - LEVERAGING LARGE TEACHERS FOR LOW-FOOTPRINT
EFFICIENT MULTILINGUAL NLU ON EDGE
Pegah Kharazmi (Amazon)*; Zhewei Zhao (Amazon); Clement Chung (Amazon); Samridhi Choudhary
(Amazon)

4931: NEURAL ARCHITECTURE SEARCH WITH MULTIMODAL FUSION METHODS FOR

DIAGNOSING DEMENTIA
Michail Chatzianastasis (École Polytechnique )*; Loukas Ilias (National Technical University of Athens);
Dimitris Askounis (National Technical University of Athens); Michalis Vazirgiannis (École Polytechnique)

4959: Exploring Subgroup Performance in End-to-End Speech Models

Alkis Koudounas (Politecnico di Torino); Eliana Pastor (Politecnico di Torino)*; Giuseppe Attanasio
(Bocconi University); Vittorio Mazzia (Amazon Alexa AI); Manuel Giollo (Amazon); Thomas Gueudre
(Amazon Alexa AI); Luca Cagliero (Dipartimento di Automatica e Informatica Politecnico di Torino); Luca
de Alfaro (University of California, Santa Cruz); Elena Baralis (Politecnico di Torino); Daniele Amberti
(Amazon Alexa AI)

4968: EXPLORING WAV2VEC 2.0 FINE TUNING FOR IMPROVED SPEECH EMOTION
RECOGNITION
Li-Wei Chen (Carnegie Mellon University)*; Alexander I. Rudnicky (Carnegie Mellon University)

4970: Adaptable End-to-End ASR Models using Replaceable Internal LMs and Residual Softmax
Keqi Deng (University of Cambridge)*; Phil Woodland (Machine Intelligence Laboratory, Cambridge
University Department of Engineering)

4975: OUTSIDE KNOWLEDGE VISUAL QUESTION ANSWERING VERSION 2.0

Benjamin Reichman (Georgia Institute of Technology)*; Anirudh S Sundar (Georgia Institute of
Technology); Christopher G Richardson (Georgia Institute of Technology); Tamara Zubatiy (Georgia
Institute of Technology); Prithwijit Chowdhury (Georgia Institute of Technology); Aaryan Shah (Georgia
Institute of Technology); Jack Truxal (Georgia Institute of Technology); Micah Grimes (Georgia Institute of
Technology); Dristi Shah (Georgia Institute of Technology); Woo Ju Chee (Georgia Institute of
Technology); Saif Punjwani (Georgia Institute of Technology); Atishay Jain (Georgia Institute of
Technology); Larry Heck (Georgia Institute of Technology)

4983: Efficient Speech Translation with Dynamic Latent Perceivers

Ioannis Tsiamas (Universitat Politècnica de Catalunya (UPC))*; Gerard Ion Gállego (Universitat
Politècnica de Catalunya); José A. R. Fonollosa (Universitat Politècnica de Catalunya); Marta R. Costa-
jussá (Meta AI)

4984: EARLY DETECTION OF COGNITIVE DECLINE USING VOICE ASSISTANT COMMANDS

Eli Kurtz (UMass Boston)*; Youxiang Zhu (UMass Boston); Tiffany Driesse (University of North Carolina);
Bang Tran (UMass Boston ); John Batsis (University of North Carolina); Robert Roth (Geisel School of
Medicine); Xiaohui Liang (University of Massachusetts Boston)

4989: M-SpeechCLIP: Leveraging Large-Scale, Pre-Trained Models for Multilingual Speech to

Image Retrieval
Layne Berry (University of Texas at Austin)*; Yi-Jen Shih (National Taiwan University); Hsuan-Fu Wang
(Institute of Information Science, Academia Sinica; National Taiwan University); Heng-Jui Chang
(Massachusetts Institute of Technology); Hung-yi Lee (National Taiwan University); David Harwath (The
University of Texas at Austin)

4991: ASSD: SYNTHETIC SPEECH DETECTION IN THE AAC COMPRESSED DOMAIN

Amit Kumar Singh Yadav (Purdue University)*; Ziyue Xiang (Purdue University); Emily Bartusiak (Purdue
University); Paolo Bestagini (Politecnico di Milano); Stefano Tubaro (Politecnico di Milano, Italy); Edward
Delp (Purdue University)

221
5011: LEVERAGING LABEL CORRELATIONS IN A MULTI-LABEL SETTING: A CASE STUDY IN
EMOTION
Georgios Chochlakis (University of Southern California)*; Girish M Mahajan (Microsoft); Sabyasachee
Baruah (University of Southern California); Keith Burghardt (ISI, University of Southern California );
Kristina Lerman (USC Information Sciences Institute); Shrikanth Narayanan (USC)

5014: USING EMOTION EMBEDDINGS TO TRANSFER KNOWLEDGE BETWEEN EMOTIONS,

LANGUAGES, AND ANNOTATION FORMATS
Georgios Chochlakis (University of Southern California)*; Girish M Mahajan (Microsoft); Sabyasachee
Baruah (University of Southern California); Keith Burghardt (ISI, University of Southern California );
Kristina Lerman (USC Information Sciences Institute); Shrikanth Narayanan (USC)

5023: Personalized Task Load Prediction in Speech Communication

Robert P Spang (TU Berlin)*; Karl El Hajal (EPFL); Sebastian Möller (TU Berlin); Milos Cernak (Logitech
Europe)

5025: FIXED-POINT QUANTIZATION AWARE TRAINING FOR ON-DEVICE KEYWORD-SPOTTING

Sashank Kumar Macha (Amazon)*; Om Oza (Amazon); Alex Escott (Amazon); Francesco Caliva
(Amazon); Robbie Armitano (Amazon); Santosh Kumar Cheekatmalla (Amazon); Sree Hari Krishnan
Parthasarathi (Amazon); Yuzong Liu (Amazon)

5030: Self-supervised speech representation learning for keyword-spotting with light-weight

transformers
Chenyang Gao (Rutgers University)*; Yue Gu (Amazon); Francesco Caliva (Amazon); Yuzong Liu
(Amazon)

5051: Efficient Domain Adaptation for Speech Foundation Models

Bo Li (Google)*; Dongseong Hwang (Google); Zhouyuan Huo (Google ); Junwen Bai (Google); Guru
Prakash Arumugam (Google LLC); Tara Sainath (Google); Khe C Sim (Google Inc.); Yu Zhang (Google);
Wei Han (Google); Trevor Strohman (Google); Françoise Beaufays (Google)

5058: Powerful and Extensible WFST Framework for RNN-Transducer Losses

Aleksandr Laptev (NVIDIA, ITMO University)*; Vladimir Bataev (NVIDIA); Igor Gitman (NVIDIA); Boris
Ginsburg (NVIDIA)

5060: Speaker-Independent Acoustic-to-Articulatory Speech Inversion

Peter Wu (UC Berkeley)*; Li-Wei Chen (Carnegie Mellon University); Cheol Jun Cho (UC Berkeley); Shinji
Watanabe (Carnegie Mellon University); Louis Goldstein (University of Southern California); Alan Black
(CMU); Gopala Krishna Anumanchipalli (UC Berkeley)

5065: Exploring Attention Mechanisms for Multimodal Emotion Recognition in an Emergency Call
Center Corpus
Theo Deschamps-Berger (Paris-Saclay University, CNRS)*; Lori Lamel (CNRS LIMSI); Laurence Y.
Devillers (LISN-CNRS)

5069: JOINT MODELLING OF SPOKEN LANGUAGE UNDERSTANDING TASKS WITH INTEGRATED

DIALOG HISTORY
Siddhant Arora (Carnegie Mellon University)*; Hayato Futami (Sony Group Corporation); Emiru Tsunoo
(Sony Group Corporation); Brian Yan (Carnegie Mellon University); Shinji Watanabe (Carnegie Mellon
University)

5075: DWFORMER: DYNAMIC WINDOW TRANSFORMER FOR SPEECH EMOTION RECOGNITION

Shuaiqi Chen (School of Electronic and Information Engineering, South China University of Technology)*;
Xiaofen Xing ( South China University of Technology); Weibin Zhang (VoiceAI Technologies); Weidong
Chen (South China University of Technology); Xiangmin Xu (South China University of Technology)

222
5084: AN ISOTROPY ANALYSIS FOR SELF-SUPERVISED ACOUSTIC UNIT EMBEDDINGS ON THE
ZERO RESOURCE SPEECH CHALLENGE 2021 FRAMEWORK
Jianan Chen (Japan Advanced Institute of Science and Technology)*; Sakriani Sakti (Japan Advanced
Institute of Science and Technology)

5093: Meta Learning for Domain Agnostic Soft Prompt

Ming-Yen Chen (National Yang Ming Chiao Tung University); Mahdin Rohmatillah (National Yang Ming
Chiao Tung University); Ching-hsien Lee (Industrial Technology Research Institute); Jen-Tzung Chien
(National Yang Ming Chiao Tung University)*

5096: THE SECRET SOURCE : INCORPORATING SOURCE FEATURES TO IMPROVE ACOUSTIC-

TO-ARTICULATORY SPEECH INVERSION
Yashish M. Siriwardena (University of Maryland College Park)*; Carol Y Espy-Wilson (University of
Maryland)

5106: To Wake-up or Not to Wake-up: Reducing Keyword False Alarm by Successive Refinement
Yashas Malur Saidutta (Samsung Research America)*; Rakshith Sharma Srinivasa (Samsung Research
America); Ching-Hua Lee (Samsung Research America); Chouchang Yang (Samsung Research
America); Yilin Shen (Samsung Research America); Hongxia Jin (Samsung Research America)

5113: Deep Implicit Distribution Alignment Networks for Cross-Corpus Speech Emotion
Recognition
Yan Zhao (Southeast University)*; JIncen Wang (Southeast University); Yuan Zong (Southeast
University); Wenming Zheng (Southeast University); Hailun lian (Southeast University); Li Zhao
(Southeast University)

5117: Self-Supervised Adversarial Training for Contrastive Sentence Embedding

Jen-Tzung Chien (National Yang Ming Chiao Tung University)*; Yuan-An Chen (National Yang Ming
Chiao Tung University)

5123: EURO: ESPnet Unsupervised ASR Open-source Toolkit

Dongji Gao (Johns Hopkins University)*; Jiatong Shi (Carnegie Mellon University); Shun-Po Chuang
(National Taiwan University); Paola Garcia (Johns Hopkins University); Hung-yi Lee (National Taiwan
University); Shinji Watanabe (Carnegie Mellon University); Sanjeev Khudanpur (Johns Hopkins
University)

5134: Voice-preserving Zero-shot Multiple Accent Conversion

Mumin Jin (MIT)*; Prashant Serai (Meta AI); Jilong Wu (Meta AI); Andros Tjandra (Meta Platforms, Inc);
Vimal Manohar (Meta Platforms Inc. ); Qing He (Meta)

5146: SPEECH-TEXT BASED MULTI-MODAL TRAINING WITH BIDIRECTIONAL ATTENTION FOR

IMPROVED SPEECH RECOGNITION
Yuhang Yang (School of Information Science and Engineering, Xinjiang University, China); Haihua Xu
(Temasek Laboratories, Nanyang Technological University, Singapore); Hao Huang (Xinjiang University)*;
Eng Siong Chng (Nanyang Technological University); Sheng Li (National Institute of Information &
Communications Technology (NICT))

5169: Joint Training And Decoding for Multilingual End-to-End Simultaneous Speech Translation
Wuwei Huang (Xiaomi Corporation)*; Renren Jin (Tianjin University); Wen Zhang (Xiaomi AI Lab); Jian
Luan (Xiaomi AI Lab); Bin Wang (Xiaomi AI Lab); Deyi Xiong (Tianjin University)

5204: A Fast and Accurate Pitch Estimation Algorithm Based on the Pseudo Wigner-Ville
Distribution
Yisi Liu (University of Chinese Academy of Sciences)*; Peter Wu (UC Berkeley); Alan Black (CMU);
Gopala Krishna Anumanchipalli (UC Berkeley)

223
5207: Federated Self-Learning with Weak Supervision for Speech Recognition
Milind M Rao (Amazon)*; Gopinath Chennupati (Amazon Alexa); Gautam Tiwari (Amazon); Anit Kumar
Sahu (Amazon Alexa AI); Anirudh Raju (Amazon Alexa); Ariya Rastrow (Amazon); Jasha Droppo
(Amazon)

5209: FREEVC: TOWARDS HIGH-QUALITY TEXT-FREE ONE-SHOT VOICE CONVERSION

Jingyi Li (Wuhan University)*; Weiping Tu (Wuhan University); Li Xiao (School of Computer Science,
Wuhan University)

5226: Learning Cross-lingual Visual Speech Representations

Andreas Zinonos (Imperial College London)*; Alexandros Haliassos (Imperial College London);
Pingchuan Ma (Meta); Stavros Petridis (Imperial College London); Maja Pantic (Imperial College London)

5238: SERI: SkEtching-Reasoning-Integrating Progressive Workflow for Empathetic Response

Generation
Guanqun Bi (Institute of Information Engineering, Chinese Academy of Sciences; School of Cyber
Security, University of Chinese Academy of Sciences)*; Yanan Cao (Institute of Information Engineering,
Chinese Academy of Sciences); Piji Li (Nanjing University of Aeronautics and Astronautics); Yuqiang Xie
(Institute of Information Engineering, Chinese Academy of Sciences); Fang Fang (Institute of Information
Engineering, Chinese Academy of Sciences); Zheng Lin (iie)

5242: WEIGHTED SAMPLING FOR MASKED LANGUAGE MODELING

Linhan Zhang (University of New South Wales)*; Qian Chen (Speech Lab, DAMO Academy, Alibaba
Group); Wen Wang (Alibaba Group); Chong Deng (Alibaba inc); Xin Cao (University of New South
Wales); Kongzhang Hao (UNSW); Yuxin Jiang (HKUST); Wei Wang (Hong Kong University of Science
and Technology (Guangzhou))

5249: ZEPHYR: ZERO-SHOT PUNCTUATION RESTORATION

Minghan Wang (Huawei)*; Yinglu Li (HUAWEI TECHNOLOGIES CO., LTD.); Jiaxin GUO (Huawei);
Xiaosong Qiao (Huawei); Chang Su (Huawei); Min Zhang (Huawei); Shimin Tao (Huawei); Hao Yang
(Huawei)

5259: towards a unified Conformer structure: from ASR to ASV task

Dexin Liao (Xiamen University); Tao Jiang (Xiamen Talentedsoft Co., Ltd.); Feng Wang (Xiamen
University); Lin Li (Xiamen University); Qingyang Hong (Xiamen University)*

5290: Knowledge-aware Few Shot Learning for Event Detection from Short Texts
Jinjin Guo (JD Intelligent Cities Research); Zhichao Huang (JD Intelligent Cities Research)*; Guangning
Xu (Harbin Institute of Technology, Shenzhen ▲); Bowen Zhang (Shenzhen Technology University);
Chaoqun Duan (JD AI Research)

5295: Conditional Conformer: Improving Speaker Modulation for Single and Multi-User Speech
Enhancement
Tom O'Malley (Google)*; Shaojin Ding (Google); Arun Narayanan (Google Inc.); Quan Wang (Google);
Rajeev Rikhye (Google); Qiao Liang (Google Inc.); Yanzhang He (Google); Ian McGraw ()

5325: MUG: A General Meeting Understanding and Generation Benchmark

Qinglin Zhang (Alibaba)*; Chong Deng (Alibaba inc); Jiaqing Liu (Speech Lab, Alibaba Group); Hai Yu
(Alibaba); Qian Chen (Speech Lab, DAMO Academy, Alibaba Group); Wen Wang (Alibaba Group); Zhijie
Yan (Alibaba Inc.); Jinglin Liu (Zhejiang University); Yi Ren (Bytedance); Zhou Zhao (Zhejiang University)

5331: MODELING TURN-TAKING IN HUMAN-TO-HUMAN SPOKEN DIALOGUE DATASETS USING

SELF-SUPERVISED FEATURES
Edmilson da Silva Morais (IBM Research Brazil)*; Matheus Damasceno (IBM Research); Hagai Aronowitz
(IBM Research - AI); Aharon Satt (IBM Research ); Ron Hoory (IBM Research)

224
5337: PREDICTING MULTI-CODEBOOK VECTOR QUANTIZATION INDEXES FOR KNOWLEDGE
DISTILLATION
Liyong Guo (Northwestern Polytechnical University); Xiaoyu Yang (Xiaomi Corp., Beijing)*; Quandong
Wang (Xiaomi Corp., Beijing); Yuxiang Kong (Xiaomi Corp., Beijing); Zengwei Yao (Xiaomi Corp., Beijing);
fan cui (xiaomi); Fangjun Kuang (Xiaomi Corp., Beijing); Wei Kang (Xiaomi Corp., Beijing, China); Long
Lin (Xiaomi Corp., Beijing); Mingshuang Luo (Xiaomi Corp., Beijing); Piotr Żelasko (Johns Hopkins
University); Daniel Povey (Johns Hopkins University)

5339: BERT is Robust! A Case Against Word Substitution-based Adversarial Attacks

Jens Hauser (ETHZ); Zhao Meng (ETHZ)*; Damian Pascual (ETHZ); Roger Wattenhofer (ETH Zurich)

5342: Adapting self-supervised models to multi-talker speech recognition using speaker

embeddings
Zili Huang (Johns Hopkins University)*; Desh Raj (Johns Hopkins University); Paola Garcia (Johns
Hopkins University); Sanjeev Khudanpur (Johns Hopkins University)

5344: EXPLORING THE ROLE OF FRICATIVES IN CLASSIFYING HEALTHY SUBJECTS AND

PATIENTS WITH AMYOTROPHIC LATERAL SCLEROSIS AND PARKINSON’S DISEASE
Tanuka Bhattacharjee (Indian Institute of Science)*; Yamini BK (NIMHANS); Nalini Atchayaram
(NIMHANS); Ravi Yadav (NIMHANS); Prasanta Dr Ghosh (Indian Institute of Science (IISc), Bangalore)

5356: Cross-utterance ASR Rescoring with Graph-based Label Propagation

Srinath Tankasala (The University of Texas at Austin); Long Chen (Amazon)*; Andreas Stolcke (Amazon);
Anirudh Raju (Amazon Alexa); Qianli Deng (Amazon); Chander Chandak (Amazon); Aparna Khare
(Amazon); Roland Maas (Amazon Inc.); Venkatesh Ravichandran (Amazon)

5361: Identifying Source Speakers for Voice Conversion based Spoofing Attacks on Speaker
Verification
Danwei Cai (Duke university)*; Zexin Cai (Duke University); Ming Li (Duke Kunshan University)

5362: Enhancement of text-predicting style token with generative adversarial network for
expressive speech synthesis
Hiroki Kanagawa (NTT Corporation)*; Yusuke Ijima (NTT Corporation)

5363: STATIC AND DYNAMIC SOURCE AND FILTER CUES FOR CLASSIFICATION OF
AMYOTROPHIC LATERAL SCLEROSIS PATIENTS AND HEALTHY SUBJECTS
Tanuka Bhattacharjee (Indian Institute of Science)*; Chowdam Venkata Thirumala Kumar (Indian Institute
of Science,Bengaluru); Yamini BK (NIMHANS); Nalini Atchayaram (NIMHANS); Ravi Yadav (NIMHANS);
Prasanta Dr Ghosh (Indian Institute of Science (IISc), Bangalore)

5381: Enhancing Ontology Translation through Cross-Lingual Agreement

Mingjie Tian (School of Artificial Intelligence, Jilin University); Fausto Giunchiglia (University of Trento);
Rui Song (School of Artificial Intelligence, Jilin University); Xing chen (Jilin University); Hao Xu (Jilin
University)*

5384: Modular Conformer Training for Flexible End-to-End ASR

Kartik Audhkhasi (Google)*; Brian Farris (Google); Bhuvana Ramabhadran (Google); Pedro J Moreno
(Google)

5406: Articulation GAN: Unsupervised modeling of articulatory learning

Gasper Begus (UC Berkeley)*; Alan Zhou (Johns Hopkins University); Peter Wu (UC Berkeley); Gopala
Krishna Anumanchipalli (UC Berkeley)

225
5415: LEARNING TO BUILD REASONING CHAINS BY RELIABLE PATH RETRIEVAL
Minjun Zhu (CASIA); Yixuan Weng (CASIA); Shizhu He (Institute of Automation, Chinese Academy of
Sciences); Kang Liu (Institute of Automation, Chinese Academy of Sciences); Jun Zhao (Institute of
Automation, Chinese Academy of Sciences)*

5418: EFFICIENT STUTTERING EVENT DETECTION USING SIAMESE NETWORKS

Payal Mohapatra (Northwestern University)*; Bashima Islam (Worcester Polytechnic Institute); MD
Tamzeed Islam (Amazon); Ruochen Jiao (Northwestern University); Zhu Qi (Northwestern University)

5423: IMPROVING TRANSFORMER-BASED END-TO-END SPEAKER DIARIZATION BY ASSIGNING

AUXILIARY LOSSES TO ATTENTION HEADS
Ye-Rin Jeoung (Hanyang University); Joon-Young Yang (Hanyang University); Jeong-Hwan Choi
(Hanyang University); Joon-Hyuk Chang (Hanyang University)*

5424: IMPROVING FAIRNESS AND ROBUSTNESS IN END-TO-END SPEECH RECOGNITION

THROUGH UNSUPERVISED CLUSTERING
Irina-Elena Veliche (Meta)*; Pascale Fung (Hong Kong University of Science and Technology)

5434: IMPROVING NON-AUTOREGRESSIVE SPEECH RECOGNITION WITH AUTOREGRESSIVE

PRETRAINING
Yanjia Li (Fano Labs)*; Lahiru T Samarakoon (Fano Labs, Hong Kong); Ivan Fung (Fano Labs)

5439: DVQVC: AN UNSUPERVISED ZERO-SHOT VOICE CONVERSION FRAMEWORK

Dayong Li (Westlake University)*; xian li (westlake university); Xiaofei Li (Westlake University)

5445: COMPENSATORY DEBIASING FOR GENDER IMBALANCES IN LANGUAGE MODELS

Tae-Jin Woo (Korea University)*; Woo-Jeoung Nam (Kyungpook National University); Yeong-Joon Ju
(Korea University); Seong-Whan Lee (Korea University)

5447: SAMO: Speaker Attractor Multi-Center One-Class Learning for Voice Anti-Spoofing
Siwen Ding (Columbia University)*; You Zhang (University of Rochester); Zhiyao Duan (Unversity of
Rochester)

5451: Choice Fusion as Knowledge for Zero-Shot Dialogue State Tracking

Ruolin Su (Georgia Institute of Technology)*; Jingfeng Yang (Amazon); Ting-Wei Wu (Georgia Institute of
Technology); Biing-Hwang Juang (Georgia Institute of Technology)

5455: Cleanformer: A Multichannel Array Configuration-Invariant Neural Enhancement Frontend

for ASR in Smart Speakers
Joseph P Caroselli (Google)*; Arun Narayanan (Google Inc.); Nathan Howard (Google); Tom O'Malley
(Google)

5456: Text Classification in the Wild: A Large-Scale Long-Tailed Name Normalization Dataset
Jiexing Qi (Shanghai Jiao Tong University)*; Shuhao Li (Shanghai Jiao Tong University ); Zhixin Guo
(Shanghai Jiao Tong University); Yusheng Huang (Shanghai Jiao Tong University); Chenghu Zhou
(Shanghai Jiao Tong University); Weinan Zhang (Shanghai Jiao Tong University); Xinbing Wang
(Shanghai Jiao Tong University); Zhouhan Lin (Shanghai Jiao Tong University)

5463: KG-ECO: Knowledge Graph Enhanced Entity Correction for Query Rewriting
Jinglun Cai (Amazon.com, Inc)*; Mingda Li (Amazon); Ziyan Jiang (Amazon); Eunah Cho (Amazon);
Zheng Chen (Amazon Alexa AI); Yang Liu (Amazon, Alexa AI); Xing Fan (Amazon); Chenlei Guo
(Amazon)

5465: UML: A Universal Monolingual Output Layer for Multilingual ASR

Chao Zhang (Tsinghua University)*; Bo Li (Google); Tara Sainath (Google); Trevor Strohman (Google);
Shuo-yiin Chang (Google)

226
5473: IMPORTANCE OF DIFFERENT TEMPORAL MODULATIONS OF SPEECH: A TALE OF TWO
PERSPECTIVES
Samik Sadhu (Johns Hopkins University)*; Hynek Hermansky (The Johns Hopkins University, USA)

5491: Improving Fast-slow Encoder based Transducer with Streaming Deliberation

Ke Li (Meta AI)*; Jay Mahadeokar (Meta AI); Jinxi Guo (Meta ); Yangyang Shi (Meta AI); Gil Keren (Meta
AI); Ozlem Kalinli (Meta AI); Michael Seltzer (Meta AI); Duc Le (Meta AI)

5496: Dynamic Alignment Mask CTC: Improved Mask-CTC with Aligned Cross Entropy
Xulong Zhang (Ping An Technology (Shenzhen) Co., Ltd.); Haobin Tang (USTC); Jianzong Wang (Ping
An Technology (Shenzhen) Co., Ltd)*; Ning Cheng (Ping An Technology (Shenzhen) Co., Ltd); Jian Luo
(Ping An Technology (Shenzhen) Co., Ltd); Jing Xiao (Ping An Insurance (Group) Company of China)

5502: Avoid Overthinking in Self-Supervised Models for Speech Recognition

Dan Berrebbi (Carnegie Mellon University)*; Brian Yan (Carnegie Mellon University); Shinji Watanabe
(Carnegie Mellon University)

5503: Code-Switching Text Generation and Injection in Mandarin-English ASR

Haibin Yu (Shanghai Jiao Tong University)*; Yuxuan Hu (Microsoft); Yao Qian (Microsoft); Ma Jin
(Microsoft); Linquan Liu (Microsoft); Shujie Liu (Microsoft Research Asia); Yu Shi (Microsoft); Yanmin
Qian (Shanghai Jiao Tong University); Ed C Lin (Microsoft); Michael Zeng (Microsoft)

5504: On the effectiveness of monoaural target source extraction for distant end-to-end automatic
speech recognition
Catalin Zorila (Toshiba Cambridge Research Laboratory)*; Rama S Doddipatla (Toshiba Europe LTD)

5520: More Speaking or More Speakers?

Dan Berrebbi (Carnegie Mellon University); Ronan Collobert (Apple); Navdeep Jaitly (Apple); Tatiana
Likhomanenko (Apple)*

5523: FILLER WORDS DETECTION WITH HARD CATEGORY MINING AND INTER-CATEGORY
FOCAL LOSS
Zhiyuan Zhao (MSRA)*; Lijun Wu (Microsoft Research); Chuanxin Tang (Microsoft); Dacheng Yin
(University of Science and Technology of China); Yucheng Zhao (University of Science and Technology of
China); Chong Luo (MSRA)

5532: DasFormer: deep alternating spectrogram transformer for multi/single-channel speech

separation
Shuo Wang (MSFT); Xiangyu Kong (Microsoft Research Asia)*; Xiulian Peng (Microsoft Research Asia);
Mahmood Movassagh (Microsoft); Vinod Prakash (Microsoft); Yan Lu (Microsoft Research Asia)

5557: TFCNET: TIME-FREQUENCY DOMAIN CORRECTOR FOR SPEECH SEPARATION

Weinan Tong (Tsinghua University)*; Jiaxu Zhu (Tsinghua University); Jun Chen (Tsinghua University);
Zhiyong Wu (Tsinghua University); Shiyin Kang (XVerse Inc.); Helen Meng (The Chinese University of
Hong Kong)

5558: Conversation-oriented ASR with multi-look-ahead CBS architecture

Huaibo Zhao (Waseda University)*; Shinya Fujie (Waseda University); Tetsuji Ogawa (Waseda
University); Jin Sakuma (Waseda University); Yusuke Kida (LINE Corp); Tetsunori Kobayashi (Waseda
University)

5568: VQ-CL: Learning disentangled speech representations with contrastive learning and vector
quantization
Huaizhen Tang (University of Science and Technology of China); Xulong Zhang (Ping An Technology
(Shenzhen) Co., Ltd.); Jianzong Wang (Ping An Technology (Shenzhen) Co., Ltd)*; Ning Cheng (Ping An
Technology (Shenzhen) Co., Ltd); Jing Xiao (Ping An Insurance (Group) Company of China)

227
5579: Lightweight feature encoder for wake-up word detection based on self-supervised speech
representation
Hyungjun Lim (LG AI Research)*; Younggwan Kim (LG AI Research); Kiho Yeom (LG AI Research);
Eunjoo Seo (LG AI Research); Hoodong Lee (LG AI Research); Stanley Jungkyu Choi (LG AI Research);
Honglak Lee (LG AI Research)

5584: Transcription free filler word detection with Neural semi-CRFs

Ge Zhu (University of Rochester)*; Yujia Yan (University of Rochester); Juan-Pablo Caceres (Stanford);
Zhiyao Duan (Unversity of Rochester)

5596: Mask The Bias: Improving Domain-Adaptive Generalization of CTC-based ASR with Internal
Language Model Estimation
Nilaksh Das (AWS AI Labs, Amazon)*; Monica Sunkara (Amazon); Sravan Babu Bodapati (Amazon);
Jinglun Cai (Amazon); Devang Kulshreshtha (Amazon); Jeff Farris (Amazon); Katrin Kirchhoff (Amazon)

5597: Parallel Sentence-Level Explanation Generation for Real-World Low-Resource Scenarios

Yan Liu (Microsoft Research)*; Xiaokang Chen (Peking University); Qi Dai (Microsoft Research)

5598: COMPARATIVE LAYER-WISE ANALYSIS OF SELF-SUPERVISED SPEECH MODELS

Ankita Pasad (Toyota Technological Institute at Chicago)*; Bowen Shi (Toyota Technological Institute at
Chicago); Karen Livescu (TTI-Chicago)

5603: Personalized Lightweight Text-to-Speech: Voice Cloning with Adaptive Structured Pruning
Sung-Feng Huang (National Taiwan University)*; Chia-ping Chen (Intelligo Technology Inc); Zhi-Sheng
Chen (Intelligo Technology Inc); Yu-Pao Tsai (Intelligo Technology Inc); Hung-yi Lee (National Taiwan
University)

5605: QI-TTS: Questioning Intonation Control for Emotional Speech Synthesis

Haobin Tang (USTC); Xulong Zhang (Ping An Technology (Shenzhen) Co., Ltd.); Jianzong Wang (Ping
An Technology (Shenzhen) Co., Ltd)*; Ning Cheng (Ping An Technology (Shenzhen) Co., Ltd); Jing Xiao
(Ping An Insurance (Group) Company of China)

5607: Using Adapters to Overcome Catastrophic Forgetting in End-to-End Automatic Speech

Recognition
Steven Vander Eeckt (KU Leuven)*; Hugo Van hamme (KU LEUVEN)

5616: URM4DMU: An User Representation Model for Darknet Markets Users

Hongmeng Liu (Beijing University of Posts and Telecommunications); zhao jiapeng (Beijing University of
Posts and Telecommunications)*; Yixuan Huo (Beijing University of Posts and Telecommunications);
Wang Yuyan (Beijing University of Posts and Telecommunications); Chun Liao (Institute of Information
Engineering, CAS); Liyan Shen (Beijing University of Posts and Telecommunications); Shiyao Cui
(Institute of Information Engineering, Chinese Academy of Sciences, Beijing, China); Jinqiao Shi (Beijing
University of Posts and Telecommunications)

5640: Articulatory Representation Learning Via Joint Factor Analysis and Neural Matrix
Factorization
Jiachen Lian (University of California Berkeley)*; Alan Black (CMU); Yijing Lu (University of Southern
California); Louis Goldstein (USC); Shinji Watanabe (Carnegie Mellon University); Gopala Krishna
Anumanchipalli (UC Berkeley)

5646: Pretraining Conformer with ASR for Speaker Verification

Danwei Cai (Duke university)*; Weiqing Wang (Duke University); Ming Li (Duke Kunshan University); Rui
Xia (ByteDance AI Lab); Chuanzeng Huang (Speech, Audio and Music Intelligence (SAMI) group,
ByteDance )

228
5649: VE-KWS: VISUAL MODALITY ENHANCED END-TO-END KEYWORD SPOTTING
Ao Zhang (Northwestern Polytechnical University)*; He Wang (NWPU); Pengcheng Guo (Northwestern
Polytechnical University); Yihui Fu (Northwestern Polytechnical University); Lei Xie (NWPU); Yingying
Gao (China Mobile Research Institute); Shilei Zhang (China Mobile Research Institute); Junlan Feng
(China Mobile Research)

5653: ACF: Aligned Contrastive Finetuning for Language and Vision Tasks
Wei Zhu (East China Normal University)*; Peng Wang (Northwestern Normal Univ); Xiaoling Wang (East
China Normal University); Yuan Ni (Ping An Technology); Guotong Xie (Ping An Technology (Shenzhen)
Co. Ltd.)

5660: Structured Pruning of Self-Supervised Pre-trained Models for Speech Recognition and
Understanding
Yifan Peng (Carnegie Mellon University)*; Kwangyoun Kim (ASAPP); Felix Wu (ASAPP); Prashant
Sridhar (ASAPP); Shinji Watanabe (Carnegie Mellon University)

5661: MARGIN-MIXUP: A METHOD FOR ROBUST SPEAKER VERIFICATION IN MULTI-SPEAKER

AUDIO
Jenthe Thienpondt (IDLab, Ghent University)*; Nilesh Madhu (IDLab, Ghent University - imec); Kris
Demuynck (Ghent Universitty)

5665: Numerical Semantic Modeling for Implicit Discourse Relation Recognition

Chenxu Wang (Department of Computer Science and Technology, Beijing Institute of Technology)*; Ping
Jian (Beijing Engineering Research Center of High Volume Language Information Processing and Cloud
Computing Applications, Department of Computer Science and Technology, Beijing Institute of
technology); Hai Wang (Beijing Institute of Technology)

5683: Designing and Evaluating Speech Emotion Recognition Systems: A reality check case study
with IEMOCAP
Nikolaos Antoniou (National Technical University of Athens)*; Athanasios Katsamanis ("ATHENA R.C.,
Behavioral Signal Technologies"); Theodoros Giannakopoulos (NCSR Demokritos); Shrikanth Narayanan
(University of Southern California)

5687: SELF-SUPERVISED ACCENT LEARNING FOR UNDER-RESOURCED ACCENTS USING

NATIVE LANGUAGE DATA
Mehul Kumar (Samsung Research); Jiyeon Kim (Samsung Research)*; Dhananjaya Gowda (Samsung
Electronics); Abhinav Garg (Stanford); Chanwoo Kim (Samsung Electronics)

5693: Learning From Yourself: A Self-Distillation Method for Fake Speech Detection
Jun Xue (Anhui Province Key Laboratory of Multimodal Cognitive Computation, School of Computer
Science and Technology, Anhui University)*; Cunhang Fan (Anhui Provincial Key Laboratory of
Multimodal Cognitive Computation, School of Computer Science and Technology, Anhui University);
Jiangyan Yi (National Laboratory of Pattern Recognition, Institute of Automation, Chinese Academy of
Sciences); chenglong wang (CASIA); Zhengqi Wen (Qiyuan Laboratory); Dan Zhang (Department of
Psychology, Tsinghua University); zhao lv (anhui university)

5700: Exploring universal singing speech language identification using self-supervised learning
based front-end features
Xingming Wang (Wuhan University)*; Hao Wu ( Speech, Audio and Music Intelligence (SAMI) group,
ByteDance); Chen Ding (Speech, Audio and Music Intelligence (SAMI) group, ByteDance); Chuanzeng
Huang (Speech, Audio and Music Intelligence (SAMI) group, ByteDance ); Ming Li (Duke Kunshan
University)

5711: EMix: A Data Augmentation Method for Speech Emotion Recognition

An Dang (National Central University)*; Toan H Vu (National Central University); Nguyen Dinh Le
(National Central University); Jia-Ching Wang (National Central University)

229
5730: Multi-View Learning for Speech Emotion Recognition With Categorical Emotion, Categorical
Sentiment, and Dimensional Scores
Daniel Tompkins (Microsoft)*; Dimitra Emmanouilidou (Microsoft Research); Soham Deshmukh
(Microsoft); Benjamin Elizalde (Microsoft)

5742: StarGAN-VC based Cross-Domain Data Augmentation for Speaker Verification

Hang-Rui Hu (University of Science and Technology of China)*; Yan Song (USTC); Jian-Tao Zhang
(University of Science and Technology of China); Lirong Dai (University of Science and Technology of
China); Ian v McLoughlin (The University of Science and Technology of China); ZHU ZHUO (alibaba); Yu
Zhou (alibaba); Yuhong Li (Alibaba); hui xue (Alibaba)

5744: Investigation into phone-based subword units for Multilingual end-to-end speech
recognition
Saierdaer Yusuyin (Xinjiang University)*; Hao Huang (Xinjiang University); Junhua Liu (University of
Science and Technology of China); Cong Liu (iFLYTEK Research)

5782: EXPRESSIVE-VC: HIGHLY EXPRESSIVE VOICE CONVERSION WITH ATTENTION FUSION OF

BOTTLENECK AND PERTURBATION FEATURES
Ziqian Ning (Northwestern Polytechnical University)*; Qicong Xie (Northwestern Polytechnical University);
Pengcheng Zhu (Fuxi AI Lab, NetEase Inc.); Zhichao Wang (Northwestern Polytechnical University);
Liumeng Xue (Northwestern Polytechnical University); Jixun Yao (Northwestern Polytechnical University);
Lei Xie (NWPU); Mengxiao Bi (Netease Fuxi AI Lab)

5784: RECOUPLE EVENT FIELD VIA PROBABILISTIC BIAS FOR EVENT EXTRACTION
Xingyu Bai (Tsinghua University); Taiqiang Wu (Tsinghua University); Han Guo (Tencent); Zhe Zhao
(Tencent ); Xuefeng Yang (Tencent); Jiayi Li (Tsinghua University); Weijie Liu (Tencent Inc.); QI JU
(Tencent); weigang guo (Tencent); Yujiu Yang (Tsinghua University)*

5785: Self-Supervised Learning for Speech Enhancement Through Synthesis

Bryce Irvin (Bose Corporation); Marko Stamenovic (Bose Corp.)*; Mikolaj Kegler (Bose Corp.); Li-Chia
Yang (Bose Corp.)

5787: Unsupervised Voice Type Discrimination Score Adaptation Using X-vector Clusters
Mark R Lindsey (Carnegie Mellon University)*; Tyler Vuong (Carnegie Mellon University); Richard M Stern
(Carnegie Mellon University)

5788: Toroidal Probabilistic Spherical Discriminant Analysis

Anna Silnova ( Brno University of Technology)*; Niko Brummer (Amazon); Albert DP Swart (Speechly);
Lukáš Burget (Brno University of Technology)

5792: Multilingual Query-by-Example Keyword Spotting with Metric Learning and Phoneme-to-
Embedding Mapping
Paul M Reuter (Fraunhofer IDMT - HSA)*; Christian Rollwage (Fraunhofer IDMT - HSA); Bernd Meyer
(Carl von Ossietzky University Oldenburg)

5798: Fast and Efficient Speech Enhancement with Variational Autoencoders

Mostafa Sadeghi (INRIA)*; romain serizel (Université de Lorraine)

5806: Think before you speak: Concept-guided Explicit Persona Reasoning for Personalized
Dialogue Generation
Yunpeng Li (Institute of Information Engineering,Chinese Academy of Sciences)*; Yue Hu (Institute of
Information Engineering,Chinese Academy of Sciences); Wei Peng (Institute of Information Engineering,
Chinese Academy of Sciences); Yuqiang Xie (Institute of Information Engineering, Chinese Academy of
Sciences)

230
5824: FAST AND PARALLEL DECODING FOR TRANSDUCER
Wei Kang (Xiaomi Corp., Beijing, China)*; Liyong Guo (Xiaomi Corp.); Fangjun Kuang (Xiaomi Corp.);
Long Lin (Xiaomi Corp., Beijing, China); Mingshuang Luo (Xiaomi Corp., Beijing, China); Zengwei Yao
(Xiaomi Corp., Beijing, China); Xiaoyu Yang (Xiaomi Corp., Beijing, China); Piotr Żelasko (Johns Hopkins
University); Daniel Povey (Johns Hopkins University)

5826: Learning interpretable filters in Wav-Unet for speech enhancement

Félix MATHIEU (Telecom Paris)*; Thomas Courtat (Thales); Gaël Richard (Telecom Paris, Institut
polytechnique de Paris); Geoffroy Peeters (LTCI - Télécom Paris, IP Paris)

5845: FEDERATED LEARNING FOR ASR BASED ON WAV2VEC 2.0

Tuan Manh Nguyen (LIA, Avignon University); Salima Mdhaffar (LIA - University of Avignon); Natalia
Tomashenko (LIA, University of Avignon)*; Jean-Francois Bonastre (Université d’Avignon); Yannick
Estève (LIA - Avignon University)

5862: Auto-AVSR: Audio-Visual Speech Recognition with Automatic Labels

Pingchuan Ma (Meta)*; Alexandros Haliassos (Imperial College London); Adriana Fernandez-Lopez
(Meta); Honglie Chen (Meta); Stavros Petridis (Imperial College London); Maja Pantic (Facebook /
Imperial College London )

5882: LEARNING TO BALANCE THE GLOBAL COHERENCE AND INFORMATIVENESS IN

KNOWLEDGE-GROUNDED DIALOGUE GENERATION
Chenxu Niu (Institute of Information Engineering, Chinese Academy of Sciences)*; Yue Hu (Institute of
Information Engineering,Chinese Academy of Sciences); Wei Peng (Institute of Information Engineering,
Chinese Academy of Sciences); Yuqiang Xie (Institute of Information Engineering, Chinese Academy of
Sciences)

5902: Improving Accented Speech Recognition with Multi-Domain Training

Lucas Maison (Laboratoire Informatique d'Avignon); Yannick Estève (LIA - Avignon University)*

5905: FULLY UNSUPERVISED TOPIC CLUSTERING OF UNLABELLED SPOKEN AUDIO USING

SELF-SUPERVISED REPRESENTATION LEARNING AND TOPIC MODEL
Takashi Maekaku (Yahoo Japan Corporation)*; Yuya Fujita (Yahoo Japan Corporation); Xuankai Chang
(Carnegie Mellon University); Shinji Watanabe (Carnegie Mellon University)

5921: Efficient Uncertainty Estimation with Gaussian Process for Reliable Dialog Response
Retrieval
Tong Ye (Ping An Technology (Shenzhen) Co., Ltd. ;University of Science and Technology of China);
Zhitao Li (Ping An Technology （Shenzhen） Co., Ltd.); Jianzong Wang (Ping An Technology (Shenzhen)
Co., Ltd)*; Ning Cheng (Ping An Technology (Shenzhen) Co., Ltd); Jing Xiao (Ping An Insurance (Group)
Company of China)

5930: Preserving background sound in noise-robust voice conversion via multi-task learning
Jixun Yao (Northwestern Polytechnical University)*; Yi Lei (Northwestern Polytechnical University); Qing
Wang (Northwestern Polytechnical University); Pengcheng Guo (Northwestern Polytechnical University);
Ziqian Ning (Northwestern Polytechnical University); Lei Xie (NWPU); Hai Li (iQIYI Inc); Junhui Liu (iQIYI
Inc); Danming Xie (iQIYI)

5932: ANY-TO-ANY VOICE CONVERSION WITH F0 AND TIMBRE DISENTANGLEMENT AND NOVEL
TIMBRE CONDITIONING
Sudheer Kumar Kovela (Nvidia)*; Rafael Valle (NVIDIA); Ambrish Dantrey (Nvidia); Bryan Catanzaro
(NVIDIA)

5935: Enhancing Unsupervised Speech Recognition with Diffusion GANs

Xianchao Wu (NVIDIA Japan)*

231
5943: REPRESENTATION OF VOCAL TRACT LENGTH TRANSFORMATION BASED ON GROUP
THEORY
Atsushi Miyashita (Nagoya University)*; Tomoki Toda (Nagoya University)

5950: SINGLE-CHANNEL SPEECH ENHANCEMENT WITH DEEP COMPLEX U-NETWORKS AND

PROBABILISTIC LATENT SPACE MODELS
Eike J Nustede (Carl von Ossietzky University Oldenburg)*; Jörn Anemüller (Carl von Ossietzky
University Oldenburg)

5966: AN EMPIRICAL STUDY AND IMPROVEMENT FOR SPEECH EMOTION RECOGNITION

Zhen Wu (Nanjing University); Yizhe Lu (NanJing University)*; Xin-yu Dai (Nanjing University)

5970: HIGH-ACOUSTIC FIDELITY TEXT TO SPEECH SYNTHESIS WITH FINE-GRAINED CONTROL

OF SPEECH ATTRIBUTES
Rafael Valle (NVIDIA)*; João Felipe Santos (NVIDIA); Kevin Shih (NVIDIA); Rohan Badlani (NVIDIA);
Bryan Catanzaro (NVIDIA)

5976: Effectiveness of Mining Audio and Text Pairs from Public Data for Improving ASR Systems
for Low-Resource Languages
Kaushal Bhogale (Indian Institute of Technology, Madras)*; Abhigyan Raman (AI4Bharat); Tahir Javed
(Indian Institute of Technology Madras); Sumanth Doddapaneni (Robert Bosch Centre for Data Science
and AI); Anoop Kunchukuttan (Microsoft); Pratyush Kumar (Indian Institute of Technology Madras); Mitesh
M. Khapra (Indian Institute of Technology Madras)

5990: AE-Flow: AutoEncoder Normalizing Flow

Jakub Mosiński (Amazon)*; Piotr Bilinski (Amazon); Thomas Merritt (Amazon); Abdelhamid Ezzerg
(Amazon); Daniel Korzekwa (Nvidia)

5998: Tranferring Quantified Emotion Knowledge for the Detection of Depression in Alzheimer's
Disease Using ForestNets
Paula Andrea Pérez-Toro (Friedrich-Alexander-Universität Erlangen-Nürnberg)*; Dalia Rodríguez-Salas
(Friedrich-Alexander-Universität Erlangen-Nürnberg); Tomas Arias-Vergara (Friedrich-Alexander-
Universitaet Erlangen-Nuernberg); Sebastian P Bayerl (Technische Hochschule Nürnberg Georg Simon
Ohm); Philipp Klumpp (Pattern Recognition Lab, FAU Erlangen-Nuremberg); Korbinian Riedhammer
(Technische Hochschule Nürnberg Georg Simon Ohm); Maria Schuster (Ludwig Maximilian University of
Munich); Elmar Noeth (friedrich Alexander Universitat, Erlangen-Nuremberg); Andreas K Maier (Pattern
Recognition Lab, FAU Erlangen-Nuremberg); Juan Rafael Orozco-Arroyave (University of Antioquia)

6004: Unsupervised Noise Adaptation using Data Simulation

Chen Chen (Nanyang Technological University)*; Yuchen Hu (Nanyang Technological University); Heqing
Zou (Nanyang Technological University); Linhui Sun (Nanjing University of Posts and
Telecommunications); Eng Siong Chng (Nanyang Technological University)

6012: PMMSD: DEVELOPMENT OF THE MATRIX SENTENCE INTELLIGIBILITY DATASET FOR

MANDARIN WITH LOMBARD EFFECT
Hanchen Pei (Wuhan University); Yuhong Yang (Wuhan University)*; Xufeng Chen (School of Computer
Science, Wuhan University); Qingmu Liu (Wuhan University); Hongyang Chen (Wuhan University);
Weiping Tu (Wuhan University); Song Lin (Oppo)

6022: ANCIENT CHINESE WORD SEGMENTATION AND PART-OF-SPEECH TAGGING USING

DISTANT SUPERVISION
Shuo Feng (Nanjing University of Aeronautics and Astronautics)*; Piji Li (Nanjing University of
Aeronautics and Astronautics)

232
6027: SIAST: A Slot Imbalance-Aware Self-Training Scheme for Semi-Supervised Slot Filling
Jiachi Liu (Beijing University of Posts and Telecommunications)*; Sishi Xiong (Beijing University of Posts
and Telecommunications); Yuehuan He (University of Toronto); tong zhou (Beijing University of Posts and
Telecommunications); Liwen Wang (Beijing University of Posts and Telecommunications); Xuefeng Li
(Beijing University of Posts and Telecommunications); Bo Xiao (Beijing University of Posts and
Telecommunications)

6035: Moving Towards Non-Binary Gender Identification Via Analysis of System Errors in Binary
Gender Classification
Sebastian CG Ellis (University of Sheffield)*; Stefan Goetze (University of Sheffield); Heidi Christensen
(University of Sheffield)

6063: Leveraging Pretrained Representations with Task-related Keywords for Alzheimer's Disease
Detection
Jinchao Li (The Chinese University of Hong Kong)*; Kaitao Song (Microsoft Research Asia); Junan Li
(The Chinese University of Hong Kong); Bo ZHENG (the Chinese University of Hong Kong); Dongsheng
Li (Microsoft Research Asia); Xixin Wu (The Chinese University of Hong Kong); Xunying Liu (The Chinese
University of Hong Kong); Helen Meng (The Chinese University of Hong Kong)

6064: TOWARDS LEARNING EMOTION INFORMATION FROM SHORT SEGMENTS OF SPEECH

Tilak Purohit (Idiap Research Institute)*; Sarthak Yadav (Aalborg University); Bogdan Vlasenko (Idiap
Research Institute); S. Pavankumar Dubagunta (Uniphore Software Systems); Mathew Magimai.-Doss
(Idiap Research Institute)

6066: UNSUPERVISED WORD SEGMENTATION BASED ON WORD INFLUENCE

ruohao yan (Beijing Institute of Technology & xinjiang university)*; Hua-Ping Zhang (Beijing Institute of
Technology); Wushour Slamu (xinjiang university); Askar Hamdulla (Xinjiang University)

6078: The DKU Post-Challenge Audio-Visual Wake Word Spotting System for the 2021 MISP
Challenge: Deep Analysis
Haoxu Wang (Wuhan University); Ming Cheng (Duke Kunshan University); Qiang Fu (Alibaba Group);
Ming Li (Duke Kunshan University)*

6079: Absolute decision corrupts absolutely: conservative online speaker diarisation

Youngki Kwon (Naver Corporation)*; Heesoo Heo (Naver Corp.); Bong-Jin Lee (Naver Corporation); You
Jin Kim (Naver Corporation); Jee-weon Jung (Naver Corp.)

6080: INCORPORATING UNCERTAINTY FROM SPEAKER EMBEDDING ESTIMATION TO SPEAKER

VERIFICATION
Qiongqiong Wang (A*STAR )*; Kong Aik Lee (Institute for Infocomm Research, A*STAR); Tianchi Liu
(Institute for Infocomm Research, A*STAR)

6081: DOCRED-FE: A DOCUMENT-LEVEL FINE-GRAINED ENTITY AND RELATION EXTRACTION

DATASET
Hongbo Wang (Peking University)*; Weimin Xiong (Peking University); Yifan Song (Peking University);
Dawei Zhu (Peking University); Yu Xia (Peking University); Sujian Li (Peking University)

6085: PUFFIN: PITCH-SYNCHRONOUS NEURAL WAVEFORM GENERATION FOR FULLBAND

SPEECH ON MODEST DEVICES
Oliver Watts (SpeakUnique)*; Lovisa Wihlborg (SpeakUnique); Cassia Valentini (SpeakUnique)

6093: Lattice-free Sequence Discriminative Training for Phoneme-based Neural Transducers

Zijian Yang (Lehrstuhl fuer Informatik 6, RWTH Aachen)*; Wei Zhou (RWTH Aachen University); Ralf
Schlüter (RWTH Aachen University); Hermann Ney ( RWTH Aachen University)

233
6105: Metric-oriented Speech Enhancement using Diffusion Probabilistic Model
Chen Chen (Nanyang Technological University)*; Yuchen Hu (Nanyang Technological University); Weiwei
Weng (Nanyang Technological University); Eng Siong Chng (Nanyang Technological University)

6116: Factorized AED: Factorized Attention-based Encoder-Decoder for Text-only Domain

Adaptive ASR
Xun Gong (Shanghai Jiaotong University)*; wei wang (Shanghai Jiao Tong University); Hang Shao
(Shanghai Jiao Tong University); Yanmin Qian (Shanghai Jiao Tong University)

6131: A Hierarchical Regression Chain Framework for Affective Vocal Burst Recognition
Jinchao Li (The Chinese University of Hong Kong)*; Xixin Wu (The Chinese University of Hong Kong);
Kaitao Song (Microsoft Research Asia); Dongsheng Li (Microsoft Research Asia); Xunying Liu (The
Chinese University of Hong Kong); Helen Meng (The Chinese University of Hong Kong)

6140: A processing framework to access large quantities of whispered speech found in ASMR
Pablo Pérez Zarazaga (KTH Royal Institute of Technology); Gustav Eje Henter (KTH Royal Institute of
Technology); Zofia Malisz (KTH Royal Institute of Technology)*

6156: DELAY-PENALIZED TRANSDUCER FOR LOW-LATENCY STREAMING ASR

Wei Kang (Xiaomi Corp., Beijing, China); Zengwei Yao (Xiaomi Corp.)*; Fangjun Kuang (Xiaomi Corp.);
Liyong Guo (Xiaomi Corp.); Xiaoyu Yang (Xiaomi Corp.); Long Lin (Xiaomi Corp. ); Piotr Żelasko (Johns
Hopkins University); Daniel Povey (Johns Hopkins University)

6177: Singing Voice Synthesis Based on a Musical Note Position-aware Attention Mechanism
Yukiya Hono (Nagoya Institute of Technology)*; Kei Hashimoto (Nagoya Institute of Technology);
Yoshihiko Nankaku (Nagoya Institute of Technology); Keiichi Tokuda (Department of Computer Science
and Engineering, Nagoya Institute of Technology)

6200: Enhancing the Vocal Range of Single-Speaker Singing Voice Synthesis with Melody-
Unsupervised Pre-training
Shaohuan Zhou (Tsinghua University)*; Xu Li (ARC Lab, Tencent); Zhiyong Wu (Tsinghua University);
Ying Shan (Tencent); Helen Meng (The Chinese University of Hong Kong)

6203: Embedding a differentiable mel-cepstral synthesis filter to a neural speech synthesis

system
Takenori Yoshimura (Nagoya Institute of Technology)*; Shinji Takaki (Nagoya Institute of Technology);
Kazuhiro Nakamura (Techno-Speech, Inc.); Keiichiro Oura (Techno-Speech, Inc.); Yukiya Hono (Nagoya
Institute of Technology); Kei Hashimoto (Nagoya Institute of Technology); Yoshihiko Nankaku (Nagoya
Institute of Technology); Keiichi Tokuda (Department of Computer Science and Engineering, Nagoya
Institute of Technology)

6216: Efficient Speech Quality Assessment using Self-supervised Framewise Embeddings

Karl El Hajal (EPFL)*; Zihan Wu (EPFL); Neil Scheidwasser-Clow (University of Copenhagen); Gasser
Elbanna (MIT); Milos Cernak (Logitech Europe)

6219: History, Present and Future: Enhancing Dialogue Generation with Few-shot History-Future
Prompt
Yihe Wang (Wuhan University)*; Yitong Li (Huawei Technologies Co., Ltd.); Yasheng Wang (NoahArk
Lab, Huawei); Fei Mi (Huawei); pingyi zhou (Noah’s Ark Lab, Huawei); Jin Liu (School of Computer
Science, Wuhan University); Xin Jiang (Huawei Noah's Ark Lab); Qun Liu (Huawei Noah's Ark Lab)

6221: Massively Multilingual ASR on 70 Languages: Tokenization, Architecture, and Generalization

Capabilities
Andros Tjandra (Meta AI)*; Nayan Singhal (Facebook); David Zhang (Meta AI); Ozlem Kalinli (Meta AI);
Abdelrahman Mohamed (Rembrand Inc); Duc Le (Meta); Michael L. Seltzer (Meta)

234
6225: Wav2vec-based Detection and Severity Level Classification of Dysarthria from Speech
Farhad Javanmardi (Aalto University)*; Saska Tirronen (Aalto University); Manila Kodali (Aalto
University); Sudarsana Reddy Kadiri (Aalto University); Paavo Alku (Aalto University)

6269: Multilingual Word Error Rate Estimation: e-WER3

Shammur Chowdhury (QCRI)*; Ahmed Ali (Qatar Computing Research Institute, HBKU)

6281: ROBUST ACOUSTIC AND SEMANTIC CONTEXTUAL BIASING IN NEURAL TRANSDUCERS

FOR SPEECH RECOGNITION
Xuandi FU (Amazon Alexa); Kanthashree Mysore Sathyendra (Amazon)*; Ankur Gandhe (Amazon
Alexa); Jing Liu (Amazon.com); Grant P. Strimel (Amazon Alexa); Ross McGowan (Amazon Alexa);
Athanasios Mouchtaris (Amazon Alexa)

6298: Visual Information Matters for ASR Error Correction

Vanya BK (Indian Institute Of Technology, Madras)*; Shanbo Cheng (ByteDance); Ningxin Peng
(ByteDance); Yuchen Zhang (ByteDance)

6305: FINDADAPTNET: FIND AND INSERT ADAPTERS BY LEARNED LAYER IMPORTANCE

Junwei Huang (Carnegie Mellon University); Karthik Ganesan (CARNeGIE MELlON UNIVERSITY);
Soumi Maiti (CMU); Young Min Kim (Carnegie Mellon University); Xuankai Chang (Carnegie Mellon
University); Paul Pu Liang (Carnegie Mellon University); Shinji Watanabe (Carnegie Mellon University)*

6307: Continuous Action Space-based Spoken Language Acquisition Agent Using Residual
Sentence Embedding and Transformer Decoder
Ryota Komatsu (Tokyo Institute of Technology)*; Yusuke Kimura (Tokyo Institute of Technology); Takuma
Okamoto (National Institute of Information and Communications Technology); Takahiro Shinozaki (Tokyo
Institute of Technology)

6316: Automatic classification of vocal intensity category from speech

Manila Kodali (Aalto University)*; Sudarsana Reddy Kadiri (Aalto University); laura laaksonen (Huawei);
Paavo Alku (Aalto University)

6318: A Sentiment and Syntactic-Aware Graph Convolutional Network for Aspect-level Sentiment
Classification
Yuxin Yang (Northwest University)*; Xia Sun (Northwest University); Qiang Lu (Northwest university);
Richard F E Sutcliffe (Northwest University); Jun Feng (Northwest University)

6320: Effectiveness of Text, Acoustic, and Lattice-based representations in Spoken Language

Understanding tasks
Esaú Villatoro-Tello (Idiap Research Institute)*; Srikanth Madikeri (Idiap); Juan Pablo Zuluaga Gomez
(Idiap Research Institute); Bidisha Sharma (Uniphore); Seyyed Saeed Sarfjoo (Idiap Research Institute);
Iuliia Nigmatulina (Idiap Research Institute); Petr Motlicek (Idiap); Aliaksei V. IVANOU (Uniphore Inc.);
Aravind Ganapathiraju (Uniphore Software Systems Inc.)

6340: SPASHT: Semantic and PrAgmatic SpeecH Features for automatic assessment of autism
B Ashwini (Indraprastha Institute of Information Technology, New Delhi, India)*; Vrinda Narayan
(Indraprastha Institute of Information Technology, New Delhi, India); Jainendra Shukla (IIIT-Delhi)

6343: Estimating Shapley Values of Training Utterances for Automatic Speech Recognition Models
Ali Raza Syed (The Graduate Center, CUNY)*; Michael I Mandel (Brooklyn College, CUNY)

6344: PRACTICE OF THE CONFORMER ENHANCED AUDIO-VISUAL HUBERT ON MANDARIN AND

ENGLISH
Xiaoming Ren (OPPO); Chao Li (OPPO)*; Shenjian Wang (OPPO); Li Biao (oppo)

235
6348: UCorrect: An Unsupervised Framework for Automatic Speech Recognition Error Correction
Jiaxin GUO (Huawei)*; Minghan Wang (Huawei); Xiaosong Qiao (Huawei); Daimeng Wei (Huawei);
Hengchao Shang (HW-TSC); ZongYao LI (HW-TSC); Zhengzhe YU (HW-TSC); Yinglu Li (HUAWEI
TECHNOLOGIES CO., LTD.); Chang Su (Huawei); Min Zhang (Huawei); Shimin Tao (Huawei); Hao Yang
(Huawei)

6353: Improving Transformer-Based Networks with Locality for Automatic Speaker Verification
Mufan Sang (University of Texas at Dallas)*; Yong Zhao (Microsoft Corporation); GANG Liu (Microsoft);
John H Hansen (Univ. of Texas at Dallas); Jian WU (Microsoft Corp)

6367: Relative dynamic time warping comparison for pronunciation errors

Caitlin Richter (Reykjavik University)*; Jon Gudnason (Reykjavik University)

6369: Unsupervised Out-of-Distribution Detection Using Few In-Distribution Samples

Chandan Gautam (A*STAR (Institute for Infocomm Research))*; Aditya Kane (Pune Institute of Computer
Technology); Ramasamy Savitha (I2R A*STAR); Suresh Sundaram (Indian Institute of Science)

6371: Towards Building Text-To-Speech Systems for the Next Billion Users
Gokul Karthik Kumar (Mohamed Bin Zayed University of Artificial Intelligence)*; Praveen S V (Indian
Institute of Technology Madras); Pratyush Kumar (Indian Institute of Technology Madras); Mitesh M.
Khapra (Indian Institute of Technology Madras); Karthik Nandakumar ( Mohamed Bin Zayed University of
Artificial Intelligence)

6376: SELF SUPERVISED BERT FOR LEGAL TEXT CLASSIFICATION

Arghya Pal (Monash University)*; Sailaja Rajanala (Monash University Malaysia); Raphael CW Phan
(Monash University); KokSheik Wong (Monash University Malaysia)

6379: I3D: Transformer architectures with input-dependent dynamic depth for speech recognition
Yifan Peng (Carnegie Mellon University)*; Jaesong Lee (NAVER); Shinji Watanabe (Carnegie Mellon
University)

6389: Noise-aware target extension with self-distillation for robust speech recognition
Ju-seok Seong (Hanyang University); Jeong-Hwan Choi (Hanyang University); Jehyun Kyung (Hanyang
University); Ye-Rin Jeoung (Hanyang University); Joon-Hyuk Chang (Hanyang University)*

6411: DiffVoice: Text-to-Speech with Latent Diffusion

Zhijun Liu (Shanghai Jiao Tong University)*; Yiwei Guo (Shanghai Jiao Tong University); Kai Yu
(Shanghai Jiao Tong University)

6418: DSPGAN: a GAN-based universal vocoder for high-fidelity TTS by time-frequency domain
supervision from DSP
Kun Song (Northwestern Polytechnical University)*; yongmao zhang (Audio, Speech and Language
Processing Group (ASLP@NPU), School of Computer Science, Northwestern Polytechnical University,
Xi’an, China); Yi Lei (Northwestern Polytechnical University); Jian Cong (Northwestern Polytechnical
University); Hanzhao Li (Northwestern Polytechnical University); Lei Xie (NWPU); Gang He (TAL
Education Group); Jinfeng Bai (TAL Education Group)

6420: Good Neighbors Are All You Need for Chinese Grapheme-to-Phoneme Conversion
Jungjun Kim (DeepBrain AI Inc.)*; Changjin Han (DeepBrain AI Inc.); Gyuhyeon Nam (DeepBrain AI Inc.);
Gyeongsu Chae (DeepBrain AI Inc.)

6449: DATA2VEC-AQC: SEARCH FOR THE RIGHT TEACHING ASSISTANT IN THE TEACHER-
STUDENT TRAINING SETUP
Vasista Sai Lodagala (Indian Institute of Technology, Madras)*; Sreyan Ghosh (University of Maryland,
College Park); S Umesh (IIT Chennai)

236
6458: PHONEix: Acoustic Feature Processing Strategy for Enhanced Singing Pronunciation with
Phoneme Distribution Predictor
Yuning Wu (Renmin University of China)*; Jiatong Shi (Carnegie Mellon University); Tao Qian (RUC);
Dongji Gao (Johns Hopkins University); Qin Jin (Renmin University of China)

6477: Incorporating Visual Information Reconstruction into Progressive Learning for Optimizing
Audio-Visual Speech Enhancement
Chen-Yue Zhang (USTC)*; Hang Chen (USTC); Jun Du (University of Science and Technology of China);
Baocai Yin (USTC,iFLYTEK); Jia Pan (iFlytek Research); Chin-hui Lee (Georgia Institute of Technology)

6512: G2PL: Lexicon Enhanced Chinese Polyphone Disambiguation using BERT Adapter with a
New Dataset
Haifeng Zhao (Anhui University); Hongzhi Wan (Anhui University)*; Lili Huang (Anhui University;Institute
of Artificial Intelligence, Hefei Comprehensive National Science Center); Mingwei Cao (Anhui University)

6523: M3ST: MIX AT THREE LEVELS FOR SPEECH TRANSLATION

Xuxin Cheng (Peking University)*; Qianqian Dong (ByteDance); fengpeng yue (ByteDance); Tom Ko
(Bytedance ); Mingxuan Wang (Bytedance); Yuexian Zou (Peking University)

6560: MFCCGAN: A Novel MFCC-Based Speech Synthesizer Using Adversarial Learning

Mohammad Reza Hasanabadi (Shahid Beheshti University)*; Majid - Behdad (Shahid Beheshti
University); Davood Gharavian (Shahid Beheshti University)

237
 Special Sessions

6G Integrated Sensing and Communication (ISAC) from Theory to Practice – A

Signal Processing Perspective
3049: 6G integrated sensing and communication - Sensing assisted environmental reconstruction
and communication
Zhi Zhou (Huawei Technologies Co., Ltd., Chengdu 610000, China)*; Xianjin Li (Huawei Technologies
Co., Ltd., Chengdu 610000, China); Jia He (HUAWEI); Xiaoyan Bi (Huawei Technologies Canada Co.,
Ltd., Ottawa K2K 3J1, Canada); Yan Chen (Huawei Technologies); Guangjian Wang (Huawei
Technologies Co., Ltd., Chengdu 610000, China); peiying zhu (Huawei Technologies Canada)

3325: Neurally Augmented State Space Model for Simultaneous Communication and Tracking with
Low Complexity Receivers
Fernando Pedraza (Technische Universität Berlin)*; Giuseppe Caire (Technische Universität Berlin)

3456: Multi-View Millimeter-Wave Imaging Over Wireless Cellular Network

Xin Tong (Zhejiang University)*; Zhaoyang Zhang (Zhejiang University); Zhaohui Yang (Zhejiang
University)

3803: Joint Data Association, NLOS Mitigation, and Clutter Suppression for Networked Device-
Free Sensing in 6G Cellular Network
Qin Shi (The Hong Kong Polytechnic University); Liang Liu (The Hong Kong Polytechnic University)*;
Shuowen Zhang (The Hong Kong Polytechnic University)

4255: INTEGRATING THE SENSING AND RADIO COMMUNICATIONS CHANNEL MODELLING

FROM RADAR MUTUAL INTERFERENCE
Narcis Cardona (iTEAM Research Institute, Universitat Politècnica de València)*; Jhoan Samuel Romero
(iTEAM Research Institute, Univesitat Politècnica de València); Wenfei Yang (Huawei Technologies); Jian
Li (Huawei Technologies)

5326: Active Beam Tracking With Reconfigurable Intelligent Surface

Han Han (University of Toronto)*; Tao Jiang (University of Toronto); Wei Yu (University of Toronto)

Advances in Signal Processing and Machine Learning for Non-Intrusive Load

Monitoring
2170: A Wavelet Scattering Approach For Load Identification with Limited Amount of Training Data
Pascal A Schirmer (University of Hertfordhshire)*; Iosif Mporas (University of Hertfordshire)

2653: Applying Symmetrical Component Transform for Industrial Appliance Classification in Non-
Intrusive Load Monitoring
Anthony Faustine (Imr); Lucas Pereira (ITI, LARSyS, Técnico Lisboa)*

3326: ContiNILM: A Continual Learning Scheme for Non-Intrusive Load Monitoring

Stavros Sykiotis (National Technical University of Athens)*; Maria Kaselimi (National Technical University
of Athens); Anastasios Doulamis (Technical University of Crete); Nikolaos Doulamis (National Technical
University of Athens)

238
5853: Improving Knowledge Distillation for Non-Intrusive Load Monitoring through Explainability
Guided Learning
Djordje Batic (Univesity of Strathclyde)*; Giulia Tanoni (Università Politecnica delle Marche); Lina
Stankovic (University of Strathclyde); Vladimir Stankovic (University of Strathclyde); Emanuele Principi
(Università Politecnica delle Marche)

6414: IMPROVED APPLIANCE TRANSIENT FEATURE EXTRACTION VIA TEMPLATE MATCHING

Bo Liu (Tianjin University); Fenglei Chang (Tianjin University); Wenpeng Luan (Tianjin University)*;
Bochao Zhao (Tianjin University)

1753: ON MULTIPLE-INPUT/BINAURAL-OUTPUT ANTIPHASIC SPEAKER SIGNAL EXTRACTION

Xianrui Wang (Northwestern Polytechnical University); Ningning Pan (Northwestern Polytechnical
University); Jacob Benesty (INRS); Jingdong Chen (Northwestern Polytechnical University)*

2357: MODEL-MATCHING PRINCIPLE APPLIED TO THE DESIGN OF AN ARRAY-BASED ALL-

NEURAL BINAURAL RENDERING SYSTEM FOR AUDIO TELEPRESENCE
Yicheng Hsu (National Tsing Hua University); Chenghung Ma (National Tsing Hua University); Mingsian
Bai (National Tsing Hua University)*

4766: Beamformer-Guided Target Speaker Extraction

Mohamed Elminshawi (International Audio Laboratories Erlangen)*; Srikanth Raj Chetupalli (Fraunhofer
IIS); Emanuel Habets (AudioLabs Erlangen)

AI Security and Privacy in Speech and Audio Processing

673: PRIVACY-ENHANCED FEDERATED LEARNING AGAINST ATTRIBUTE INFERENCE ATTACK
FOR SPEECH EMOTION RECOGNITION
Huan Zhao ( Hunan University); Haijiao Chen (Hunan University)*; Yufeng Xiao (Hunan University); Zixing
Zhang (Hunan University)

2009: Privacy-Preserving Occupancy Estimation

Jennifer Williams (University of Southampton)*; Vahid Yazdanpanah (University of Southampton);
Sebastian Stein (University of Southampton)

3761: FEDERATED INTELLIGENT TERMINALS FACILITATE STUTTERING MONITORING

Yongzi Yu (Beijing institute of technology); Wanyong Qiu (Beijing Institute of Technology); Chen Quan
(Beijing Institute of Technology); Kun Qian (Beijing Institute of Technology)*; Zhihua Wang (The University
of Tokyo); Yu Ma (Beijing Institute of Technology); Bin Hu (Beijing Institute of Technology); Bjorn W.
Schuller (Imperial College London); Yoshiharu Yamamoto (The University of Tokyo)

4942: Beyond Neural-on-Neural Approaches to Speaker Gender Protection

Loes van Bemmel (Radboud University)*; Zhuoran Liu (Radboud University); Nik Vaessen (Radboud
University); Martha Larson (Radboud University)

6129: Distinguishable Speaker Anonymization based on Formant and Fundamental Frequency

Scaling
Jixun Yao (Northwestern Polytechnical University)*; Qing Wang (Northwestern Polytechnical University);
Yi Lei (Northwestern Polytechnical University); Pengcheng Guo (Northwestern Polytechnical University);
Lei Xie (NWPU); Namin Wang (Huawei Cloud); Jie Liu (Huawei Cloud)

239
 Automotive Radar Signal Processing and Machine Learning for Autonomous
Driving
2374: DOPPLER-CODED JOINT DIVISION MULTIPLE ACCESS WAVEFORM FOR AUTOMOTIVE
MIMO RADAR
Yanhua Wang (School of Information and Electronics, Beijing Institute of Technology;Electromagnetic
Sensing Research Center of CEMEE State Key Laboratory, Beijing Institute of Technology, Beijing,
China); Qiubo Pei (School of Information and Electronics, beijing institute of technology;Chongqing
Innovation Center, Beijing Institute of Technology, Chongqing, China); Xueyao Hu (School of Information
and Electronics, beijing institute of technology;Chongqing Innovation Center, Beijing Institute of
Technology, Chongqing, China)*; Jiamin Long (School of Information and Electronics, beijing institute of
technology;Chongqing Innovation Center, Beijing Institute of Technology, Chongqing, China); Hao Yu
(School of Information and Electronics, beijing institute of technology;Chongqing Innovation Center,
Beijing Institute of Technology, Chongqing, China); Le Zheng (School of Information and Electronics,
beijing institute of technology;Chongqing Innovation Center, Beijing Institute of Technology, Chongqing,
China)

3982: Multi-Carrier Wideband OCDM-Based THz Automotive Radar

Sangeeta Bhattacharjee (Indian Institute of Science, Bangalore)*; Kumar Vijay Mishra (United States
DEVCOM Army Research Laboratory); Ramesh Annavajjala (University of Massachusetts Boston);
Chandra Murthy (Indian Institute of Science)

5043: Machine learning based early debris detection using automotive low level radar data
Kanishka Tyagi (Aptiv Advance Research Center)*; Shan Zhang (Aptiv Advance Research Center);
Yihang Zhang (Aptiv Advance Research Center); John Kirkwood (Aptiv Advance Research Center);
Sanling Song (Aptiv); Narbik Manukian (Aptiv Advance Research Center)

5064: Joint Antenna Selection and Beamforming in Integrated Automotive Radar Sensing-
Communications with Quantized Double Phase Shifters
lifan xu (University of Alabama); Shunqiao Sun (The University of Alabama)*; Yimin D Zhang (Temple
University); Athina Petropulu (Rutgers)

Conversational Healthcare Interfaces

1644: HEALTHCALL CORPUS AND TRANSFORMER EMBEDDINGS FROM HEALTHCARE
CUSTOMER-AGENT CONVERSATIONS
Nikola Lackovic (Malakoff Humanis)*; Montacié Claude (Sorbonne Université); Cédric Lequilliec (Malakoff
Humanis); marie-josé Caraty (Sorbonne Université)

3195: Forecasting of breathing events from speech for respiratory support

Aki Harma (Philips)*; Ulf Grossekathofer (Philips Research); Okke Ouweltjes (Philips Research); Venkata
Srikanth Nallanthighal (Philips Research)

5137: Navigating and Reaching Therapeutic Goals with Dynamical Systems in Conversation-based
Interventions
Victor Ardulov (Amazon)*; Shrikanth Narayanan (USC)

5359: Exploiting prompt learning with pre-trained language models for Alzheimer's Disease
detection
Yi Wang (The Chinese University of Hong Kong)*; Jiajun Deng (The Chinese University of HongKong);
Tianzi Wang (The Chinese University of HongKong); Bo ZHENG (the Chinese University of Hong Kong);
Shoukang Hu (Nanyang Technological University); Xunying Liu (The Chinese University of Hong Kong);
Helen Meng (The Chinese University of Hong Kong)

240
6377: Egocentric Action Anticipation for Personal Health
Ivan Rodin (University of Catania)*; Antonino Furnari (University of Catania); Dimitrios Mavroeidis (Philips
Research); Giovanni Maria Farinella (University of Catania, Italy)

6428: A Controllable Lifestyle Simulator for use in Deep Reinforcement Learning Algorithms
Libio Gonçalves Braz (UPSSITECH)*; Allmin Susaiyah (Philips)

Data Driven and Machine Learning based Room Acoustic Modeling

2532: Towards Improved Room Impulse Response Estimation for Speech Recognition
Anton J Ratnarajah (University of Maryland, College Park)*; Ishwarya Ananthabhotla (Reality Labs
Research at Meta, Redmond, WA ); Vamsi Krishna Ithapu (Reality Labs Research at Meta, Redmond,
WA); Pablo Hoffmann ( Reality Labs Research at Meta, Redmond, WA); Dinesh Manocha (University of
Maryland at College Park); Paul Calamia ( Reality Labs Research at Meta, Redmond, WA)

3300: Learning Audio-Visual Dereverberation

Changan Chen (University of Texas at Austin)*; Wei Sun (University of Texas at Austin); David Harwath
(The University of Texas at Austin); Kristen Grauman (Facebook AI Research & UT Austin)

4315: Room Impulse Response Reconstruction Based on Spatio-Temporal-Spectral Features

Learned from a Spherical Microphone Array Measurement
AMY BASTINE (THE AUSTRALIAN NATIONAL UNIVERSITY)*; thushara abhayapala (The Australian
National University); Jihui (Aimee) Zhang (University of Southampton)

4415: Contrastive Representation Learning for Acoustic Parameter Estimation

Philipp Goetz (International Audio Laboratories Erlangen)*; Cagdas Tuna (Fraunhofer Institute for
Integrated Circuits IIS); Andreas Walther (Fraunhofer Institute for Integrated Circuits IIS); Emanuel Habets
(AudioLabs Erlangen)

4799: Interpolation of spatial room impulse responses using partial optimal transport
Aaron Geldert (Aalto University)*; Nils Meyer-Kahlen (Aalto University); Sebastian J Schlecht (Aalto
University)

4884: Simultaneous Acoustic Echo Sorting and 3-D Room Geometry Inference
Kathleen C MacWiliam (Department of Electrical Engineering (ESAT-STADIUS/ETC))*; Filip Elvander
(Aalto University); Toon van Waterschoot (Department of Electrical Engineering (ESAT-STADIUS/ETC))

4967: Blind Acoustic Room Parameter Estimation Using Phase Features

Christopher A Ick (New York University)*; Adib Mehrabi (Sonos Experience Limited); Wenyu Jin (Sonos,
Inc.)

Edge Learning for Emerging Wireless Technologies

312: Semi-Federated Learning for Edge Intelligence with Imperfect SIC
Wanli Ni (Beijing University of Posts and Telecommunications)*; Jingheng Zheng (Beijing University of
Posts and Telecommunications); Yonina Eldar (); Changsheng You (Southern University of Science and
Technology); Kaibin Huang (University of Hong Kong)

576: Calibrating AI Models for Few-Shot Demodulation via Conformal Prediction

Kfir Cohen (KCL)*; Sangwoo Park (King's College London); Osvaldo Simeone (King's College London);
Shlomo Shamai (The Technion)

241
2905: CADET: Control-Aware Dynamic Edge Computing for Real-Time Target Tracking in UAV
Systems
Luis Felipe Florenzan Reyes (University of L'Aquila)*; Francesco Smarra (University of L'Aquila);
Alessandro D'Innocenzo (University of L'Aquila); marco levorato (University of California, Irvine)

3457: RELIABLE BEAMFORMING AT TERAHERTZ BANDS: ARE CAUSAL REPRESENTATIONS

THE WAY FORWARD?
Christo Kurisummoottil Thomas (Virginia Tech)*; Walid Saad (Virginia Tech)

4520: Personalizing Federated Learning with Over-the-Air Computations

Zihan Chen (Singapore University of Technology and Design); Zeshen Li (Zhejiang University); Howard
H. Yang (ZJU-UIUC Institute)*; Tony Quek (Singapore University of Technology and Design)

4969: BER-aware dynamic resource management for edge-assisted goal-oriented communications

Francesco F Binucci (University of Perugia)*; Paolo Banelli (University of Perugia)

6336: Lyapunov-driven deep reinforcement learning for edge inference empowered by

Reconfigurable Intelligent Surfaces
Kyriakos Stylianopoulos (National and Kapodistrian University of Athens)*; Mattia Merluzzi (CEA-Leti);
Paolo Di Lorenzo (Sapienza University of Rome); George Alexandropoulos (National and Kapodistrian
University of Athens)

Graphical Inference and Modeling in Dynamical Systems

649: GraphIT: Iterative reweighted l1 algorithm for sparse graph inference in state-space models
Emilie Chouzenoux (Inria Saclay)*; Victor Elvira (University of Edinburgh)

1742: MATRIX RESOLVENT EIGENEMBEDDINGS FOR DYNAMIC GRAPHS

Vasileios Kalantzis (IBM Research); Panagiotis Traganitis (Michigan State University)*

3263: Extended Kalman Filter for Graph Signals in Nonlinear Dynamic Systems
Guy Sagi (Ben Gurion University of the Negev); Nir Shlezinger (Ben-Gurion University); Tirza S
Routtenberg (Ben Gurion University of the Negev)*

4316: Estimating Normalized Graph Laplacians in Financial Markets

José Vinícius de Miranda Cardoso (HKUST)*; Jiaxi Ying (The Hong Kong University of Science and
Technology); Sandeep Prof. Kumar (IIT Delhi); Daniel Palomar (The Hong Kong University of Science
and Technology)

4779: Dual-based Online Learning of Dynamic Network Topologies

Seyed Saman Saboksayr (University of Rochester)*; Gonzalo Mateos (University of Rochester)

5427: ESTIMATION OF TIME-VARYING GRAPH TOPOLOGIES FROM GRAPH SIGNALS

Yuhao Liu (Stony Brook University)*; Cui Chen (Stony Brook University); Marzieh Ajirak (Stony Brook
University); Petar Djuric ()

Intelligent and Semantic Communications for 5G Mobile Networks and Beyond

2242: Rate Region Characterization for Semantics and Bits Based Multiuser Communications
Xidong Mu (Queen Mary Univeristy of London)*; Yuanwei Liu (Queen Mary University of London)

3359: HARQ Delay Minimization of 5G Wireless Network with Imperfect Feedback

Weihang Ding (King's College London)*; Mohammad Shikh-Bahaei (King's College London)

242
3484: Multi-Agent Reinforcement Learning for Covert Semantic Communications over Wireless
Networks
Yining Wang (Beijing University of Posts and Telecommunications)*; Ye Hu (Columbia University);
HONGYANG DU (Nanyang Technological University); Tao Luo (Beijing University of Posts and
Communications); Dusit Niyato ()

5623: Asynchronous Federated Learning for Real-time Multiple Licence Plate Recognition through
Semantic Communication
renyou xie (Central South University); Chaojie Li (The University of New South Wales)*; Xiaojun Zhou
(Central South University); Zhao Yang Dong (The University of New South Wales)

6234: An Efficient Relay Selection Scheme for Relay-assisted HARQ

Weihang Ding (King's College London)*; Mohammad Shikh-Bahaei (King's College London)

6293: Adaptive CSI Feedback with Hidden Semantic Information Transfer

Jiaqi Cao (ShanghaiTech University)*; Lixiang Lian (ShanghaiTech University ); Yijie Mao (ShanghaiTech
University); Bruno Clerckx (Imperial College London)

6483: Generative Model Based Highly Efficient Semantic Communication Approach for Image
Transmission
TIANXIAO HAN (Zhejiang University); Jiancheng Tang (Zhejiang University); Qianqian Yang (Zhejiang
University)*; Yiping Duan (Tsinghua University); Zhaoyang Zhang (Zhejiang University); Zhiguo Shi
(Zhejiang University)

Learning on graphs for biology and medicine

2914: Deep spatio-temporal multiplex graph learning for cardiac imaging classification
Jaume Banus (Lausanne University Hospital (CHUV))*; Augustin Ogier (Lausanne University Hospital
(CHUV)); Roger Hullin (Lausanne University Hospital (CHUV)); Philippe Meyer (Geneva University
Hospital (HUG)); Ruud Van Heeswijk (Lausanne University Hospital (CHUV)); Jonas Richiardi (Lausanne
University Hospital (CHUV))

4165: GRAPH SIGNAL PROCESSING FOR NEUROGIMAGING TO REVEAL DYNAMICS OF BRAIN

STRUCTURE-FUNCTION COUPLING
Maria Giulia Preti (EPFL)*; Thomas A.W. Bolton (Centre Hospitalier Universitaire Vaudois); Alessandra
Griffa (EPFL/UNIGE/CHUV); Dimitri Van De Ville (Ecole Polytechnique F�d�rale de Lausanne - LIB)

4375: Multiple Signed Graph Learning for Gene Regulatory Network Inference
Abdullah Karaaslanli (Michigan State University)*; Satabdi Saha (Michigan State University); Taps Maiti
(Michigan State University); Selin Aviyente (Michigan State University)

4599: Predicting Brain Age using Transferable CoVariance Neural Networks

Saurabh Sihag (University of Pennsylvania)*; Gonzalo Mateos (University of Rochester); Corey McMillan
(University of Pennsylvania); Alejandro Ribeiro (University of Pennsylvania)

6456: Spatial Graph Signal Interpolation with an Application for Merging BCI Datasets with Various
Dimensionalities
Yassine El Ouahidi (IMT Atlantique)*; Lucas Drumetz (IMT Atlantique); Giulia Lioi (IMT Atlantique);
Nicolas Farrugia (IMT Atlantique); Bastien Pasdeloup (IMT Atlantique, Lab-STICC); Vincent Gripon (IMT
Atlantique)

243
Near-Field and Non-Planar Beamforming, Source Localization, and Adaptive Array
Processing
2309: Channel State Information-Free Artificial Noise-Aided Location-Privacy Enhancement
Jianxiu Li (University of Southern California)*; Urbashi Mitra (USC)

3446: Phase Retrieval for Rydberg Quantum Arrays

Peter Vouras (U.S Department of Defense)*; Kumar Vijay Mishra (United States DEVCOM Army
Research Laboratory); Alexandra Artusio-Glimpse (National Institute of Standards and Technology)

4418: Compressive estimation of near field channels for ultra massive-MIMO wideband THz
systems
Simon Tarboush (Independent Researcher)*; Anum Ali (Samsung Research America); Tareq Al-NAffouri
(CEMSE, KAUST)

6678: Utilization of Bessel Beams in Wideband Sub Terahertz Communication Systems to Mitigate
Beamsplit Effects in the Near-field
Arjun Singh (SUNY Polytechnic Institute)*; Vitaly Petrov (Northeastern University ); Josep Jornet
(Northeastern University)

6681: NBA-OMP: NEAR-FIELD BEAM-SPLIT-AWARE ORTHOGONAL MATCHING PURSUIT FOR

WIDEBAND THZ CHANNEL ESTIMATION
Ahmet M Elbir (University of Luxembourg)*; Kumar Vijay Mishra (United States DEVCOM Army Research
Laboratory); Symeon Chatzinotas (University of Luxembourg)

Neural speech and audio coding: emerging challenges and opportunities

929: AudioDec: An Open-source Streaming High-fidelity Neural Audio Codec
Yi-Chiao Wu (META)*; Israel Dejene Gebru (Reality Labs Research); Dejan Markovic (META); Alexander
Richard (META)

3436: Low-Bitrate Redundancy Coding of Speech Using a Rate-Distortion-Optimized Variational

Autoencoder
Jean-Marc Valin (Amazon)*; Jan Büthe (Amazon); Ahmed Mustafa (Amazon)

3491: High Quality Audio Coding with MDCTNet

Grant Davidson (Dolby Laboratories)*; Mark Vinton (Dolby Laboratories); Per Ekstrand (Dolby Sweden
AB); Cong Zhou (Dolby Laboratories); Lars F Villemoes (Dolby Sweden AB); Lie Lu (Dolby Laboratories)

3543: END-TO-END NEURAL AUDIO CODING IN THE MDCT DOMAIN

Hyungseob Lim (Yonsei University)*; Jihyun Lee (yonsei university); Byeong Hyeon Kim (Yonsei
University); Inseon Jang (Electronics and Telecommunications Research Institution); Hong-Goo Kang
(Yonsei University)

3657: A Perceptual Neural Audio Coder with A Mean-Scale Hyperprior

Joon Byun (Yonsei University)*; Seungmin Shin (Yonsei University); Young-Cheol Park (Yonsei
University); Jongmo Sung (ETRI); Seung-Kwon Beack (IEEE Broadcast Technology Society (BTS))

4687: DISENTANGLED FEATURE LEARNING FOR REAL-TIME NEURAL SPEECH CODING

Xue Jiang (Communication University of China); Xiulian Peng (Microsoft Research Asia)*; Yuan Zhang
(Communication University of China); Yan Lu (Microsoft Research Asia)

244
4715: LMCodec: A Low Bitrate Speech Codec With Causal Transformer Models
Teerapat Jenrungrot (University of Washington)*; Michael Chinen (Google); W. Bastiaan Kleijn (Google);
Jan Skoglund (Google); Zalán Borsos (Google); Neil Zeghidour (Google); Marco Tagliasacchi (Google)

4906: Native Multi-Band Audio Coding within Hyper-Autoencoded Reconstruction Propagation

Networks
Darius Petermann (Indiana University - Bloomington)*; Inseon Jang (Electronics and Telecommunications
Research Institution); Minje Kim (Indiana University)

5073: INDIVIDUAL SUB-BAND ESTIMATION APPROACH TO BANDWIDTH EXTENSION AND

ENHANCEMENT OF CODED SPEECH
Youngwon Choi (Gwangju Institute of Science and Technology); Eunkyun Lee (GIST); Inseon Jang
(Electronics and Telecommunications Research Institution); Jong Won Shin (Gwangju Institute of Science
and Technology)*

5088: MULTI-CHANNEL AUDIO SIGNAL GENERATION

W. Bastiaan Kleijn (Google)*; Michael Chinen (Google); Felicia S. C. Lim (Google); Jan Skoglund
(Google)

5161: Neural Feature Predictor and Discriminative Residual Coding for Low-Bitrate Speech Coding
Haici Yang (Indiana University)*; Wootaek Lim (ETRI); Minje Kim (Indiana University)

5911: Disentangling speech from surroundings with neural embeddings

Ahmed Omran (Google)*; Neil Zeghidour (Google); Zalán Borsos (Google); Félix de Chaumont Quitry
(Google); Malcolm Slaney (Google); Marco Tagliasacchi (Google)

Non-linear Joint Spatial-Spectral Speech Enhancement and Separation

2807: Streaming Multi-channel Speech Separation with Online Time-domain Generalized Wiener
Filter
Yi Luo (Tencent AI Lab)*

3112: Multi-Microphone Speaker Separation by Spatial Regions

Julian Wechsler (AudioLabs Erlangen)*; Srikanth Raj Chetupalli (Fraunhofer IIS); Wolfgang Mack
(AudioLabs Erlangen); Emanuel Habets (AudioLabs Erlangen)

3253: Exploiting spatial information with the informed complex-valued spatial autoencoder for
target speaker extraction
Annika Briegleb (Friedrich-Alexander-University Erlangen-Nürnberg)*; Mhd Modar Halimeh (Friedrich-
Alexander-University Erlangen-Nürnberg); Walter Kellermann (Friedrich-Alexander-University Erlangen-
Nürnberg)

3949: McNet: Fuse Multiple Cues for Multichannel Speech Enhancement

Yujie Yang (Westlake University)*; Changsheng Quan (Westlake University); Xiaofei Li (Westlake
University)

4787: Spatially Selective Deep Non-linear Filters for Speaker Extraction

Kristina Tesch (Universität Hamburg)*; Timo Gerkmann (Universität Hamburg)

245
 Quantum Computing for Machine Learning and Signal Processing

184: Learning Quantum Entanglement Distillation with Noisy Classical Communications

HARI HARA SUTHAN CHITTOOR (Kings College London)*; Osvaldo Simeone (King's College London)

4852: The role of initial entanglement in adaptive Gibbs state preparation on quantum computers
Sophia Economou (Virginia Tech)*; Ada Warren (Virginia Tech); Edwin Barnes (Virginia Tech)

5284: DISTRIBUTED QUANTUM SENSING NETWORK WITH GEOGRAPHICALLY CONSTRAINED

MEASUREMENT STRATEGIES
Yingkang Cao (University of Maryland-College Park)*; Xiaodi Wu (University of Maryland)

5405: Quantum Graph Transformers

Georgios Kollias (IBM Research)*; Vasileios Kalantzis (IBM Research); Theodoros Salonidis (IBM T.J.
Watson Research Center); Shashanka Ubaru (IBM Research)

6386: FINER-GRAINED DECOMPOSITION FOR PARALLEL QUANTUM MIMO PROCESSING

Minsung Kim (Princeton University)*; Kyle Jamieson (Princeton University)

6391: A Quantum Approach for Stochastic Constrained Binary Optimization

Sarthak Gupta (Virginia Tech); Vassilis Kekatos (Virginia Tech)*

Quantum Machine Learning Algorithms and Applications on NISQ Devices

1857: A Quantum Kernel Learning Approach to Low-Resource Spoken Command Recognition
Chao-Han Huck Yang (Georgia Institute of Technology )*; Bo Li (Google); Yu Zhang (Google); Nanxin
Chen (John Hopkins Universoty); Tara Sainath (Google); Sabato M Siniscalchi (Kore University of Enna);
Chin-hui Lee (Georgia Institute of Technology)

2107: PQLM - Multilingual Decentralized Portable Quantum Language Model

Shuyue Stella Li (Johns Hopkins University)*; Xiangyu Zhang (Johns Hopkins University); Shu Zhou
(HKUST); Hongchao Shu (Johns Hopkins University); Ruixing Liang (Johns Hopkins University); Hexin
Liu (Nanyang Technological University); Paola Garcia (Johns Hopkins University)

2691: OPTIMIZING QUANTUM FEDERATED LEARNING BASED ON FEDERATED QUANTUM

NATURAL GRADIENT DESCENT
Jun Qi (Georgia Institute of Technology )*; Zhang XiaoLei (Northwestern Polytechnical University); Javier
Tejedor (Institute of Technology, Universidad San Pablo-CEU, CEU Universities)

3265: Quantum deep recurrent reinforcement learning

Samuel Yen-Chi Chen (Wells Fargo)*

3634: Certified Robustness of Quantum Classifiers against Adversarial Examples through

Quantum Noise
Jhih-Cing Huang (National Taiwan University); Yu-Lin Tsai (National Yang Ming Chiao Tung University);
Chao-Han Huck Yang (Georgia Institute of Technology )*; Cheng-Fang Su (National Yang Ming Chiao
Tung University); Chia-Mu Yu (National Yang Ming Chiao Tung University); Pin-Yu Chen (IBM Research);
Sy-Yen Kuo (National Taiwan University)

5392: Quantum transfer learning using the large-scale unsupervised pre-trained model WavLM-
Large for synthetic speech detection
Ruoyu Wang (University of Science and Technology of China)*; Jun Du (University of Science and
Technology of China); Tian Gao (iFlytek Research)

246
 Radar Waveform Design: Recent Advances and New Emerging Applications
1475: Co-Design for MIMO radar and MIMO communication aided by reconfigurable intelligent
surface
Da Li (National University of Defense Technology); Bo Tang (National University of Defense Technology
)*; Lei Xue (National University of Defense Technology)

2263: Dual-Use Signal Design for MIMO RadCom with Inter-pulse Index Modulation
Xue Yao (Southeast University)*; Cui Guolong (UESTC); Xianxiang Yu (UESTC)

3271: Interpretable, Unrolled Deep Radar Beampattern Design

Kareem M Metwaly (The Pennsylvania State University)*; Junho Kweon (The Pennsylvania State
University); Khaled Alhujaili (The Taibah University); Maria S. Greco (University of Pisa); Fulvio Gini
(University of Pisa); Vishal Monga (The Pennsylvania State University)

3358: RIS-Aided Wideband DFRC with Reconfigurable Holographic Surface

Tong Wei (Interdisciplinary Centre for Security, Reliability and Trust (SnT), University of Luxembourg)*;
Linlong Wu (University of Luxembourg); Kumar Vijay Mishra (United States DEVCOM Army Research
Laboratory); Bhavani Shankar Mysore Ramarao (University of Luxembourg)

3548: Joint Waveform and Passive Beamformer Design in Multi-IRS Aided Radar
Zahra Esmaeilbeig (University of Illinois at Chicago)*; Arian Eamaz (University of Illinois - Chicago, IL);
Kumar Vijay Mishra (United States DEVCOM Army Research Laboratory); Mojtaba Soltanalian (University
of Illinois)

4515: RESOURCE ALLOCATION FOR UAV-ENABLED INTEGRATED SENSING AND

COMMUNICATION (ISAC) VIA MULTI-OBJECTIVE OPTIMIZATION
Omid Rezaei (Sharif University of Technology)*; Mohammad Mahdi Naghsh (Isfahan University of
Technology); Seyed Mohammad Karbasi (Sharif University of Technology); Mohammad Mahdi Nayebi
(Sharif University of Technology)

Radar-Assisted Perception (RAP)

291: Exploiting Virtual Array Diversity For Accurate Radar Detection
Junfeng Guan (UIUC)*; Sohrab Madani (UIUC); Waleed Ahmed (UIUC); Samah Ahmed Hussein (EPFL);
Saurabh Gupta (UIUC); Haitham Z Alhassanieh (EPFL)

609: ST-MVDNet++: Improve Vehicle Detection with Lidar-Radar Geometrical Augmentation via
Self-Training
Yu-Jhe Li (Carnegie Mellon University)*; Matthew O'Toole (Carnegie Mellon University); Kris Kitani
(Carnegie Mellon University)

1203: Graph Neural Networks for Object Type Classification Based on Automotive Radar Point
Clouds and Spectra
Loveneet Saini (Room 28); Axel Acosta (Bosch); Gor Hakobyan (Bosch)*

1422: Fast 3D Human Pose Estimation Using RF Signals

Cong Yu (University of Electronic Science and Technology of China)*; Dongheng Zhang (University of
Science and Technology of China); Zhi Wu (University Of Science And Technology Of China); Chunyang
Xie (University of Electronic Science and Technology of China); Zhi Lu (University of Science and
Technology of China); Yang Hu (University of Science and Technology of China); Yan Chen (University of
Science and Technology of China)

247
3467: SPATIAL-DOMAIN OBJECT DETECTION UNDER MIMO-FMCW AUTOMOTIVE RADAR
INTERFERENCE
Sian Jin (Princeton University); Pu Wang (MERL)*; Petros Boufounos (Mitsubishi Electric Research
Laboratories); Ryuhei Takahashi (Mitsubishi Electric Information Technology R&D Center); Sumit Roy
(University of Washington)

4666: Online Learning-based Waveform Selection for Improved Vehicle Recognition in Automotive
Radar
Charles E Thornton (Virginia Tech)*; William Howard (Virginia Tech); Michael R. Buehrer (Virginia Tech,
USA)

Recent Advances in Robust Learning for Modern Computational Imaging

1037: Provably Convergent Plug & Play Linearized ADMM, applied to Deblurring Spatially Varying
Kernels
Charles Laroche (GoPro)*; Andres Almansa (CNRS & Université Paris Cité, MAP5); Eva Coupeté
(GoPro); Matias Tassano (Meta Inc)

2014: Robust Data-Driven Accelerated Mirror Descent

Hong Ye Tan (University of Cambridge)*; Subhadip Mukherjee (University of Cambridge); Junqi Tang
(University of Cambridge); Andreas Hauptmann (University of Oulu); Carola-Bibiane B Schönlieb
(Cambridge University)

3187: Robustness of Deep Equilibrium Architectures to Changes in the Measurement Model

Junhao Hu (Wustl); Shirin Shoushtari (washington university in st. Louis ); Zihao Zou (washington
university in St. Louis); Jiaming Liu (Washington University in St. Louis); Zhixin Sun (Washington
University in St Louis); Ulugbek S. Kamilov (Washington University in St. Louis)*

3345: A Variational Inequality Model for Learning Neural Networks

Patrick Combettes ()*; Jean-Christophe Pesquet (); Audrey Repetti (Heriot Watt University)

3641: Compressive Sensing with Tensorized Autoencoder

Rakib Hyder (University of California, Riverside); M. Salman Asif (University of California, Riverside)*

5624: Image Reconstruction Without Explicit Priors

Angela F Gao (Caltech)*; Oscar Leong (California Institute of Technology); He Sun (Peking University);
Katherine Bouman (Caltech)

Resource-efficient Real-time Neural Speech Separation

444: On the Design and Training Strategies for RNN-based Online Neural Speech Separation
Systems
Kai Li (Tsinghua University)*; Yi Luo (Tencent AI Lab)

2493: Computational Efficient Monaural Speech Enhancement with Universal Sample rate Band-
split RNN
Jianwei Yu (Tencent AI lab)*; Yi Luo (Tencent AI Lab)

3416: Towards Real-Time Single-Channel Speech Separation in Noisy and Reverberant

Environments
Julian Neri (McGill University)*; Sebastian Braun (Microsoft)

248
4244: Predictive SkiM: Contrastive Predictive Coding for Low-Latency Online Speech Separation
Chenda Li (Shanghai Jiao Tong University)*; Yifei Wu (Shanghai Jiao Tong University); Yanmin Qian
(Shanghai Jiao Tong University)

5485: Neural Speech Enhancement with Very Low Algorithmic Latency and Complexity via
Integrated Full- and Sub-Band Modeling
Zhong-Qiu Wang (Carnegie Mellon University)*; Samuele Cornell (Università Politecnica delle Marche);
Shukjae Choi (Hyundai Motor Company); Younglo Lee (42dot); Byeong-Yeol Kim (42dot); Shinji
Watanabe (Carnegie Mellon University)

6492: Latent Iterative Refinement for Modular Source Separation

Dimitrios Bralios (University of Illinois at Urbana-Champaign)*; Efthymios Tzinis (University of Illinois at
Urbana-Champaign); Gordon Wichern (Mitsubishi Electric Research Laboratories (MERL)); Paris
Smaragdis (University of Illinois at Urbana-Champaign); Jonathan LeRoux (Mitsubishi Electric Research
Laboratories (MERL))

Robust Learning and Inference

783: Adversarially Robust Fairness-aware Regression
Yulu Jin (University of California, Davis)*; Lifeng Lai (UC Davis)

1100: Distributionally Robust Multiclass Classification and Applications in Deep Image Classifiers
Ruidi Chen (Amazon); Boran Hao (Boston University); Ioannis C Paschalidis (Boston University)*

3165: Training Neural networks for sequential change-point detection

Junghwan Lee (Georgia Institute of Technology); Yao Xie (Georgia Tech)*; Xiuyuan Cheng (Duke
University)

3334: Robust and Parallelizable Tensor Completion based on Tensor Factorization and Maximum
Correntropy Criterion
Yicong He (University of Central Florida); George Atia (University of Central Florida)*

3373: ROBUST HYPOTHESIS TESTING WITH MOMENT CONSTRAINED UNCERTAINTY SETS

Akshayaa Magesh (University of Illinois at Urbana-Champaign)*; Zhongchang Sun (University at Buffalo,
the State University of New York); Venugopal V. Veeravalli (University of Illinois at Urbana Champaign);
Shaofeng Zou (University at Buffalo, the State University of New York)

3905: LABEL-EFFICIENT AND ROBUST LEARNING FROM MULTIPLE EXPERTS

Bojan Kolosnjaji (Technical University of Munich)*; Apostolis Zarras (Delft University of Technology)

Signal Processing and Learning over Dynamic Graphs

2557: LEARNING DYNAMIC GRAPHS UNDER PARTIAL OBSERVABILITY
Michele Cirillo (University of Salerno)*; Vincenzo Matta (DIEM, University of Salerno); Ali H. Sayed (Ecole
Polytechnique Fédérale de Lausanne)

3321: Dynamic Signed Graph Learning

Abdullah Karaaslanli (Michigan State University)*; Selin Aviyente (Michigan State University)

3388: Gaussian process dynamical modeling for adaptive inference over graphs
Qin Lu (University of Minnesota)*; Konstantinos D. Polyzos (University of Minnesota)

249
3987: Online Vector Autoregressive Models over Expanding Graphs
Bishwadeep Das (TU Delft)*; Elvin Isufi (Tu Delft)

4681: Dynamic Fair Node Representation Learning

Oyku D Kose (University of California Irvine)*; Yanning Shen (University of California, Irvine)

Signal Processing and Machine Learning for Networked Autonomous Agents

1017: Approximation Error Backtracking for Q-function in Scalable Reinforcement Learning with
Tree Dependence Structure
Yuzi Yan (Tsinghua University)*; Yu Dong (Tsinghua University); Kai Ma (Tsinghua University); Yuan Shen
(Tsinghua University)

1656: Implicit vehicle positioning with cooperative lidar sensing

Luca Barbieri (Politecnico di Milano)*; Bernardo Camajori Tedeschini (Politecnico di Milano); Mattia
Brambilla (Politecnico di Milano); Monica Nicoli (Politecnico di Milano University)

2153: Distributed ADMM with Limited Communications via Deep Unfolding

Yoav Noah (Ben-Gurion University of the Negev); Nir Shlezinger (Ben-Gurion University)*

2250: ENSEMBLE GRAPH Q-LEARNING FOR LARGE SCALE NETWORKS

Talha Bozkus (University of Southern California)*; Urbashi Mitra (USC)

3232: DRL Path Planning For UAV-Aided V2X Networks: Comparing Discrete To Continuous Action
Spaces
Leonardo Spampinato (WiLab, CNIT / DEI, University of Bologna)*; Alessia Tarozzi (WiLab, CNIT / DEI,
University of Bologna); Chiara Buratti (WiLab, CNIT / DEI, University of Bologna); Riccardo Marini
(WiLab, CNIT / DEI, University of Bologna)

4082: Autonomous Navigation of a Robotic Swarm in Space Exploration Missions

Siwei Zhang (German Aerospace Center (DLR))*; Tobias Baumgartner (German Aerospace Center
(DLR)); Emanuel Staudinger (German Aerospace Center (DLR) e.V.); Robert Pöhlmann (DLR); Fabio
Broghammer (German Aerospace Center (DLR)); Armin Dammann (German Aerospace Center (DLR)
e.V.)

5010: UWB Localization-of-Things via Soft Information: Network Experimentation in Indoor

Environment
Carlos Antonio Gomez Vega (University of Ferrara)*; Moe Win (Massachusetts Institute of Technology,
USA); Andrea Conti (University of Ferrara)

Signal Processing and Systems for Remote Biometrics

2094: Decorrelating language model embeddings for speech-based prediction of cognitive
impairment
Lingfeng Xu (Arizona State University)*; Kimberly D. Mueller (University of Wisconsin–Madison); Julie
Liss (Arizona State University); Visar Berisha (Arizona State University)

2669: COUGH DETECTION USING MILLIMETER-WAVE FMCW RADAR

Kawon Han (KAIST)*; Songcheol Hong (KAIST)

3921: Wireless sensing for simultaneous human vocal sound and heart sound recognition
yu rong (Arizona State University)*; Kumar Vijay Mishra (United States DEVCOM Army Research
Laboratory); Daniel Bliss (Arizona State University)

250
5221: Flexible Beam Design for Vital Sign Monitoring Using a Phased Array Equipped with Double-
Phase Shifters
Zhaoyi Xu (Rutgers, the State University of New Jersey)*; Donglin Gao (Rutgers University); Shuping Li
(Rutgers University); Chung-Tse Michael Wu (Rutgers University); Athina Petropulu (Rutgers)

6245: Exploiting CCTV Cameras for Hand Hygiene Recognition in ICU

Weijun Huang (Institute of Basic Medicine and Cancer, China); Jia Huang (The Third People's Hospital of
Shenzhen); Guowei Wang (The Third People's Hospital of Shenzhen, China); Hongzhou Lu (Department
of Infectious Diseases, Shanghai Public Health Clinical Center, Fudan University, Shanghai, China); Min
He (College of Electrical and Information Engineering, Hunan University; Institute of Basic Medicine and
Cancer, Chinese Academy of Sciences); Wenjin Wang (Southern University of Science and Technology)*

6452: BENCHMARK OF PHYSIOLOGICAL MODEL BASED AND DEEP LEARNING BASED REMOTE
PHOTOPLETHYSMOGRAPHY IN AUTOMOTIVE
Zhiyu Wang (Shandong University of Science and Technology); Xuezhi Yang (Hefei University of
Technology); Hongzhou Lu (Department of Infectious Diseases, Shanghai Public Health Clinical Center,
Fudan University, Shanghai, China); Caifeng Shan (Shandong Univ. Science & Technology); Wenjin
Wang (Southern University of Science and Technology)*

Signal Processing for RIS-Enabled Smart Wireless Environments

646: Codebook-Based User Tracking in IRS-Assisted mmWave Communication Networks
Moritz Garkisch (Friedrich-Alexander University of Erlangen-Nuremberg )*; Vahid Jamali (Technical
University of Darmstadt); Robert Schober (Friedrich-Alexander University Erlangen-Nurnberg)

1144: Beamforming Optimization in RIS-Aided MIMO Systems Under Multiple-Reflection Effects

Dilki Wijekoon (University of Manitoba); Amine Mezghani (University of Manitoba); Ekram Hossain
(University of Manitoba)*

1846: Hybrid RIS-Assisted Interference Mitigation for Spectrum Sharing

Fangzhou Wang (University of California Irvine)*; Lee Swindlehurst (University of California at Irvine)

2477: An Efficient Beam-Sharing Algorithm for RIS-aided Simultaneous Wireless Information and
Power Transfer Applications
Tran Minh Nguyen (Sungkyunkwan University)*; Muhammad Miftahul Amri (Sungkyunkwan University);
Je Hyeon Park (Sungkyunkwan University); Dong In Kim (Sungkyunkwan University); Kae Won Choi
(Sungkyunkwan University)

3625: Compressed-Sensing-Based 3D Localization with Distributed Passive Reconfigurable

Intelligent Surfaces
Jiguang He (Technology Innovation Institute, 9639 Masdar City, Abu Dhabi)*; Aymen Fakhreddine
(Technology Innovation Institute, 9639 Masdar City, Abu Dhabi); Henk Wymeersch (Department of
Electrical Engineering, Chalmers University of Technology, Gothenburg, Sweden); George
Alexandropoulos (National and Kapodistrian University of Athens)

4022: ENERGY EFFICIENCY MAXIMIZATION IN RIS-AIDED NETWORKS WITH GLOBAL

REFLECTION CONSTRAINTS
Robert Fotock (University of Cassino and Southern Lazio); Alessio Zappone (University of Cassino and
Southern Lazio)*; Marco Di Renzo (Université Paris Saclay)

251
 Signal Processing for Smart City Applications and the Internet of Things
1180: MSN-net: Multi-Scale Normality Network for Video Anomaly Detection
Yang Liu (Fudan University)*; Di Li (Shanghai East-bund Research Institute on NSAI); Wei Zhu (Fudan
University); Dingkang Yang (Fudan University); Jing Liu (Fudan University); Liang Song (Fudan
University)

2262: EEG Emotion Recognition via Ensemble Learning Representations

Bilal Taha (University of Toronto)*; Dae Yon Hwang (University of Toronto); Dimitrios Hatzinakos
(University of Toronto)

3043: Hybrid Indoor Localization via Reinforcement Learning-based Information Fusion

Mohammad Salimibeni (Concordia University); Arash Mohammadi (Concordia University)*

3111: Adapting exploratory behaviour in Active Inference for Autonomous Driving

Sheida Nozari (University of Genoa)*; Ali Krayani (University of Genoa); Pablo Marín (University Carlos III
de Madrid); LUCIO MARCENARO (Universita degli Studi di Genoa, Genoa); David Martín (University
Carlos III de Madrid); Carlo Regazzoni (Universita degli Studi di Genoa, Genoa)

5446: Federated Semi-Supervised Learning for Object Detection in Autonomous Driving

Fangyuan Chi (The University of British Columbia)*; Yixiao Wang (University of British Columbia); Panos
Nasiopoulos (University of British Columbia); Victor C. M. Leung (Shenzhen University); Mahsa Pourazad
(TELUS Communications Inc.)

6114: SINGLE-SAMPLE DIRECTION-OF-ARRIVAL ESTIMATION FOR FAST AND ROBUST 3D

LOCALIZATION WITH REAL MEASUREMENTS FROM A MASSIVE MIMO SYSTEM
Stephan Mazokha (Florida Atlantic University); Sanaz Naderi (Florida Atlantic University); Georgios
Orfanidis (Florida Atlantic University); George Sklivanitis (Florida Atlantic University)*; Dimitris Pados
(Florida Atlantic University); Jason Hallstrom (Florida Atlantic University)

Symbol-Level Precoding: Recent Advance and New Applications in 6G and

Beyond
924: OVERLAY COGNITIVE RADIO USING SYMBOL LEVEL PRECODING WITH QUANTIZED CSI
Lu Liu (University Of California, Irvine)*; Lee Swindlehurst (University of California at Irvine)

2299: Efficient Quantized Constant Envelope Precoding for Multiuser Downlink Massive MIMO
Systems
Zheyu Wu (Academy of Mathematics and Systems Science); Ya-Feng Liu (Chinese Academy of
Sciences)*; Bo Jiang (Nanjing Normal University); Yu-Hong Dai (Academy of Mathematics and Systems
Science)

3177: Joint Symbol-Level Precoding and Sub-Block-Level RIS Design for Dual-Function Radar-
Communications
Linlong Wu (University of Luxembourg)*; Bowen Wang (University of Electronic Science and Technology
of China); Ziyang Cheng (University of Electronic Science and Technology of China); Bhavani Shankar
Mysore Ramarao (University of Luxembourg); Bjorn Ottersten (SnT)

3644: SYMBOL LEVEL PRECODING IN THE RF DOMAIN FOR LOW HARDWARE COMPLEXITY RIS-
ASSISTED MU-MISO SYSTEMS
Christos Tsinos (University of Athens); Theodoros Tsiftsis (Jinan University)*; Robert Schober (Friedrich-
Alexander University Erlangen-Nurnberg)

252
6212: SYMBOL-LEVEL PRECODING IS RELATED TO PARAMETER ESTIMATION FROM
QUANTIZED DATA
Mingjie Shao (The Chinese University of Hong Kong, Shandong University )*; Wing-Kin Ma (The Chinese
University of Hong Kong); Yatao Liu (The Chinese University of Hong Kong)

Synergy between human and machine approaches to sound/scene recognition

and processing
2581: Perceptual analysis of speaker embeddings for voice discrimination between machine and
human listening
Iordanis Thoidis (Aristotle University of Thessaloniki)*; Clément Gaultier (University of Cambridge); Tobias
Goehring (University of Cambridge)

4176: Semantically-informed Deep Neural Networks for sound recognition

Michele Esposito (Maastricht University)*; Giancarlo Valente (Maastricht University); Yenisel Plasencia-
Calaña (Maastricht University); Michel Dumontier (Maastricht University); Bruno L. Giordano (CNRS); Elia
Formisano (Maastricht University)

4472: An Approach to Ontological Learning from Weak Labels

Ankit Parag Shah (Carnegie Mellon University)*; Larry Tang (Carnegie Mellon University); Po Hao Chou
(Carnegie Mellon University); Yi Yu Zheng (Carnegie Mellon University); Ziqiang Ge (Carnegie Mellon
University); Bhiksha Raj (Carnegie Mellon University)

4813: CLASSIFYING NON-INDIVIDUAL HEAD-RELATED TRANSFER FUNCTIONS WITH A

COMPUTATIONAL AUDITORY MODEL: CALIBRATION AND METRICS
Rapolas Daugintis (Imperial College London)*; Roberto Barumerli (Austrian Academy of Sciences);
Lorenzo Picinali (Imperial College London); Michele Geronazzo (Imperial College London)

4960: Perceptual-Neural-Physical Sound Matching

Han Han (Ecole Centrale Nantes)*; Vincent Lostanlen (Cornell Lab of Ornithology); Mathieu Lagrange
(LS2N)

4988: USING MACHINE LEARNING TO UNDERSTAND THE RELATIONSHIPS BETWEEN

AUDIOMETRIC DATA, SPEECH PERCEPTION, TEMPORAL PROCESSING, AND COGNITION
Rana Khalil (University of Maryland - College Park); Alexandra Papanicolaou (University of Maryland -
College Park); Renee Chou (University of Maryland - College Park); Bobby Gibbs (University of Maryland
- College Park); Samira B Anderson (University of Maryland); Sandra Gordon-Salant (University of
Maryland - College Park); Michael Cummings (University of Maryland - College Park); Matthew J. Goupell
(University of Maryland - College Park)*

Topological and Simplicial Data Processing

2602: Signal Processing on Product Spaces
T. Mitchell Roddenberry (Rice University)*; Vincent P Grande (RWTH Aachen University); Florian
Frantzen (RWTH Aachen University); Michael Schaub (RWTH Aachen University); Santiago Segarra
(Rice University)

2607: Online Edge Flow Prediction over Expanding Simplicial Complexes

Maosheng Yang (Delft University of Technology)*; Bishwadeep Das (TU Delft); Elvin Isufi (Tu Delft)

3653: TOPOLOGICAL SIGNAL PROCESSING OVER WEIGHTED SIMPLICIAL COMPLEXES

Claudio Battiloro (Sapienza University of Rome); Stefania Sardellitti (Sapienza University of Rome)*;
Sergio Barbarossa (Sapienza University of Rome); Paolo Di Lorenzo (Sapienza University of Rome)

253
5420: Topo-MLP : A Simplicial Network Without Message Passing
Karthikeyan Natesan Ramamurthy (IBM Research)*; Aldo Guzmán-Sáenz (IBM); Mustafa Hajij (USFCA )

5898: Higher-order Spatio-temporal Neural Networks for COVID-19 Forecasting

Yuzhou Chen (Temple University)*; Sotirios P Batsakis (University of Huddersfield); H. Vincent Poor
(Princeton University)

Unsupervised Deep Learning of Image Priors for Inverse Problems

357: Stay in the Middle: A Semi-Supervised Model for CT Metal Artifact Reduction
Tao Wang (Sichuan University); Hui Yu (Sichuan University); Zexin Lu (Sichuan University); Zhongzhou
Zhang (Sichuan university); Jiliu Zhou (Chengdu University of Information Technology); Yi Zhang
(Sichuan University)*

873: Unsupervised Deep Virtual Staining for Microscopic Cell Images via Knowledge Distillation
Ziwang Xu (School of Electrical and Electronic Engineering, Nanyang Technological University); Lanqing
Guo (Nanyang Technological University); Shuyan Zhang (Agency for Science, Technology and
Research); Alex Kot (Nanyang Technological University); Bihan Wen (Nanyang Technological University)*

4737: DEEP PROXIMAL GRADIENT METHOD FOR LEARNED CONVEX REGULARIZERS

Aaron Berk (McGill University); Yanting Ma (Mitsubishi Electric Research Laboratories, USA); Petros
Boufounos (Mitsubishi Electric Research Laboratories); Pu Wang (MERL); Hassan Mansour (Mitsubishi
Electric Research Laboratories (MERL))*

4993: ROBUST SELF-GUIDED DEEP IMAGE PRIOR

Evan Bell (Michigan State University); Shijun Liang (michigan state university)*; Qing Qu (University of
Michigan); Saiprasad Ravishankar (Michigan State University)

5248: CryoSWD: Sliced Wasserstein Distance Minimization for 3D Reconstruction in Cryo-Electron

Microscopy
Mona Zehni (University of Illinois at Urbana-Champaign)*; Zhizhen Zhao (University of Illinois at Urbana-
Champaign)

Variational Inference and Approximate Bayesian Techniques

250: OUTLIER-INSENSITIVE KALMAN FILTERING USING NUV PRIORS
Shunit Truzman (University of Haifa)*; Guy Revach (ETH Zürich); Nir Shlezinger (Ben-Gurion University);
Itzik Klein (University of Haifa)

838: Long-Memory Message-Passing for Spatially Coupled Systems

Keigo Takeuchi (Toyohashi University of Technology)*

1444: A unitary transform based generalized approximate message passing

Jiang Zhu (Zhejiang University); Xiangming Meng (The University of Tokyo)*; Xupeng Lei (Zhejiang
University); Qinghua Guo (UNIVERSITY OF WOLLONGONG)

1782: QUANTUM VARIATIONAL BAYES ON MANIFOLDS

Anna Lopatnikova (U of Sydney); Minh-Ngoc Tran (U of Sydney)*

254
2545: Overcoming Posterior Collapse in Variational Autoencoders via EM-type Training
Ying Li (The University of Hong Kong); Lei Cheng (Zhejiang University)*; Feng Yin (The Chinese
University of Hong Kong, Shenzhen); Michael Zhang (University of Hong Kong); Sergios Theodoridis
(National and Kapodistrian University of Athens)

3413: Alternating Constrained Minimization based Approximate Message Passing

Christo Kurisummoottil Thomas (Virginia Tech)*; Dirk Slock (EURECOM, France)

6098: Variational Bayesian Channel Estimation in Wideband Multi-Scale Multi-Lag Channels

Niladri Halder (Indian Institute of Science); Arunkumar K. P. (Indian Institute of Science); Chandra Murthy
(Indian Institute of Science)*

Vision Transformers for Medical Image Processing

3480: Classification of the Cervical Vertebrae Maturation (CVM) stages Using the Tripod Network
Salih Furkan Atici (University of Illinois Chicago); Hongyi Pan (University of Illinois Chicago )*;
Mohammed Elnagar (University of Illinois Chicago); Veerasathpurush Allareddy (University of Illinois
Chicago); Omar Suhaym (University of Illinois Chicago); Rashid Ansari (n/a); Ahmet E Cetin (University of
Illinois at Chicago)

255