%***************************************************************************
%                              README
%   This source code is (c) Copyright 2004 by Jia-Yu (Tim) Pan 
%   (Computer Science Department, Carnegie Mellon University).
%   It may not be redistributed without the express consent of the
%   author.
%
%   Descriptions on the method MMG can be found in the following
%   papers:
%
%   Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, and Pinar Duygulu.
%   Automatic Multimedia Cross-modal Correlation Discovery. 
%   In Proceedings of the 10th ACM SIGKDD Conference, 2004.
%   Seattle, WA, August 22-25, 2004
%
%   Jia-Yu Pan, Hyung-Jeong Yang, Christos Faloutsos, and Pinar Duygulu. 
%   GCap: Graph-based Automatic Image Captioning. 
%   In Proceedings of the 4th International Workshop on Multimedia
%   Data and Document Engineering (MDDE 04), in conjunction with
%   Computer Vision Pattern Recognition Conference (CVPR 04), 2004.
%   Washington DC, July 2nd 2004
%
%***************************************************************************

In MATLAB, run 'MMG_demo', for a demo.

The result will be stored in a file in directory 'result/'.

In demo_data/:
   demo_data/graph/:
      001_trnK3_graph.mat:
         contains the adjacency matrix 'A';
         'dims' specifies the numbers of each node-type: region-node, image-node, and term-nodes.

   demo_data/NN/:
      001_NNmax20_labels.txt:
         each row is the nearest 20 training region-node IDs for a testing region-node.

   demo_data/test_data/:
      Test set 001/ from the corel image set.
      To download the data, please go to
http://vision.cs.arizona.edu/kobus/research/data/eccv_2002/index.html

