Project director: Prof. Zhuang Yueting
There is rapid growth of the number of texts, images, and videos on the Web. These cross-media data is usually of high dimensionality, high order and large scale. Moreover, different types of media data are interrelated everywhere in a complicated way. How to analyze and mine the interrelationship between Web pages, different types of media data, and user logs is a challenging problem for the next generation search engine. Supported by NSFC, we studied the large scale cross-media understanding and retrieval and published our results on highly qualified international journals (IEEE Transactions on Image Processing 、IEEE Transactions on Multimedia、IEEE Transactions on Circuits and Systems for Video Technology and Pattern Recognition) and top conferences (AAAI、CVPR、ICCV、ACM MM).