Prof. Zhuang Yueting in CCST was the Principle Investigator of the project which won the first prize of Natural Science Award of Zhejiang Province in 2015. Nowadays, there are lots of heterogeneous and homogeneous media data from multiple sources, such as news media websites, social networking websites, and photo/video sharing websites. This project studies the fundamental problems in cross media research. A series of new theories and techniques have been studied and proposed, which together reveal the internal structural information and external semantic correlation of cross-media data. The research provides a new computational model for bridging the heterogeneity-gap and the semantic-gap, and initiates cross-media retrieval (the query examples and the returned results can be of different modalities, e.g., to query images by an example of audio.).