Present Development and Prospect of Cross-Media Retrieval

Cross-media retrieval is a new type of multimedia retrieval in which the media types of query examples and the returned results can be different. It complements the currently popular retrieval method which can be referred as single-media retrieval. And it is becoming an emerging research topic. Recently, the multimedia resources on the Web have become richer, and the related machine learning methods have been constantly improved. All these factors contribute to the development of cross-media retrieval. In this paper, we review the advanced methods and achievements in the area of cross-media retrieval and explore the future research direction of cross-media retrieval according to the current technologies and applications.