Cross-media retrieval: state-of-the-art and open issues

Abstract

Cross-media retrieval is able to provide retrieval results with similar semantics but different media to the query. Since cross-media retrieval complements currently popular text/content-based retrieval which provides retrieval results with the same media to the query, it becomes an emerging research topic. In this paper, we give an overview of recent advances and research challenges in cross-media retrieval. Such retrieval paradigm has been driven by the wide availability of large multimedia resources on the web, innovative approaches to semantically understanding various multimedia objects, and novel machine learning techniques for the interactive mappings among heterogeneous feature spaces. Emphasising on these respects, we review the state-of-the-art approaches and achieved progresses in cross-media retrieval. According to the current technologies used in cross-media retrieval and the demand from real-world applications, open research issues and future research opportunities are identified.