Intelligent multimedia indexing and retrieval through multi-source information extraction and merging

Jan Kuper, Horacio Saggion, Hamish Cunningham, Thierry Declerck, Franciska M. G. de Jong, Dennis Reidsma, Yorick Alexander Wilks, Peter Wittenburg · University of Twente Research Information · 2003

This paper reports work on automated meta-data creation for multimedia content. The approach results in the generation of a conceptual index of the content which may then be searched via semantic categories instead of keywords. The novelty of the work is to exploit multiple sources of information relating to video content (in this case the rich range of sources covering important sports events). News, commentaries and web reports covering international football games in multiple languages and multiple modalities is analysed and the resultant data merged. This merging process leads to increased accuracy relative to individual sources.

Read the paper · More papers on PaperTik