A Learned Lexicon-Driven Paradigm for Interactive Video Retrieval
- 22 January 2007
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Multimedia
- Vol. 9 (2), 280-292
- https://doi.org/10.1109/tmm.2006.886275
Abstract
Effective video retrieval is the result of interplay between interactive query selection, advanced visualization of results, and a goal-oriented human user. Traditional interactive video retrieval approaches emphasize paradigms, such as query-by-keyword and query-by-example, to aid the user in the search for relevant footage. However, recent results in automatic indexing indicate that query-by-concept is becoming a viable resource for interactive retrieval also. We propose in this paper a new video retrieval paradigm. The core of the paradigm is formed by first detecting a large lexicon of semantic concepts. From there, we combine query-by-concept, query-by-example, query-by-keyword, and user interaction into the MediaMill semantic video search engine. To measure the impact of increasing lexicon size on interactive video retrieval performance, we performed two experiments against the 2004 and 2005 NIST TRECVID benchmarks, using lexicons containing 32 and 101 concepts, respectively. The results suggest that from all factors that play a role in interactive retrieval, a large lexicon of semantic concepts matters most. Indeed, by exploiting large lexicons, many video search questions are solvable without using query-by-keyword and query-by-example. In addition, we show that the lexicon-driven search engine outperforms all state-of-the-art video retrieval systems in both TRECVID 2004 and 2005Keywords
This publication has 35 references indexed in Scilit:
- Machine Translation in the Year 2004Published by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Learning rich semantics from news video archives by style analysisACM Transactions on Multimedia Computing, Communications, and Applications, 2006
- Interactive Video Search Using Multilevel IndexingLecture Notes in Computer Science, 2005
- Exploiting multiple modalities for interactive video retrievalPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- ViBE: A Compressed Video Database Structured for Active Browsing and SearchIEEE Transactions on Multimedia, 2004
- ClassView : Hierarchical Video Shot Classification, Indexing, and AccessingIEEE Transactions on Multimedia, 2004
- Towards a Large Scale Concept Ontology for Broadcast VideoLecture Notes in Computer Science, 2004
- The LIMSI Broadcast News transcription systemSpeech Communication, 2002
- Lessons learned from building a terabyte digital video libraryComputer, 1999
- Indexing by latent semantic analysisJournal of the American Society for Information Science, 1990