Michael G. Christel
ABSTRACT
The Carnegie Mellon University Informedia group has enjoyed consistent success with TRECVID interactive search using traditional storyboard interfaces for shot-based retrieval. For TRECVID 2006 the output of automatic search was included for the first time with storyboards, as an option for an interactive user. This access mechanism, query-by-best-of-topic, complements other access strategies, namely query-by-text (dominated by closed captioned text), query-by-image (primarily color-based syntactic lookup), and query-by-concept (using concept classifiers trained through machine learning techniques). The interface is tuned to support efficient performance required for TRECVID interactive search tasks where a maximum of 15 minutes can be spent per task. This 4-strategy Informedia interface scored significantly better than all other TRECVID 2006 interactive search systems. Interface attributes will be demonstrated in shot-based retrieval from news corpora.
- Christel, M., and Yan, R. Merging Storyboard Strategies and Automatic Retrieval for Improving Interactive Video Search. In Proc. Image and Video Retrieval (CIVR) (July 2007). Google Scholar
Digital Library
- Snoek, C., Worring, M., Koelma, D., and Smeulders, A. A Learned Lexicon-Driven Paradigm for Interactive Video Retrieval. IEEE Trans. Multimedia 9(2), Feb. 2007, 280--292. Google ScholarDigital Library
Index Terms
Carnegie Mellon University traditional informedia digital video retrieval system
Recommendations
Merging storyboard strategies and automatic retrieval for improving interactive video search
CIVR '07: Proceedings of the 6th ACM international conference on Image and video retrievalThe Carnegie Mellon University Informedia group has enjoyed consistent success with TRECVID interactive search using traditional storyboard interfaces for shot-based retrieval. For TRECVID 2006 the output of automatic search was included for the first ...
Multimodal Video Retrieval with the 2017 IMOTION System
ICMR '17: Proceedings of the 2017 ACM on International Conference on Multimedia RetrievalThe IMOTION system is a multimodal content-based video search and browsing application offering a rich set of query modes on the basis of a broad range of different features. It is able to scale with the size of the collection due to its underlying ...
Addressing the challenge of visual information access from digital image and video libraries
JCDL '05: Proceedings of the 5th ACM/IEEE-CS joint conference on Digital librariesWhile it would seem that digital video libraries should benefit from access mechanisms directed to their visual contents, years of TREC Video Retrieval Evaluation (TRECVID) research have shown that text search against transcript narrative text provides ...
Comments