Abstract : Automatic semantic classification of video databases is very useful for users searching and browsing but it is a very challenging re- search problem as well. Combination of visual and text modalities is one of the key issues to bridge the semantic gap between signal and semantic. In this paper, we propose to enhance the classification of high- level concepts using intermediate topic concepts and study various fu- sion strategies to combine topic concepts with visual features in order to outperform unimodal classifiers. We have conducted several experiments on the TRECVID'05 collection and show here that several intermediate topic classifiers can bridge parts of the semantic gap and help to detect high-level concepts.
Type de document :
Communication dans un congrès
International Conference on Image and Video Retrieval CIVR'06, 2006, Tempe, United States. 2006
https://hal.inria.fr/hal-00953902
Contributeur : Marie-Christine Fauvet
<>
Soumis le : lundi 3 mars 2014 - 15:05:24
Dernière modification le : mardi 24 avril 2018 - 13:29:33
Document(s) archivé(s) le : samedi 31 mai 2014 - 10:48:08
Stéphane Ayache, Georges Quénot, Jérôme Gensel, Shin'Ichi Satoh. Using Topic Concepts for Semantic Video Shots Classification. International Conference on Image and Video Retrieval CIVR'06, 2006, Tempe, United States. 2006. 〈hal-00953902〉
