Using Topic Concepts for Semantic Video Shots Classification

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.
Document type :
Conference papers
Liste complète des métadonnées

Cited literature [16 references]  Display  Hide  Download

https://hal.inria.fr/hal-00953902
Contributor : Marie-Christine Fauvet <>
Submitted on : Monday, March 3, 2014 - 3:05:24 PM
Last modification on : Tuesday, April 2, 2019 - 1:47:35 AM
Document(s) archivé(s) le : Saturday, May 31, 2014 - 10:48:08 AM

File

civr06a.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : hal-00953902, version 1

Collections

Citation

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. ⟨hal-00953902⟩

Share

Metrics

Record views

362

Files downloads

96