Video Story Segmentation with Multi-Modal Features: Experiments on TRECvid 2003 - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2004

Video Story Segmentation with Multi-Modal Features: Experiments on TRECvid 2003

Résumé

This paper describes the first steps of CLIPS/IMAG on the TREC video story segmentation task. We mostly describe the multi-modal features used and their respective performance for the story segmentation task. These features are based on the audio, video and text modalities. The preliminary system, which has the advantage to be relatively free with respect to the use of training data, is also presented in this paper. First experiments on the TRECVID 2003 evaluation set lead to a recall rate of 0.613 and a precision rate of 0.467.
Fichier non déposé

Dates et versions

hal-00953929 , version 1 (28-02-2014)

Identifiants

  • HAL Id : hal-00953929 , version 1

Citer

Laurent Besacier, Georges Quénot, Stéphane Ayache, Daniel Moraru. Video Story Segmentation with Multi-Modal Features: Experiments on TRECvid 2003. 6th ACM SIGMM International Workshop on Multimedia Information Retrieval (MIR'04), 2004, New York, NY, United States. ⟨hal-00953929⟩
216 Consultations
0 Téléchargements

Partager

Gmail Facebook X LinkedIn More