A framework for aligning and indexing movies with their script

Rémi Ronfard 1 Tien Tran-Thuong 2
1 MOVI - Modeling, localization, recognition and interpretation in computer vision
GRAVIR - IMAG - Graphisme, Vision et Robotique, Inria Grenoble - Rhône-Alpes, CNRS - Centre National de la Recherche Scientifique : FR71
2 WAM - Web, adaptation and multimedia
Inria Grenoble - Rhône-Alpes
Abstract : A continuity script describes very carefully the content of a movie shot by shot. This paper introduces a framework for extracting structural units such as shots, scenes, actions and dialogs from the script, and aligning them to the movie based on the longest matching subsequence between them. We present experimental results and applications of the framework with a full-length movie and discuss its applicability to large-scale film repositories.
Type de document :
Communication dans un congrès
Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Jul 2003, Baltimore, MD, United States. 2003
Liste complète des métadonnées



https://hal.inria.fr/inria-00423417
Contributeur : Vincent Quint <>
Soumis le : vendredi 9 octobre 2009 - 17:49:34
Dernière modification le : mercredi 21 mars 2012 - 10:34:35
Document(s) archivé(s) le : mercredi 16 juin 2010 - 00:35:45

Fichiers

icmeTien.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00423417, version 1

Collections

IMAG | INRIA | UGA

Citation

Rémi Ronfard, Tien Tran-Thuong. A framework for aligning and indexing movies with their script. Proceedings of IEEE International Conference on Multimedia and Expo (ICME), Jul 2003, Baltimore, MD, United States. 2003. <inria-00423417>

Partager

Métriques

Consultations de
la notice

327

Téléchargements du document

336