The LIGVID System for Video Retrieval and Concept Annotation

Stéphane Ayache 1 Georges Quénot 2 Andy Tseng
1 LIF - Laboratoire d'informatique Fondamentale de Marseille - UMR 6166
2 MRIM - Modélisation et Recherche d’Information Multimédia [Grenoble]
Inria - Institut National de Recherche en Informatique et en Automatique, LIG - Laboratoire d'Informatique de Grenoble
Abstract : The LIGVID system is designed for online interactive video shots retrieval and annotation. It uses a user-controlled combination of multiple criteria: keywords, phonetic string, similarity to example images, semantic categories, and relevance feedback strategies: visual and temporal similarity to already identified positive images. In addition to Relevance Feedback processes, the system runs in background an active learning algorithm to better model the user's information need. Previous participation to video retrieval challenges has permit to show the effectiveness of our system.
keyword : multi-criteria search Video retrieval multi-criteria search.
Document type :
Conference papers
Liste complète des métadonnées
https://hal.inria.fr/hal-00953840
Contributor : Marie-Christine Fauvet <>
Submitted on : Friday, February 28, 2014 - 4:02:13 PM
Last modification on : Tuesday, April 2, 2019 - 2:34:26 AM

Identifiers

  • HAL Id : hal-00953840, version 1

Collections

UNIV-AMU | LIG_TDCGE_MRIM | LIG_TDCGE | LIG | UGA | LIF | INRIA | LIS-LAB

Citation

Stéphane Ayache, Georges Quénot, Andy Tseng. The LIGVID System for Video Retrieval and Concept Annotation. 11th ACM SIGMM International Conference on Multimedia Information Retrieval (demo session), 2010, Philadelphia, Pennsylvania, United States. ⟨hal-00953840⟩

Export

BibTeX TEI DC DCterms EndNote

Share

Metrics

Record views

287

Contact


archive-ouverte@inria.fr