LIG at TRECVID 2009: Hierarchical Fusion for High Level Feature Extraction

Bahjat Safadi 1 Georges Quénot 2
2 MRIM - Modélisation et Recherche d’Information Multimédia [Grenoble]
LIG - Laboratoire d'Informatique de Grenoble, Inria - Institut National de Recherche en Informatique et en Automatique
Abstract : We investigated in this work a hierarchical fusion strategy for fusing the outputs of hundreds of descriptors~×~classifier combinations. Over one hundred descriptors gathered in the context of the IRIM consortium were used for HLF detection with up to four different classifiers. The produced classification scores are then fused in order to produce a unique classification score for each video shot and HLF. In order to cope with the redundancy of the information obtained from similar descriptors and from different classifiers using them, we propose a hierarchical fusion approach so that 1) each different source type gets an appropriate global weight, 2) all the descriptors~×~classifier combinations from similar source type are first combined in the optimal way before being merged at the next level. The best LIG run has a Mean Inferred Average Precision of 0.1276, which is significantly above TRECVID 2009 HLF detection task median performance. We found that fusion of the classification scores from different classifier types improves the performance and that even with a quite low individual performance, audio descriptors can help.
Type de document :
Communication dans un congrès
TREC Video Retrieval Evaluation workshop, 2009, Gaithersburg, MD, United States. 2009
Liste complète des métadonnées

https://hal.inria.fr/hal-00953859
Contributeur : Marie-Christine Fauvet <>
Soumis le : vendredi 28 février 2014 - 16:02:34
Dernière modification le : jeudi 11 janvier 2018 - 06:22:06

Identifiants

  • HAL Id : hal-00953859, version 1

Collections

Citation

Bahjat Safadi, Georges Quénot. LIG at TRECVID 2009: Hierarchical Fusion for High Level Feature Extraction. TREC Video Retrieval Evaluation workshop, 2009, Gaithersburg, MD, United States. 2009. 〈hal-00953859〉

Partager

Métriques

Consultations de la notice

87