Efficient feature extraction, encoding and classification for action recognition

Vadim Kantorov 1, * Ivan Laptev 1
* Auteur correspondant
1 WILLOW - Models of visual object recognition and scene understanding
CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure
Abstract : Local video features provide state-of-the-art performance for action recognition. While the accuracy of action recognition has been continuously improved over the recent years, the low speed of feature extraction and subsequent recognition prevents current methods from scaling up to real-size problems. We address this issue and first develop highly efficient video features using motion information in video compression. We next explore feature encoding by Fisher vectors and demonstrate accurate action recognition using fast linear classifiers. Our method improves the speed of video feature extraction, feature encoding and action classification by two orders of magnitude at the cost of minor reduction in recognition accuracy. We validate our approach and compare it to the state of the art on four recent action recognition datasets.
Type de document :
Communication dans un congrès
CVPR 2014 - Computer Vision and Pattern Recognition, Jun 2014, Columbus, United States. 2014
Liste complète des métadonnées

Littérature citée [40 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/hal-01058734
Contributeur : Vadim Kantorov <>
Soumis le : mercredi 27 août 2014 - 20:32:17
Dernière modification le : vendredi 25 mai 2018 - 12:02:06
Document(s) archivé(s) le : vendredi 28 novembre 2014 - 10:55:41

Fichier

cvpr2014_kantorov_paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01058734, version 1

Collections

Citation

Vadim Kantorov, Ivan Laptev. Efficient feature extraction, encoding and classification for action recognition. CVPR 2014 - Computer Vision and Pattern Recognition, Jun 2014, Columbus, United States. 2014. 〈hal-01058734〉

Partager

Métriques

Consultations de la notice

327

Téléchargements de fichiers

447