Skip to Main content Skip to Navigation
Conference papers

Efficient feature extraction, encoding and classification for action recognition

Vadim Kantorov 1, * Ivan Laptev 1 
* Corresponding author
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique - ENS Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
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.
Document type :
Conference papers
Complete list of metadata

Cited literature [40 references]  Display  Hide  Download
Contributor : Vadim Kantorov Connect in order to contact the contributor
Submitted on : Wednesday, August 27, 2014 - 8:32:17 PM
Last modification on : Thursday, March 17, 2022 - 10:08:39 AM
Long-term archiving on: : Friday, November 28, 2014 - 10:55:41 AM


Files produced by the author(s)


  • HAL Id : hal-01058734, version 1



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. ⟨hal-01058734⟩



Record views


Files downloads