Evaluation of local descriptors for action recognition in videos

Abstract : Recently, local descriptors have drawn a lot of attention as a representation method for action recognition. They are able to capture appearance and motion. They are robust to viewpoint and scale changes. They are easy to implement and quick to calculate. Moreover, they have shown to obtain good performance for action classification in videos. Over the last years, many different local spatio-temporal descriptors have been proposed. They are usually tested on different datasets and using different experimental methods. Moreover, experiments are done making assumptions that do not allow to fully evaluate descriptors. In this paper, we present a full evaluation of local spatio-temporal descriptors for action recognition in videos. Four widely used in state-of-the-art approaches descriptors and four video datasets were chosen. HOG, HOF, HOG-HOF and HOG3D were tested under a framework based on the bag-of-words model and Support Vector Machines.
Document type :
Conference papers
International Conference on Computer Vision Systems, Sep 2011, Sophia Antipolis, France. 2011
Liste complète des métadonnées


https://hal.inria.fr/inria-00619091
Contributor : Piotr Bilinski <>
Submitted on : Tuesday, September 20, 2011 - 7:00:17 AM
Last modification on : Tuesday, September 20, 2011 - 7:00:17 AM
Document(s) archivé(s) le : Wednesday, December 21, 2011 - 2:20:41 AM

File

ICVS2011.pdf
Files produced by the author(s)

Identifiers

  • HAL Id : inria-00619091, version 1

Collections

Citation

Piotr Bilinski, François Bremond. Evaluation of local descriptors for action recognition in videos. International Conference on Computer Vision Systems, Sep 2011, Sophia Antipolis, France. 2011. <inria-00619091>

Share

Metrics

Record views

238

Document downloads

223