Action Recognition with Improved Trajectories

Heng Wang 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Recently dense trajectories were shown to be an efficient video representation for action recognition and achieved state-of-the-art results on a variety of datasets. This paper improves their performance by taking into account camera motion to correct them. To estimate camera motion, we match feature points between frames using SURF descriptors and dense optical flow, which are shown to be complementary. These matches are, then, used to robustly estimate a homography with RANSAC. Human motion is in general different from camera motion and generates inconsistent matches. To improve the estimation, a human detector is employed to remove these matches. Given the estimated camera motion, we remove trajectories consistent with it. We also use this estimation to cancel out camera motion from the optical flow. This significantly improves motion-based descriptors, such as HOF and MBH. Experimental results on four challenging action datasets (i.e., Hollywood2, HMDB51, Olympic Sports and UCF50) significantly outperform the current state of the art.
Type de document :
Communication dans un congrès
ICCV 2013 - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.3551-3558, 2013, <10.1109/ICCV.2013.441>
Liste complète des métadonnées



https://hal.inria.fr/hal-00873267
Contributeur : Thoth Team <>
Soumis le : mercredi 16 octobre 2013 - 11:40:57
Dernière modification le : mardi 11 août 2015 - 01:05:15

Fichiers

wang_iccv13.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Heng Wang, Cordelia Schmid. Action Recognition with Improved Trajectories. ICCV 2013 - IEEE International Conference on Computer Vision, Dec 2013, Sydney, Australia. IEEE, pp.3551-3558, 2013, <10.1109/ICCV.2013.441>. <hal-00873267v2>

Partager

Métriques

Consultations de
la notice

9990

Téléchargements du document

17886