Action Recognition by Dense Trajectories

Heng Wang 1, 2, * Alexander Kläser 1 Cordelia Schmid 1 Liu Cheng-Lin 2
* Auteur correspondant
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : Feature trajectories have shown to be efficient for representing videos. Typically, they are extracted using the KLT tracker or matching SIFT descriptors between frames. However, the quality as well as quantity of these trajectories is often not sufficient. Inspired by the recent success of dense sampling in image classification, we propose an approach to describe videos by dense trajectories. We sample dense points from each frame and track them based on displacement information from a dense optical flow field. Given a state-of-the-art optical flow algorithm, our trajectories are robust to fast irregular motions as well as shot boundaries. Additionally, dense trajectories cover the motion information in videos well. We, also, investigate how to design descriptors to encode the trajectory information. We introduce a novel descriptor based on motion boundary histograms, which is robust to camera motion. This descriptor consistently outperforms other state-of-the-art descriptors, in particular in uncontrolled realistic videos. We evaluate our video description in the context of action classification with a bag-of-features approach. Experimental results show a significant improvement over the state of the art on four datasets of varying difficulty, i.e. KTH, YouTube, Hollywood2 and UCF sports.
Type de document :
Communication dans un congrès
CVPR 2011 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.3169-3176, 2011, 〈10.1109/CVPR.2011.5995407〉
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00583818
Contributeur : Thoth Team <>
Soumis le : jeudi 7 avril 2011 - 10:13:18
Dernière modification le : jeudi 11 janvier 2018 - 06:21:56
Document(s) archivé(s) le : vendredi 8 juillet 2011 - 02:35:35

Fichier

wang_cvpr11.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Heng Wang, Alexander Kläser, Cordelia Schmid, Liu Cheng-Lin. Action Recognition by Dense Trajectories. CVPR 2011 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2011, Colorado Springs, United States. IEEE, pp.3169-3176, 2011, 〈10.1109/CVPR.2011.5995407〉. 〈inria-00583818〉

Partager

Métriques

Consultations de la notice

5310

Téléchargements de fichiers

29173