P-CNN: Pose-based CNN Features for Action Recognition

Guilhem Chéron 1, 2, 3, 4 Ivan Laptev 1, 2 Cordelia Schmid 3
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : This work targets human action recognition in video. While recent methods typically represent actions by statistics of local video features, here we argue for the importance of a representation derived from human pose. To this end we propose a new Pose-based Convolutional Neural Network descriptor (P-CNN) for action recognition. The descriptor aggregates motion and appearance information along tracks of human body parts. We investigate different schemes of temporal aggregation and experiment with P-CNN features obtained both for automatically estimated and manually annotated human poses. We evaluate our method on the recent and challenging JHMDB and MPII Cooking datasets. For both datasets our method shows consistent improvement over the state of the art.
Type de document :
Communication dans un congrès
ICCV - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. IEEE, pp.3218-3226, <10.1109/ICCV.2015.368>
Liste complète des métadonnées


https://hal.inria.fr/hal-01187690
Contributeur : Thoth Team <>
Soumis le : mercredi 23 septembre 2015 - 13:55:35
Dernière modification le : vendredi 11 août 2017 - 11:48:31
Document(s) archivé(s) le : mardi 29 décembre 2015 - 09:36:06

Fichier

P-CNN_cheronICCV15.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Guilhem Chéron, Ivan Laptev, Cordelia Schmid. P-CNN: Pose-based CNN Features for Action Recognition. ICCV - IEEE International Conference on Computer Vision, Dec 2015, Santiago, Chile. IEEE, pp.3218-3226, <10.1109/ICCV.2015.368>. <hal-01187690>

Partager

Métriques

Consultations de
la notice

1156

Téléchargements du document

489