P-CNN: Pose-based CNN Features for Action Recognition - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2015

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

Résumé

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.
Fichier principal
Vignette du fichier
P-CNN_cheronICCV15.pdf (2.77 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Loading...

Dates et versions

hal-01187690 , version 1 (23-09-2015)

Identifiants

Citer

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. pp.3218-3226, ⟨10.1109/ICCV.2015.368⟩. ⟨hal-01187690⟩
1484 Consultations
645 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More