Actlets: A novel local representation for human action recognition in video

Muhammad Ullah 1 Ivan Laptev 1
1 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
Abstract : This paper addresses the problem of human action recognition in realistic videos. We follow the recently successful local approaches and represent videos by means of local motion descriptors. To overcome the huge variability of human actions in motion and appearance, we propose a supervised approach to learn local motion descriptors - actlets - from a large pool of annotated video data. The main motivation behind our method is to construct action-characteristic representations of body joints undergoing specific motion patterns while learning invariance with respect to changes in camera views, lighting, human clothing, and other factors. We avoid the prohibitive cost of manual supervision and show how to learn actlets automatically from synthetic videos of avatars driven by the motion-capture data. We evaluate our method and show its significant improvement as well as its complementarity to existing techniques on the challenging UCF-sports and YouTube-actions datasets.
Keywords : Action recognition actlets local motion descriptors supervised learning
Type de document :
Communication dans un congrès
ICIP 2012 - International Conference on Image Processing, Sep 2012, Orlando, Florida, United States. IEEE, pp.777 - 780, 2012, 〈10.1109/ICIP.2012.6466975〉
Liste complète des métadonnées

Littérature citée [15 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01063332
Contributeur : Suha Kwak <>
Soumis le : jeudi 11 septembre 2014 - 18:09:09
Dernière modification le : vendredi 25 mai 2018 - 12:02:06
Document(s) archivé(s) le : vendredi 12 décembre 2014 - 10:57:24

Fichier

ullah_icip12.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

INRIA | ENS-PARIS | PSL | INRIA-ROCQ

Citation

Muhammad Ullah, Ivan Laptev. Actlets: A novel local representation for human action recognition in video. ICIP 2012 - International Conference on Image Processing, Sep 2012, Orlando, Florida, United States. IEEE, pp.777 - 780, 2012, 〈10.1109/ICIP.2012.6466975〉. 〈hal-01063332〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

464

Téléchargements de fichiers

956

Contact


archive-ouverte@inria.fr