Action Recognition using Exemplar-based Embedding

Daniel Weinland 1 Edmond Boyer 1
1 PERCEPTION - Interpretation and Modelling of Images and Videos
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : In this paper, we address the problem of representing human actions using visual cues for the purpose of learning and recognition. Traditional approaches model actions as space-time representations which explicitly or implicitly encode the dynamics of an action through temporal dependencies. In contrast, we propose a new compact and efficient representation which does not account for such dependencies. Instead, motion sequences are represented with respect to a set of discriminative static key-pose exemplars and without modeling any temporal ordering. The interest is a time-invariant representation that drastically simplifies learning and recognition by removing time related information such as speed or length of an action. The proposed representation is equivalent to embedding actions into a space defined by distances to key-pose exemplars. We show how to build such embedding spaces of low dimension by identifying a vocabulary of highly discriminative exemplars using a forward selection. To test our representation, we have used a publicly available dataset which demonstrates that our method can precisely recognize actions, even with cluttered and non-segmented sequences.
Type de document :
Communication dans un congrès
CVPR 2008 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2008, Anchorage, United States. IEEE Computer Society, pp.1-7, 2008, 〈10.1109/CVPR.2008.4587731〉
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00590256
Contributeur : Team Perception <>
Soumis le : mardi 3 mai 2011 - 09:50:23
Dernière modification le : lundi 21 juillet 2014 - 07:41:30
Document(s) archivé(s) le : jeudi 4 août 2011 - 03:09:01

Fichier

weinland08.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Daniel Weinland, Edmond Boyer. Action Recognition using Exemplar-based Embedding. CVPR 2008 - IEEE Conference on Computer Vision and Pattern Recognition, Jun 2008, Anchorage, United States. IEEE Computer Society, pp.1-7, 2008, 〈10.1109/CVPR.2008.4587731〉. 〈inria-00590256〉

Partager

Métriques

Consultations de
la notice

249

Téléchargements du document

251