An Unsupervised Framework for Action Recognition Using Actemes

Kaustubh Kulkarni 1 Edmond Boyer 1 Radu Horaud 1 Amit Kale 2
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 speech recognition, phonemes have demonstrated their ef- ficacy to model the words of a language. While they are well defined for languages, their extension to human actions is not straightforward. In this paper, we study such an extension and propose an unsupervised framework to find phoneme-like units for actions, which we call actemes, using 3D data and without any prior assumptions. To this purpose, build on an earlier proposed framework in speech literature to automatically find actemes in the training data. We experimentally show that actions defined in terms of actemes and actions defined by whole units give simi- lar recognition results. We define actions out of the training set in terms of these actemes to see whether the actemes generalize to unseen actions. The results show that although the acteme definitions of the actions are not always semantically meaningful, they yield optimal recognition accu- racy and constitute a promising direction of research for action modeling.
Type de document :
Communication dans un congrès
Ron Kimmel and Reinhard Klette and Akihiro Sugimoto. ACCV 2010 - 10th Asian Conference on Computer Vision, Nov 2010, Queenstown, New Zealand. Springer, 6495, pp.592-605, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-19282-1_47〉
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00568906
Contributeur : Edmond Boyer <>
Soumis le : mercredi 23 février 2011 - 19:23:31
Dernière modification le : mardi 15 juillet 2014 - 22:01:50
Document(s) archivé(s) le : mardi 24 mai 2011 - 04:31:15

Fichier

accv2010_TemporalSeg.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

Collections

Citation

Kaustubh Kulkarni, Edmond Boyer, Radu Horaud, Amit Kale. An Unsupervised Framework for Action Recognition Using Actemes. Ron Kimmel and Reinhard Klette and Akihiro Sugimoto. ACCV 2010 - 10th Asian Conference on Computer Vision, Nov 2010, Queenstown, New Zealand. Springer, 6495, pp.592-605, 2010, Lecture Notes in Computer Science. 〈10.1007/978-3-642-19282-1_47〉. 〈inria-00568906〉

Partager

Métriques

Consultations de
la notice

369

Téléchargements du document

236