Flexible Dictionaries for Action Classification

Abstract : We present a simple approach to action classification which constructs a vector quantization of primitive motions from time series data corresponding to relative limb position estimates. The temporal scale, mean, and shape of primitive motion trajectories are independently modeled, thus creating a exible dictionary of action primitives. We then explore two inference techniques that leverage our action dictionary representation, and evaluate their performance on both motion capture and video benchmark data. Our results indicate that even simplistic algorithms can outperform significantly more sophisticated ones in existing benchmark datasets.
Type de document :
Communication dans un congrès
The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008
Liste complète des métadonnées

Littérature citée [33 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00326723
Contributeur : Peter Sturm <>
Soumis le : dimanche 5 octobre 2008 - 12:46:37
Dernière modification le : lundi 6 octobre 2008 - 09:39:49
Document(s) archivé(s) le : lundi 8 octobre 2012 - 13:56:52

Fichier

mlvma08_submission_13.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00326723, version 1

Collections

Citation

Michalis Raptis, Kamil Wnuk, Stefano Soatto. Flexible Dictionaries for Action Classification. The 1st International Workshop on Machine Learning for Vision-based Motion Analysis - MLVMA'08, Oct 2008, Marseille, France. 2008. 〈inria-00326723〉

Partager

Métriques

Consultations de la notice

135

Téléchargements de fichiers

153