Human interaction recognition based on the co-occurence of visual words

Abstract : This paper describes a novel methodology for automated recognition of high-level activities. A key aspect of our framework relies on the concept of co-occurring visual words for describing interactions between several persons. Motivated by the numerous success of human activity recognition methods using bag-of-words, this paradigm is extended. A 3-D XYT spatio-temporal volume is generated for each interacting person and a set of visual words is extracted to represent his activity. The interaction is then represented by the frequency of co-occurring visual words between persons. For our experiments, we used the UT-interaction dataset which contains several complex human-human interactions.
Type de document :
Communication dans un congrès
IEEE CVPR CMSI workshop, Jun 2014, United States. pp.455-460, 2014
Liste complète des métadonnées

Littérature citée [25 références]  Voir  Masquer  Télécharger

https://hal-univ-bourgogne.archives-ouvertes.fr/hal-01018752
Contributeur : Yannick Benezeth <>
Soumis le : vendredi 4 juillet 2014 - 21:52:43
Dernière modification le : lundi 7 juillet 2014 - 08:52:58
Document(s) archivé(s) le : samedi 4 octobre 2014 - 13:05:53

Fichier

human-interaction-recognition....
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : hal-01018752, version 1

Collections

Citation

K. Nour El Houda Slimani, Yannick Benezeth, Feriel Souami. Human interaction recognition based on the co-occurence of visual words. IEEE CVPR CMSI workshop, Jun 2014, United States. pp.455-460, 2014. 〈hal-01018752〉

Partager

Métriques

Consultations de
la notice

154

Téléchargements du document

138