Pairwise features for human action recognition

Anh Phuong Ta 1 Christian Wolf 1, 2 Guillaume Lavoué 1 Atilla Baskurt 1, 2 Jean-Michel Jolion 1
1 M2DisCo - Geometry Processing and Constrained Optimization
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
2 imagine - Extraction de Caractéristiques et Identification
LIRIS - Laboratoire d'InfoRmatique en Image et Systèmes d'information
Abstract : Existing action recognition approaches mainly rely on the discriminative power of individual local descriptors extracted from spatio-temporal interest points (STIP), while the geometric relationships among the local features are ignored. This paper presents new features, called pairwise features (PWF), which encode both the appearance and the spatio-temporal relations of the local features for action recognition. First STIPs are extracted, then PWFs are constructed by grouping pairs of STIPs which are both close in space and close in time. We propose a combination of two codebooks for video representation. Experiments on two standard human action datasets: the KTH dataset and the Weizmann dataset show that the proposed approach outperforms most existing methods.
Type de document :
Communication dans un congrès
International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. IEEE, pp.3224-3227, 2010, 〈10.1109/ICPR.2010.788〉
Liste complète des métadonnées
https://hal.archives-ouvertes.fr/hal-01381471
Contributeur : Équipe Gestionnaire Des Publications Si Liris <>
Soumis le : vendredi 14 octobre 2016 - 14:46:23
Dernière modification le : lundi 10 décembre 2018 - 17:47:42

Identifiants

Collections

EC-LYON | LIRIS | INSA-LYON | UNIV-LYON1 | LABEXIMU

Citation

Anh Phuong Ta, Christian Wolf, Guillaume Lavoué, Atilla Baskurt, Jean-Michel Jolion. Pairwise features for human action recognition. International Conference on Pattern Recognition (ICPR), Aug 2010, Istanbul, Turkey. IEEE, pp.3224-3227, 2010, 〈10.1109/ICPR.2010.788〉. 〈hal-01381471〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

133

Contact

support.ccsd.cnrs.fr
hal.support@ccsd.cnrs.fr
Logo CCSD