A time series kernel for action recognition

Adrien Gaidon 1, 2 Zaid Harchaoui 1 Cordelia Schmid 1
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We address the problem of action recognition by describing actions as time series of frames and introduce a new kernel to compare their dynamical aspects. Action recognition in realistic videos has been successfully addressed using kernel methods like SVMs. Most existing approaches average local features over video volumes and compare the resulting vectors using kernels on bags of features. In contrast, we model actions as time series of per-frame representations and propose a kernel specifically tailored for the purpose of action recognition. Our main contributions are the following: (i) we provide a new principled way to compare the dynamics and temporal structure of actions by computing the distance between their auto-correlations, (ii) we derive a practical formulation to compute this distance in any feature space deriving from a base kernel between frames and (iii) we report experimental results on recent action recognition datasets showing that it provides useful complementary information to the average distribution of frames, as used in state-of-the-art models based on bag-of-features.
Type de document :
Communication dans un congrès
Jesse Hoey and Stephen McKenna and Emanuele Trucco. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. BMVA Press, pp.63.1-63.11, 2011, 〈10.5244/C.25.63〉
Liste complète des métadonnées

Littérature citée [7 références]  Voir  Masquer  Télécharger


https://hal.inria.fr/inria-00613089
Contributeur : Thoth Team <>
Soumis le : vendredi 5 août 2011 - 11:09:43
Dernière modification le : mercredi 11 avril 2018 - 01:58:19
Document(s) archivé(s) le : lundi 5 décembre 2016 - 00:25:52

Identifiants

Collections

Citation

Adrien Gaidon, Zaid Harchaoui, Cordelia Schmid. A time series kernel for action recognition. Jesse Hoey and Stephen McKenna and Emanuele Trucco. BMVC 2011 - British Machine Vision Conference, Aug 2011, Dundee, United Kingdom. BMVA Press, pp.63.1-63.11, 2011, 〈10.5244/C.25.63〉. 〈inria-00613089v2〉

Partager

Métriques

Consultations de la notice

1349

Téléchargements de fichiers

1756