Will person detection help bag-of-features action recognition? - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Rapport (Rapport De Recherche) Année : 2010

Will person detection help bag-of-features action recognition?

Résumé

Bag-of-feature (BoF) models currently achieve state-of-the-art performance for action recognition. While such models do not explicitly account for people in video, person localization combined with BoF is expected to give further improvement for action recognition. The purpose of this paper is to validate this assumption and to quantify the improvements in action recognition expected from current and future person detectors. Given locations of people in video, we find that---somewhat surprisingly---background suppression leads only to a limited gain in performance. This holds for actions in both simple and complex scenes. On the other hand, we show how spatial locations of people enable to incorporate strong geometrical constraints in BoF models and in this way to improve the accuracy of action recognition in some cases. Our conclusions are validated with extensive experiments on three datasets with varying complexity, basic KTH, realistic UCF Sports and challenging Hollywood.
Fichier principal
Vignette du fichier
RR-7373.pdf (1.19 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)

Dates et versions

inria-00514828 , version 1 (03-09-2010)

Identifiants

  • HAL Id : inria-00514828 , version 1

Citer

Alexander Klaser, Marcin Marszałek, Ivan Laptev, Cordelia Schmid. Will person detection help bag-of-features action recognition?. [Research Report] RR-7373, INRIA. 2010. ⟨inria-00514828⟩
580 Consultations
200 Téléchargements

Partager

Gmail Facebook X LinkedIn More