Actions in Context - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2009

Actions in Context

Résumé

This paper exploits the context of natural dynamic scenes for human action recognition in video. Human actions are frequently constrained by the purpose and the physical properties of scenes and demonstrate high correlation with particular scene classes. For example, eating often happens in a kitchen while running is more common outdoors. The contribution of this paper is three-fold: (a) we automatically discover relevant scene classes and their correlation with human actions, (b) we show how to learn selected scene classes from video without manual supervision and (c) we develop a joint framework for action and scene recognition and demonstrate improved recognition of both in natural video. We use movie scripts as a means of automatic supervision for training. For selected action classes we identify correlated scene classes in text and then retrieve video samples of actions and scenes for training using script-to-video alignment. Our visual models for scenes and actions are formulated within the bag-of-features framework and are combined in a joint scene-action SVM-based classifier. We report experimental results and validate the method on a new large dataset with twelve action classes and ten scene classes acquired from 69 movies.
Fichier principal
Vignette du fichier
MarszalekLaptevSchmid-CVPR09-ActionsContext.pdf (356.69 Ko) Télécharger le fichier
Vignette du fichier
actcon.png (422.92 Ko) Télécharger le fichier
MarszalekLaptevSchmid-CVPR09-ActionsContext-demo.avi (12.25 Mo) Télécharger le fichier
MarszalekLaptevSchmid-CVPR09-ActionsContext-poster.pdf (401.31 Ko) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Format : Autre
Format : Autre

Dates et versions

inria-00548645 , version 1 (20-12-2010)

Identifiants

Citer

Marcin Marszałek, Ivan Laptev, Cordelia Schmid. Actions in Context. CVPR 2009 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2009, Miami, United States. pp.2929-2936, ⟨10.1109/CVPR.2009.5206557⟩. ⟨inria-00548645⟩
609 Consultations
2244 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More