Learning Realistic Human Actions from Movies - Inria - Institut national de recherche en sciences et technologies du numérique Accéder directement au contenu
Communication Dans Un Congrès Année : 2008

Learning Realistic Human Actions from Movies

Résumé

The aim of this paper is to address recognition of natural human actions in diverse and realistic video settings. This challenging but important subject has mostly been ignored in the past due to several problems one of which is the lack of realistic and annotated video datasets. Our first contribution is to address this limitation and to investigate the use of movie scripts for automatic annotation of human actions in videos. We evaluate alternative methods for action retrieval from scripts and show benefits of a text-based classifier. Using the retrieved action samples for visual learning, we next turn to the problem of action classification in video. We present a new method for video classification that builds upon and extends several recent ideas including local space-time features, space-time pyramids and multi-channel non-linear SVMs. The method is shown to improve state-of-the-art results on the standard KTH action dataset by achieving 91.8% accuracy. Given the inherent problem of noisy labels in automatic annotation, we particularly investigate and show high tolerance of our method to annotation errors in the training set. We finally apply the method to the learning and classification of challenging action classes in movies and show promising results.
Fichier principal
Vignette du fichier
LaptevMarszalekSchmidRozenfeld-CVPR08-HumanActions.pdf (829.19 Ko) Télécharger le fichier
Vignette du fichier
humact.png (380.57 Ko) Télécharger le fichier
LaptevMarszalekSchmidRozenfeld-CVPR08-HumanActions-demo.mpg (22.42 Mo) Télécharger le fichier
Origine : Fichiers produits par l'(les) auteur(s)
Format : Figure, Image
Format : Autre
Loading...

Dates et versions

inria-00548659 , version 1 (20-12-2010)

Identifiants

Citer

Ivan Laptev, Marcin Marszałek, Cordelia Schmid, Benjamin Rozenfeld. Learning Realistic Human Actions from Movies. CVPR 2008 - IEEE Conference on Computer Vision & Pattern Recognition, Jun 2008, Anchorage, United States. pp.1-8, ⟨10.1109/CVPR.2008.4587756⟩. ⟨inria-00548659⟩
2249 Consultations
3924 Téléchargements

Altmetric

Partager

Gmail Facebook X LinkedIn More