Weakly supervised learning of interactions between humans and objects

Alessandro Prest 1, 2 Cordelia Schmid 1 Vittorio Ferrari 2
1 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We introduce a weakly supervised approach for learning human actions modeled as interactions between humans and objects. Our approach is human-centric: we first localize a human in the image and then determine the object relevant for the action and its spatial relation with the human. The model is learned automatically from a set of still images annotated (only) with the action label. Our approach relies on a human detector to initialize the model learning. For robustness to various degrees of visibility, we build a detector that learns to combine a set of existing part detectors. Starting from humans detected in a set of images depicting the action, our approach determines the action object and its spatial relation to the human. Its final output is a probabilistic model of the human-object interaction, i.e. the spatial relation between the human and the object.
Type de document :
Rapport
[Technical Report] RT-391, INRIA. 2010
Liste complète des métadonnées



https://hal.inria.fr/inria-00516477
Contributeur : Alessandro Prest <>
Soumis le : jeudi 9 septembre 2010 - 17:28:21
Dernière modification le : samedi 17 septembre 2016 - 01:36:50
Document(s) archivé(s) le : mardi 23 octobre 2012 - 15:50:20

Fichiers

RT-0391.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00516477, version 1

Collections

Citation

Alessandro Prest, Cordelia Schmid, Vittorio Ferrari. Weakly supervised learning of interactions between humans and objects. [Technical Report] RT-391, INRIA. 2010. <inria-00516477>

Partager

Métriques

Consultations de
la notice

439

Téléchargements du document

367