Unsupervised Discovery, Modeling and Analysis of long term Activities

Abstract : This work proposes a complete framework for human activity discovery, modeling, and recognition using videos. The framework uses trajectory information as input and goes up to video interpretation. The work reduces the gap between low-level vision information and semantic interpretation, by building an intermediate layer composed of Primitive Events. The proposed representation for primitive events aims at capturing meaningful motions (actions) over the scene with the advantage of being learned in an unsupervised manner. We propose the use of Primitive Events as descriptors to discover, model, and recognize activities automatically. The activity discovery is performed using only real tracking data. Semantics are added to the discovered activities (e.g., "Preparing Meal", "Eating") and the recognition of activities is performed with new datasets.
Type de document :
Communication dans un congrès
international Conference in Vision Systems, Nov 2011, Sophia Antipolis, France. 2011
Liste complète des métadonnées

Littérature citée [19 références]  Voir  Masquer  Télécharger

https://hal.inria.fr/inria-00621201
Contributeur : Guido Pusiol <>
Soumis le : vendredi 9 septembre 2011 - 16:18:31
Dernière modification le : jeudi 11 janvier 2018 - 16:22:50
Document(s) archivé(s) le : lundi 5 décembre 2016 - 00:26:49

Fichier

ICVS_Paper.pdf
Fichiers produits par l'(les) auteur(s)

Identifiants

  • HAL Id : inria-00621201, version 1

Collections

Citation

Guido Pusiol, François Bremond, Monique Thonnat. Unsupervised Discovery, Modeling and Analysis of long term Activities. international Conference in Vision Systems, Nov 2011, Sophia Antipolis, France. 2011. 〈inria-00621201〉

Partager

Métriques

Consultations de la notice

158

Téléchargements de fichiers

267