Weakly Supervised Action Labeling in Videos Under Ordering Constraints

Piotr Bojanowski 1, 2 Rémi Lajugie 1, 3 Francis Bach 1, 3 Ivan Laptev 1, 2 Jean Ponce 1, 2 Cordelia Schmid 4 Josef Sivic 1, 2
1 LIENS - Laboratoire d'informatique de l'école normale supérieure
2 WILLOW - Models of visual object recognition and scene understanding
DI-ENS - Département d'informatique de l'École normale supérieure, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
3 SIERRA - Statistical Machine Learning and Parsimony
DI-ENS - Département d'informatique de l'École normale supérieure, ENS Paris - École normale supérieure - Paris, Inria Paris-Rocquencourt, CNRS - Centre National de la Recherche Scientifique : UMR8548
4 LEAR - Learning and recognition in vision
Inria Grenoble - Rhône-Alpes, LJK - Laboratoire Jean Kuntzmann, INPG - Institut National Polytechnique de Grenoble
Abstract : We are given a set of video clips, each one annotated with an ordered list of actions, such as "walk" then "sit" then "answer phone" extracted from, for example, the associated text script. We seek to tem- porally localize the individual actions in each clip as well as to learn a discriminative classifier for each action. We formulate the problem as a weakly supervised temporal assignment with ordering constraints. Each video clip is divided into small time intervals and each time interval of each video clip is assigned one action label, while respecting the order in which the action labels appear in the given annotations. We show that the action label assignment can be determined together with learning a classifier for each action in a discriminative manner. We evaluate the proposed model on a new and challenging dataset of 937 video clips with a total of 787720 frames containing sequences of 16 different actions from 69 Hollywood movies.
Type de document :
Communication dans un congrès
David Fleet; Tomas Pajdla; Bernt Schiele; Tinne Tuytelaars. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. Springer, 8693 (Part V), pp.628-643, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-10602-1_41〉
Liste complète des métadonnées

Littérature citée [35 références]  Voir  Masquer  Télécharger
https://hal.inria.fr/hal-01053967
Contributeur : Piotr Bojanowski <>
Soumis le : lundi 4 août 2014 - 15:35:43
Dernière modification le : vendredi 25 mai 2018 - 12:02:06
Document(s) archivé(s) le : mercredi 26 novembre 2014 - 00:05:51

Fichier

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

Identifiants

Collections

INRIA | LJK | LJK_GI | LJK_GI_LEAR | UGA | ENS-PARIS | PSL

Citation

Piotr Bojanowski, Rémi Lajugie, Francis Bach, Ivan Laptev, Jean Ponce, et al.. Weakly Supervised Action Labeling in Videos Under Ordering Constraints. David Fleet; Tomas Pajdla; Bernt Schiele; Tinne Tuytelaars. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. Springer, 8693 (Part V), pp.628-643, 2014, Lecture Notes in Computer Science. 〈10.1007/978-3-319-10602-1_41〉. 〈hal-01053967〉

Exporter

BibTeX TEI DC DCterms EndNote

Partager

Métriques

Consultations de la notice

1525

Téléchargements de fichiers

502

Contact


archive-ouverte@inria.fr