Weakly Supervised Action Labeling in Videos Under Ordering Constraints

Piotr Bojanowski; Rémi Lajugie; Francis Bach; Ivan Laptev; Jean Ponce; Cordelia Schmid; Josef Sivic

doi:10.1007/978-3-319-10602-1_41

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

CNRS - Centre National de la Recherche Scientifique : UMR8548, Inria Paris-Rocquencourt, DI-ENS - Département d'informatique de l'École normale supérieure

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〉

Domaine :

Informatique [cs] / Vision par ordinateur et reconnaissance de formes [cs.CV]

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

main.pdf

Fichiers produits par l'(les) auteur(s)

Weakly Supervised Action Labeling in Videos Under Ordering Constraints

Fichier

Identifiants

Collections

Citation

Exporter

Métriques

1657

513

Contact

Weakly Supervised Action Labeling in Videos Under Ordering Constraints

Fichier

Identifiants

Collections

Citation

Exporter

Partager

Métriques

1657

513

Contact