Weakly Supervised Action Labeling in Videos Under Ordering Constraints - Archive ouverte HAL Access content directly
Conference Papers Year : 2014

Weakly Supervised Action Labeling in Videos Under Ordering Constraints

(1, 2) , (1, 3) , (1, 3) , (1, 2) , (1, 2) , (4) , (1, 2)
1
2
3
4

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.
Fichier principal
Vignette du fichier
main.pdf (3.6 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01053967 , version 1 (04-08-2014)

Identifiers

Cite

Piotr Bojanowski, Rémi Lajugie, Francis Bach, Ivan Laptev, Jean Ponce, et al.. Weakly Supervised Action Labeling in Videos Under Ordering Constraints. ECCV - European Conference on Computer Vision, Sep 2014, Zurich, Switzerland. pp.628-643, ⟨10.1007/978-3-319-10602-1_41⟩. ⟨hal-01053967⟩
1746 View
359 Download

Altmetric

Share

Gmail Facebook Twitter LinkedIn More