Sciweavers

ICCV
2009
IEEE

Automatic annotation of human actions in video

14 years 7 months ago
Automatic annotation of human actions in video
This paper addresses the problem of automatic temporal annotation of realistic human actions in video using mini- mal manual supervision. To this end we consider two asso- ciated problems: (a) weakly-supervised learning of action models from readily available annotations, and (b) tempo- ral localization of human actions in test videos. To avoid the prohibitive cost of manual annotation for training, we use movie scripts as a means of weak supervision. Scripts, how- ever, provide only implicit, noisy, and imprecise information about the type and location of actions in video. We address this problem with a kernel-based discriminative clustering algorithm that locates actions in the weakly-labeled train- ing data. Using the obtained action samples, we train tem- poral action detectors and apply them to locate actions in the raw video data. Our experiments demonstrate that the proposed method for weakly-supervised learning of action models leads to significant improvement i...
Olivier Duchenne, Ivan Laptev, Josef Sivic, Franci
Added 13 Jul 2009
Updated 10 Jan 2010
Type Conference
Year 2009
Where ICCV
Authors Olivier Duchenne, Ivan Laptev, Josef Sivic, Francis Bach and Jean Ponce
Comments (0)