Loading...
Loading...

Go to the content (press return)

Metric learning from poses for temporal clustering of human motion

Author
Lopez, A.; Gall, J.; Casas, J.; van Gool, L.
Type of activity
Presentation of work at congresses
Name of edition
24th British Machine Vision Conference
Date of publication
2013
Presentation's date
2012-09-04
Book of congress proceedings
BMVC 2013: Proceedings of the 13th British Machine Vision Conference: 9-13 September 2013, Bristol University, UK
First page
49.1
Last page
49.12
DOI
https://doi.org/10.5244/C.26.49 Open in new window
Repository
http://hdl.handle.net/2117/18496 Open in new window
URL
http://www.bmva.org/bmvc/2012/BMVC/paper049/index.html Open in new window
Abstract
Temporal clustering of human motion into semantically meaningful behaviors is a challenging task. While unsupervised methods do well to some extent, the obtained clusters often lack a semantic interpretation. In this paper, we propose to learn what makes a sequence of human poses different from others such that it should be annotated as an action. To this end, we formulate the problem as weakly supervised temporal clustering for an unknown number of clusters. Weak supervision is attained by lear...
Citation
Lopez, A. [et al.]. Metric learning from poses for temporal clustering of human motion. A: British Machine Vision Conference. "Proceedings of the British Machine Vision Conference". Surrey: 2012, p. 49.1-49.12.
Group of research
GPI - Image and Video Processing Group
IDEAI-UPC - Intelligent Data Science and Artificial Intelligence Research Center

Participants

  • Lopez Mendez, Adolfo  (author and speaker )
  • Gall, Juergen  (author and speaker )
  • Casas Pla, Josep Ramon  (author and speaker )
  • van Gool, Luc  (author and speaker )