Institute Homepage
Institute Homepage DE Sign In

Back

Perceiving Systems Conference Paper 2018

Human Motion Parsing by Hierarchical Dynamic Clustering

Thumb ticker sm img 20170401 214555 1
Perceiving Systems
Siyu Tang
Guest Scientist
Thumb ticker sm profile1
Perceiving Systems
Yan Zhang
Bmvc pic

Parsing continuous human motion into meaningful segments plays an essential role in various applications. In this work, we propose a hierarchical dynamic clustering framework to derive action clusters from a sequence of local features in an unsuper- vised bottom-up manner. We systematically investigate the modules in this framework and particularly propose diverse temporal pooling schemes, in order to realize accurate temporal action localization. We demonstrate our method on two motion parsing tasks: temporal action segmentation and abnormal behavior detection. The experimental results indicate that the proposed framework is significantly more effective than the other related state-of-the-art methods on several datasets.

Author(s): Yan Zhang and Siyu Tang and He Sun and Heiko Neumann
Book Title: Proceedings of the British Machine Vision Conference (BMVC)
Pages: 269
Year: 2018
Month: September
Day: 3-6
Publisher: BMVA Press
Project(s):
Bibtex Type: Conference Paper (inproceedings)
Event Name: 29th British Machine Vision Conference
Event Place: Newcastle upon Tyne
Electronic Archiving: grant_archive
Attachments:

BibTex 

@inproceedings{hdc:bmvc:2018,
  title = {Human Motion Parsing by Hierarchical Dynamic Clustering},
  booktitle = {Proceedings of the British Machine Vision Conference (BMVC)},
  abstract = {Parsing continuous human motion into meaningful segments plays an essential role in various applications. In this work, we propose a hierarchical dynamic clustering framework to derive action clusters from a sequence of local features in an unsuper- vised bottom-up manner. We systematically investigate the modules in this framework and particularly propose diverse temporal pooling schemes, in order to realize accurate temporal action localization. We demonstrate our method on two motion parsing tasks: temporal action segmentation and abnormal behavior detection. The experimental results indicate that the proposed framework is significantly more effective than the other related state-of-the-art methods on several datasets.},
  pages = {269},
  publisher = {BMVA Press},
  month = sep,
  year = {2018},
  slug = {hdc-bmvc-2018},
  author = {Zhang, Yan and Tang, Siyu and Sun, He and Neumann, Heiko},
  month_numeric = {9}
}