Human Motion Parsing by Hierarchical Dynamic Clustering

2018

Conference Paper

ps

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.

@inproceedings{hdc:bmvc:2018,
  title = {Human Motion Parsing by Hierarchical Dynamic Clustering},
  author = {Zhang, Yan and Tang, Siyu and Sun, He and Neumann, Heiko},
  booktitle = {Proceedings of the British Machine Vision Conference (BMVC)},
  pages = {269},
  publisher = {BMVA Press},
  month = sep,
  year = {2018},
  doi = {},
  month_numeric = {9}
}