Institute Homepage
Institute Homepage EN Sign In

Back

Perzeptive Systeme Article 2018

Temporal Human Action Segmentation via Dynamic Clustering

Thumb ticker sm img 20170401 214555 1
Perzeptive Systeme
Siyu Tang
Guest Scientist
Thumb ticker sm profile1
Perzeptive Systeme
Yan Zhang
Yanzhang clustering

We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applica- ble in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of- the-art results for both online and offline settings.

Author(s): Yan Zhang and He Sun and Siyu Tang and Heiko Neumann
Journal: arXiv preprint arXiv:1803.05790
Year: 2018
Project(s):
Bibtex Type: Article (article)
URL: https://arxiv.org/pdf/1803.05790.pdf
Electronic Archiving: grant_archive
Institution: arXiv

BibTex 

@article{humanActionSegmentationZhang,
  title = {Temporal Human Action Segmentation via Dynamic Clustering},
  journal = {arXiv preprint 	arXiv:1803.05790},
  abstract = {We present an effective dynamic clustering algorithm for the task of temporal human action segmentation, which has comprehensive applications such as robotics, motion analysis, and patient monitoring. Our proposed algorithm is unsupervised, fast, generic to process various types of features, and applica- ble in both the online and offline settings. We perform extensive experiments of processing data streams, and show that our algorithm achieves the state-of- the-art results for both online and offline settings.},
  institution = {arXiv},
  year = {2018},
  slug = {human-action-segmentation-dynamic-clustering},
  author = {Zhang, Yan and Sun, He and Tang, Siyu and Neumann, Heiko},
  url = {https://arxiv.org/pdf/1803.05790.pdf}
}