English

Temporal Human Action Segmentation via Dynamic Clustering

Computer Vision and Pattern Recognition 2018-03-20 v2

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 applicable 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.

Keywords

Cite

@article{arxiv.1803.05790,
  title  = {Temporal Human Action Segmentation via Dynamic Clustering},
  author = {Yan Zhang and He Sun and Siyu Tang and Heiko Neumann},
  journal= {arXiv preprint arXiv:1803.05790},
  year   = {2018}
}

Comments

comparing with the 1st version, only corrected typos

R2 v1 2026-06-23T00:54:20.047Z