Unsupervised Representation Learning with Long-Term Dynamics for Skeleton Based Action Recognition

Abstract

In recent years, skeleton based action recognition is becoming an increasingly attractive alternative to existing video-based approaches, beneficial from its robust and comprehensive 3D information. In this paper, we explore an unsupervised representation learning approach for the first time to capture the long-term global motion dynamics in skeleton sequences. We design a conditional skeleton inpainting architecture for learning a fixed-dimensional representation, guided by additional adversarial training strategies. We quantitatively evaluate the effectiveness of our learning approach on three well-established action recognition datasets. Experimental results show that our learned representation is discriminative for classifying actions and can substantially reduce the sequence inpainting errors.

Cite

Text

Zheng et al. "Unsupervised Representation Learning with Long-Term Dynamics for Skeleton Based Action Recognition." AAAI Conference on Artificial Intelligence, 2018. doi:10.1609/AAAI.V32I1.11853

Markdown

[Zheng et al. "Unsupervised Representation Learning with Long-Term Dynamics for Skeleton Based Action Recognition." AAAI Conference on Artificial Intelligence, 2018.](https://mlanthology.org/aaai/2018/zheng2018aaai-unsupervised/) doi:10.1609/AAAI.V32I1.11853

BibTeX

@inproceedings{zheng2018aaai-unsupervised,
  title     = {{Unsupervised Representation Learning with Long-Term Dynamics for Skeleton Based Action Recognition}},
  author    = {Zheng, Nenggan and Wen, Jun and Liu, Risheng and Long, Liangqu and Dai, Jianhua and Gong, Zhefeng},
  booktitle = {AAAI Conference on Artificial Intelligence},
  year      = {2018},
  pages     = {2644-2651},
  doi       = {10.1609/AAAI.V32I1.11853},
  url       = {https://mlanthology.org/aaai/2018/zheng2018aaai-unsupervised/}
}