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

Authors

  • Nenggan Zheng Zhejiang University
  • Jun Wen Zhejiang University
  • Risheng Liu Dalian University of Technology
  • Liangqu Long Zhejiang University
  • Jianhua Dai Hunan Normal University
  • Zhefeng Gong Zhejiang University

Keywords:

Unsupervised Learning, Action Recognition, RNN, GAN

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.

Downloads

Published

2018-04-26

How to Cite

Zheng, N., Wen, J., Liu, R., Long, L., Dai, J., & Gong, Z. (2018). Unsupervised Representation Learning With Long-Term Dynamics for Skeleton Based Action Recognition. Proceedings of the AAAI Conference on Artificial Intelligence, 32(1). Retrieved from https://ojs.aaai.org/index.php/AAAI/article/view/11853

Issue

Section

Main Track: Machine Learning Applications