Multiple stream deep learning model for human action recognition

作者：

Highlights：

• Multi-stream deep learning model for action recognition

• 3-Channel depth based MHI for forward and backward motion discrimination

• Relevant joint selection mechanism to create sparse skeleton graph

摘要

•Multi-stream deep learning model for action recognition•3-Channel depth based MHI for forward and backward motion discrimination•Relevant joint selection mechanism to create sparse skeleton graph

论文关键词：Deep learning,Information fusion,Action recognition

论文评审过程：Received 17 May 2019, Revised 21 September 2019, Accepted 3 October 2019, Available online 31 October 2019, Version of Record 21 January 2020.

论文官网地址：https://doi.org/10.1016/j.imavis.2019.10.004