Global relational reasoning with spatial temporal graph interaction networks for skeleton-based action recognition

作者：

Highlights：

• Spatial–temporal graph interaction network is proposed.

• A fully connected similarity graph for capturing relations is proposed.

• Local dynamics and global spatial–temporal relations can be simultaneously mined.

摘要

•Spatial–temporal graph interaction network is proposed.•A fully connected similarity graph for capturing relations is proposed.•Local dynamics and global spatial–temporal relations can be simultaneously mined.

论文关键词：Deep learning,Graph convolutional network,Convolutional neural networks,Spatio-temporal graph,Message passing

论文评审过程：Received 9 October 2019, Revised 18 December 2019, Accepted 30 December 2019, Available online 7 January 2020, Version of Record 15 January 2020.

论文官网地址：https://doi.org/10.1016/j.image.2019.115776