Multi-Term Attention Networks for Skeleton-Based Action Recognition

The same action takes different time in different cases. This difference will affect the accuracy of action recognition to a certain extent. We propose an end-to-end deep neural network called “Multi-Term Attention Networks” (MTANs), which solves the above problem by extracting temporal features wit...

Full description

Bibliographic Details

Published in:	Applied Sciences
Main Authors:	Xiaolei Diao, Xiaoqiang Li, Chen Huang
Format:	Article
Language:	English
Published:	MDPI AG 2020-07-01
Subjects:	action recognition skeleton sequences attention mechanism spatio-temporal features
Online Access:	https://www.mdpi.com/2076-3417/10/15/5326