Human action recognition using two-stream attention based LSTM networks

It is well known that different frames play different roles in feature learning in video based human action recognition task. However, most existing deep learning models put the same weights on different visual and temporal cues in the parameter training stage, which severely affects the feature dis...

Full description

Bibliographic Details
Published in:Applied soft computing : the official journal of the World Federation on Soft Computing (WFSC), Vol. 86 (2020), p. 0
Main Author: Dai, Cheng
Other Involved Persons: Liu, Xingang ; Lai, Jinfeng
Format: electronic Article
Language:English
ISSN:1568-4946
Physical Description:Online-Ressource
DOI:10.1016/j.asoc.2019.105820
QR Code: Show QR Code