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...
|Published in:||Applied soft computing : the official journal of the World Federation on Soft Computing (WFSC), Vol. 86 (2020), p. 0|
|Other Involved Persons:||;|
|QR Code:||Show QR Code|
Applied soft computing : the official journal of the World Federation on Soft Computing (WFSC), Vol. 86 (2020), p. 0