An End to End Framework With Adaptive Spatio-Temporal Attention Module for Human Action Recognition

An End to End Framework With Adaptive Spatio-Temporal Attention Module for Human Action Recognition

Human action recognition is a challenging task in computer vision. Modeling spatial-temporal information in videos effectively is crucial for the performance improvement of action recognition. In this paper, we introduce an end to end framework, Spatio-Temporal Attention ConvNet (STACNet), which com...

Full description

Bibliographic Details
Main Authors: Shaocan Liu, Xin Ma, Hanbo Wu, Yibin Li
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Action recognition
spatial attention
temporal attention
end to end
convolutional neural network
Online Access:https://ieeexplore.ieee.org/document/9028179/

Internet

https://ieeexplore.ieee.org/document/9028179/

Similar Items