Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks

Human Action Recognition by Learning Spatio-Temporal Features With Deep Neural Networks

Human action recognition is one of the fundamental challenges in robotics systems. In this paper, we propose one lightweight action recognition architecture based on deep neural networks just using RGB data. The proposed architecture consists of convolution neural network (CNN), long short-term memo...

Celý popis

Podrobná bibliografie
Hlavní autoři: Lei Wang, Yangyang Xu, Jun Cheng, Haiying Xia, Jianqin Yin, Jiaji Wu
Médium: Článek
Jazyk:English
Vydáno: IEEE 2018-01-01
Edice:IEEE Access
Témata:
Artificial intelligent
human action recognition
attention model
deep neural networks
robotic system
On-line přístup:https://ieeexplore.ieee.org/document/8319974/

Internet

https://ieeexplore.ieee.org/document/8319974/

Podobné jednotky