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...

Full description

Bibliographic Details
Main Authors: Lei Wang, Yangyang Xu, Jun Cheng, Haiying Xia, Jianqin Yin, Jiaji Wu
Format: Article
Language:English
Published: IEEE 2018-01-01
Series:IEEE Access
Subjects:
Artificial intelligent
human action recognition
attention model
deep neural networks
robotic system
Online Access:https://ieeexplore.ieee.org/document/8319974/

Similar Items

Similar Items