2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition

2s-GATCN: Two-Stream Graph Attentional Convolutional Networks for Skeleton-Based Action Recognition

As human actions can be characterized by the trajectories of skeleton joints, skeleton-based action recognition techniques have gained increasing attention in the field of intelligent recognition and behavior analysis. With the emergence of large datasets, graph convolutional network (GCN) approache...

Full description

Bibliographic Details
Main Authors: Shu-Bo Zhou, Ran-Ran Chen, Xue-Qin Jiang, Feng Pan
Format: Article
Language:English
Published: MDPI AG 2023-04-01
Series:Electronics
Subjects:
action recognition
GCN
connection strength
graph attention block
CBAM
Online Access:https://www.mdpi.com/2079-9292/12/7/1711

Internet

https://www.mdpi.com/2079-9292/12/7/1711

Similar Items