STGL-GCN: Spatial–Temporal Mixing of Global and Local Self-Attention Graph Convolutional Networks for Human Action Recognition

STGL-GCN: Spatial–Temporal Mixing of Global and Local Self-Attention Graph Convolutional Networks for Human Action Recognition

Human action recognition methods based on skeleton data have been widely studied owing to their strong robustness to illumination and complex backgrounds. Existing methods have achieved good recognition results; however, they have certain challenges, such as the fixed topological structure of the gr...

Full description

Bibliographic Details
Main Authors: Zhenggui Xie, Gengzhong Zheng, Liming Miao, Wei Huang
Format: Article
Language:English
Published: IEEE 2023-01-01
Series:IEEE Access
Subjects:
Global self-attention matrix
local self-attention matrix
spatial–temporal graph convolutional networks
action recognition
Online Access:https://ieeexplore.ieee.org/document/10047922/

Similar Items

Similar Items