Adaptive Channel-Enhanced Graph Convolution for Skeleton-Based Human Action Recognition

Adaptive Channel-Enhanced Graph Convolution for Skeleton-Based Human Action Recognition

Obtaining discriminative joint features is crucial for skeleton-based human action recognition. Current models mainly focus on the research of skeleton topology encoding. However, their predefined topology is the same and fixed for all action samples, making it challenging to obtain discriminative j...

Full description

Bibliographic Details
Main Authors: Xiao-Wei Han, Xing-Yu Chen, Ying Cui, Qiu-Yang Guo, Wen Hu
Format: Article
Language:English
Published: MDPI AG 2024-09-01
Series:Applied Sciences
Subjects:
human action recognition
adaptive graph convolutional neural network
channel attention
skeleton data
Online Access:https://www.mdpi.com/2076-3417/14/18/8185

Internet

https://www.mdpi.com/2076-3417/14/18/8185

Similar Items