Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition

Global Co-Occurrence Feature and Local Spatial Feature Learning for Skeleton-Based Action Recognition

Recent progress on skeleton-based action recognition has been substantial, benefiting mostly from the explosive development of Graph Convolutional Networks (GCN). However, prevailing GCN-based methods may not effectively capture the global co-occurrence features among joints and the local spatial st...

Full description

Bibliographic Details
Main Authors: Jun Xie, Wentian Xin, Ruyi Liu, Qiguang Miao, Lijie Sheng, Liang Zhang, Xuesong Gao
Format: Article
Language:English
Published: MDPI AG 2020-10-01
Series:Entropy
Subjects:
skeleton-based action recognition
graph convolutional network
feature fusion
Online Access:https://www.mdpi.com/1099-4300/22/10/1135

Internet

https://www.mdpi.com/1099-4300/22/10/1135

Similar Items