Structure-Feature Fusion Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

Structure-Feature Fusion Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition

Human skeleton contains intuitive information of actions and has high robustness in dynamic environment. Therefore, it has been widely studied in action recognition tasks. Most existing methods of skeleton recognition are based on graph convolutional networks (GCNs), which extract the topological st...

Full description

Bibliographic Details
Main Authors: Zhitao Zhang, Zhengyou Wang, Shanna Zhuang, Fuyu Huang
Format: Article
Language:English
Published: IEEE 2020-01-01
Series:IEEE Access
Subjects:
Action recognition
structure-feature
adaptive fusion
graph convolution networks
Online Access:https://ieeexplore.ieee.org/document/9300173/

Internet

https://ieeexplore.ieee.org/document/9300173/

Similar Items