GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition

GAS-GCN: Gated Action-Specific Graph Convolutional Networks for Skeleton-Based Action Recognition

Skeleton-based action recognition has achieved great advances with the development of graph convolutional networks (GCNs). Many existing GCNs-based models only use the fixed hand-crafted adjacency matrix to describe the connections between human body joints. This omits the important implicit connect...

Full description

Bibliographic Details
Main Authors: Wensong Chan, Zhiqiang Tian, Yang Wu
Format: Article
Language:English
Published: MDPI AG 2020-06-01
Series:Sensors
Subjects:
deep learning
action recognition
graph convolutional networks
gated convolutional neural networks
Online Access:https://www.mdpi.com/1424-8220/20/12/3499

Internet

https://www.mdpi.com/1424-8220/20/12/3499

Similar Items