A spatial attentive and temporal dilated (SATD) GCN for skeleton‐based action recognition

A spatial attentive and temporal dilated (SATD) GCN for skeleton‐based action recognition

Abstract Current studies have shown that the spatial‐temporal graph convolutional network (ST‐GCN) is effective for skeleton‐based action recognition. However, for the existing ST‐GCN‐based methods, their temporal kernel size is usually fixed over all layers, which makes them cannot fully exploit th...

Full description

Bibliographic Details
Main Authors: Jiaxu Zhang, Gaoxiang Ye, Zhigang Tu, Yongtao Qin, Qianqing Qin, Jinlu Zhang, Jun Liu
Format: Article
Language:English
Published: Wiley 2022-03-01
Series:CAAI Transactions on Intelligence Technology
Subjects:
feature extraction
image representation
image recognition
image motion analysis
learning (artificial intelligence)
image classification
Online Access:https://doi.org/10.1049/cit2.12012

Internet

https://doi.org/10.1049/cit2.12012

Similar Items