SpatioTemporal focus for skeleton-based action recognition

•The multi-scale representations of the skeleton improve the performance of recognition.•Learning different temporal dynamics according to different action instances.•The model based on GCN and attention captures the topology information of skeleton.•A complementary representation of video against R...

Full description

Saved in:
Bibliographic Details
Published inPattern recognition Vol. 136; p. 109231
Main Authors Wu, Liyu, Zhang, Can, Zou, Yuexian
Format Journal Article
LanguageEnglish
Published Elsevier Ltd 01.04.2023
Subjects
Online AccessGet full text

Cover

Loading…