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...
Saved in:
Published in | Pattern recognition Vol. 136; p. 109231 |
---|---|
Main Authors | , , |
Format | Journal Article |
Language | English |
Published |
Elsevier Ltd
01.04.2023
|
Subjects | |
Online Access | Get full text |
Cover
Loading…
Be the first to leave a comment!