STEP CATFormer: Spatial-Temporal Effective Body-Part Cross Attention Transformer for Skeleton-based Action Recognition.

Nguyen Huu Bao Long

Published in: CoRR (2023)

Keyphrases

action recognition
spatial temporal
body parts
human actions
bag of words
human detection
human pose
activity recognition
computer vision
static images
human pose estimation
bag of features
video database
event detection
human activities
sensor networks
image sequences