3Mformer: Multi-order Multi-mode Transformer for Skeletal Action Recognition.

Lei Wang Piotr Koniusz

Published in: CVPR (2023)

Keyphrases

action recognition
spatial temporal
bag of words
activity recognition
human actions
human detection
viewpoint
body parts
bag of features
static images
view invariant
computer vision
feature vectors
image representation
human activities
depth sensors