GeometryMotion-Transformer: An End-to-End Framework for 3D Action Recognition.

Jiaheng Liu Jinyang Guo Dong Xu

Published in: IEEE Trans. Multim. (2023)

Keyphrases

end to end
action recognition
bag of words
human detection
computer vision
video dataset
probabilistic model
spatial temporal
action classification
activity recognition
human actions
congestion control
video sequences
static images
recognition of human actions