Cross-Modal Learning with 3D Deformable Attention for Action Recognition.

Sangwon Kim Dasom Ahn ByoungChul Ko

Published in: ICCV (2023)

Keyphrases

action recognition
cross modal
bag of words
activity recognition
learning algorithm
computer vision
action classification
multi modal
pose estimation
recognizing human actions
visual recognition
human actions
image classification
semi supervised
low level
spatio temporal
high level
search engine