Multi-modal Instance Refinement for Cross-domain Action Recognition.

Yuan Qing Naixing Wu Shaohua Wan Lixin Duan

Published in: CoRR (2023)

Keyphrases

multi modal
action recognition
cross domain
bag of words
computer vision
transfer learning
activity recognition
knowledge transfer
human actions
text categorization
image annotation
high dimensional
audio visual
e government
data points
human activities
high level