Cmf-transformer: cross-modal fusion transformer for human action recognition.

Jun Wang Limin Xia Xin Wen

Published in: Mach. Vis. Appl. (2024)

Keyphrases

cross modal
multi modal
multimedia retrieval
multimedia databases
action recognition
information retrieval systems
human body
visual recognition
information retrieval
computer vision
similarity measure
high dimensional
image retrieval
perceptual information