Multi-modal Multi-label Facial Action Unit Detection with Transformer.

Lingfeng Wang Shisen Wang Jin Qi

Published in: CoRR (2022)

Keyphrases

multi modal
multi label
image annotation
multi label classification
text categorization
image classification
graph cuts
automatic image annotation
text classification
facial action units
semantic concepts
multiscale
data sets
semi supervised learning
text mining
domain knowledge
metadata