A vision-language model for 3D/4D facial expression recognition is reported to reach state-of-the-art accuracy, but it secretly relies on emotion labels to choose its training prompts.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
REJECT 1representative citing papers
citing papers explorer
-
Self-Supervised Multi-View Representation Learning using Vision-Language Model for 3D/4D Facial Expression Recognition
A vision-language model for 3D/4D facial expression recognition is reported to reach state-of-the-art accuracy, but it secretly relies on emotion labels to choose its training prompts.