A frozen-CLIP facial expression recognition framework with LLM-guided prompts, prototype regularization, and sparse global-local alignment claims new state-of-the-art accuracy across RAF-DB, FERPlus, and AffectNet.
Training deep networks for facial ex- pression recognition with crowd-sourced label distribution
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Multimodal Prompt Alignment for Facial Expression Recognition
A frozen-CLIP facial expression recognition framework with LLM-guided prompts, prototype regularization, and sparse global-local alignment claims new state-of-the-art accuracy across RAF-DB, FERPlus, and AffectNet.