Preprint
Sep 2026
Predicting Human Disagreement for Calibrated Dynamic Facial Expression Recognition
A disagreement-aware DFER framework that trains directly on the raw annotator count vector using a Dirichlet-Multinomial likelihood that provides scale-sensitive supervision for the Dirichlet concentration while preserving the predictive mean.
Yi-Ming Wang, Frederick W. B. Li, Jing-Yun Wang
· 0 citations