Preprint
Jul 2026
AffectFlow-DINO: Uncertainty-Aware Multi-Task Affect Estimation via Conditional Rectified Flow
A multi-task learning system for the 11th ABAW challenge that extends a standard deterministic architecture with a conditional rectified-flow head to model the inherent ambiguity of in-the-wild facial behavior, enabling uncertainty-aware one-to-many predictions through Monte Carlo sampling.
S. E. Bekhouche, A. Sellam, Fadi Dornaika et al.
· 0 citations