AI RESEARCH

Multimodal Emotion Recognition via Causal-Diffusion Bridge (Affect-Diff)

arXiv CS.CV

ArXi:2605.08252v1 Announce Type: new Multimodal emotion recognition on CMU-MOSEI faces an extreme imbalance as Happy accounts for 65.9% of samples while three Ekman categories collectively represent under 7%, causing standard fusion models to maximize accuracy by ignoring minority emotions entirely.