A cue-coverage reward plus a modality-token KL penalty makes multimodal emotion-reasoning models cite more real visual/audio evidence and hallucinate less, with reported SoTA on emotion benchmarks.
arXiv preprint arXiv:2404.17205 , year=
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2representative citing papers
Controlled study finds CLIP-based body-scene fusion model for emotion recognition on EMOTIC is not improved by context debiasing or rare-class training, with best mAP of 34.52%.
citing papers explorer
-
Omni-Perception Policy Optimization for Multimodal Emotion Reasoning
A cue-coverage reward plus a modality-token KL penalty makes multimodal emotion-reasoning models cite more real visual/audio evidence and hallucinate less, with reported SoTA on emotion benchmarks.
-
A Controlled Study of CLIP-Based Body-Scene Fusion for Emotion Recognition in Context
Controlled study finds CLIP-based body-scene fusion model for emotion recognition on EMOTIC is not improved by context debiasing or rare-class training, with best mAP of 34.52%.