M. S. Sran

DiMoE: Disentangled Representation Learning with Mixture of Experts Fusion for Sentiment Intensity Prediction and Emotion Classification

Multimodal affective analysis benefits from combining textual, acoustic, and visual cues, yet many methods implicitly mix modality-invariant information with modality-specific factors, which can reduce robustness when modalities vary in reliability. We propose DiMoE, a representation-first framework that integrates fea...