DAGF: a disentangled adaptive gating fusion network for multimodal sentiment analysis

Reliability-aware disentangled adaptive network for multimodal sentiment analysis

A novel reliability-aware disentangled adaptive network that consists of three components, dynamically modulating per-modality contributions by information quality to mitigate misleading effects of unreliable modalities is proposed.

Cross-modal consistency gating for reliable LLM reasoning in multimodal sentiment analysis

I$^2$-KAN: Interpretable Intra- and Inter-Modal Multi-Pathway Representation Learning for Multimodal Sentiment Analysis

Multimodal sentiment analysis (MSA) aims to infer sentiment by integrating linguistic, acoustic, and visual information. However, many fusion methods integrate modality-specific representations and cross-modal interactions into joint representations, making it difficult to determine whether predictive utility arises fr...

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

DiMoE is proposed, a representation-first framework that integrates feature disentanglement with sparse Mixture of Experts (MoE) fusion, indicating that explicit modality disentanglement combined with Mixture of Experts fusion yields effective multimodal affective representations.

Dynamic graph interaction for feature-augmented multimodal sentiment analysis

GEMA-M2SF: adaptive noise-aware fusion for multimodal aspect-based sentiment analysis