Research map / Vision-language and multimodal / Cross-modal learning
MIDAS: Mutual Information Disentanglement With Uncertainty-Aware Fusion for Incomplete Multimodal Sentiment Analysis
Yuhua Wen, Yingying Zhou, Qifei Li, Yingming Gao, Zhengqi Wen, Jianhua Tao, Ya Wen Li
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| add MI minimax objective to variational modeling (ablation) | MIDAS (VM) · MOSI | Acc-2: 70.98 -> 71.50 | Improved |
| add uncertainty-aware fusion to variational modeling (ablation) | MIDAS (VM) · MOSI | Acc-2: 70.98 -> 71.31 | Improved |
| add uncertainty-aware fusion on top of VM+MIM (full model) (ablation) | MIDAS (VM+MIM) · MOSI | Acc-2: 71.50 -> 71.88 | Improved |
| add MI minimax to variational modeling (ablation) | MIDAS (VM) · CH-SIMS | Acc-2: 72.45 -> 73.29 | Improved |
| add uncertainty-aware fusion to variational modeling (ablation) | MIDAS (VM) · CH-SIMS | Acc-2: 72.45 -> 72.72 | No clear effect |
| add disentanglement loss (ablation) | MIDAS · MOSI | Acc-2: 70.59 -> 71.88 | Improved |
| add alignment loss (ablation) | MIDAS · MOSI | Acc-2: 70.84 -> 71.88 | Improved |
| add prediction loss (ablation) | MIDAS · MOSI | Acc-2: 61.96 -> 71.88 | Improved |
| add reconstruction loss (ablation) | MIDAS · MOSI | Acc-2: 71.15 -> 71.88 | Improved |
| add disentanglement loss (ablation) | MIDAS · CH-SIMS | F1: 67.06 -> 72.15 | Improved |
| add prediction loss (ablation) | MIDAS · CH-SIMS | F1: 66.09 -> 72.15 | Improved |
| add alignment loss (ablation) | MIDAS · CH-SIMS | Acc-3: 58.17 -> 57.72 | Hurt |
Closest papers by meaning
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.91)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.90)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.90)
- Correlation-Decoupled Knowledge Distillation for Multimodal Sentiment Analysis with Incomplete Modalities (CVPR 2024 · similarity 0.90)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.90)
- A Multi-Focus-Driven Multi-Branch Network for Robust Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.89)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
