Research map / Vision-language and multimodal / Cross-modal learning
A Text-Routed Sparse Mixture-of-Experts Model with Explanation and Temporal Alignment for Multi-Modal Sentiment Analysis
Dongning Rao, Yunbiao Zeng, Zhihua Jiang, Jujian Lv
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 |
|---|---|---|---|
| remove MLLM-generated explanations (ablation) | TEXT · MOSEI | MAE: 0.569 -> 0.528 | Improved |
| replace temporal alignment block with concatenation (ablation) | TEXT · MOSEI | MAE: 0.580 -> 0.528 | Improved |
| use proposed temporal alignment instead of Mamba (ablation) | TEXT · MOSEI | MAE: 0.562 -> 0.528 | Improved |
| use proposed temporal alignment instead of TCA (ablation) | TEXT · MOSEI | MAE: 0.565 -> 0.528 | Improved |
| use text-routed SMoE instead of Transformer (ablation) | TEXT · MOSEI | MAE: 0.573 -> 0.528 | Improved |
| add gate fusion (ablation) | TEXT · MOSEI | MAE: 0.571 -> 0.528 | Improved |
| add explanation alignment instead of linear layer (ablation) | TEXT · MOSEI | Acc-7: 48.21 -> 52.29 | Improved |
| fuse text with audio and video rather than text alone (ablation) | TEXT · MOSEI | Acc-7: 52.84 -> 52.29 | No clear effect |
| TEXT versus KuDA on fine-grained accuracy | TEXT · MOSI | Acc-7: 47.08 -> 45.92 | Hurt |
| TEXT versus strongest baselines on MAE | TEXT · CH-SIMS | MAE: 0.408 -> 0.353 | Improved |
Closest papers by meaning
- MSE-Adapter: A Lightweight Plugin Endowing LLMs with the Capability to Perform Multimodal Sentiment Analysis and Emotion Recognition (AAAI 2025 · similarity 0.85)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.85)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.85)
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.84)
- MSAmba: Exploring Multimodal Sentiment Analysis with State Space Models (AAAI 2025 · similarity 0.84)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.84)
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.
