Research map / Vision-language and multimodal / Cross-modal learning
Enhance-then-Balance Modality Collaboration for Robust Multimodal Sentiment Analysis
Kang He, Yuzhe Ding, Xinrong Wang, Fei Li, Chong Teng, Donghong Ji
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 MSD module (ablation) | EBMC · CMU-MOSI | F1: 84.30/86.16 -> 86.20/87.79 | Improved |
| add MSD module (ablation) | EBMC · CMU-MOSEI | F1: 84.16/86.31 -> 86.23/88.07 | Improved |
| add CCE module (ablation) | EBMC · CMU-MOSI | F1: 84.87/86.90 -> 86.20/87.79 | Improved |
| add CCE module (ablation) | EBMC · CMU-MOSEI | F1: 84.52/86.89 -> 86.23/88.07 | Improved |
| add EMC module (ablation) | EBMC · CMU-MOSI | F1: 83.56/85.32 -> 86.20/87.79 | Improved |
| add EMC module (ablation) | EBMC · CMU-MOSEI | F1: 83.47/85.20 -> 86.23/88.07 | Improved |
| add IMTD module (ablation) | EBMC · CMU-MOSI | F1: 85.24/86.77 -> 86.20/87.79 | Improved |
| add IMTD module (ablation) | EBMC · CMU-MOSEI | F1: 84.96/87.09 -> 86.23/88.07 | Improved |
| add quadratic norm energy term (ablation) | EMC · CMU-MOSEI | Acc-7: 56.62 -> 57.32 | Improved |
| add task-loss energy term (ablation) | EMC · CMU-MOSEI | Acc-7: 55.94 -> 57.32 | Improved |
| add uncertainty energy term (ablation) | EMC · CMU-MOSEI | Acc-7: 56.40 -> 57.32 | Improved |
| EBMC versus LNLN under frame dropping | EBMC · CMU-MOSI (frame-drop robustness) | MAE: 1.046 -> 0.994 | Improved |
Closest papers by meaning
- Toward Robust Incomplete Multimodal Sentiment Analysis via Hierarchical Representation Learning (NeurIPS 2024 · similarity 0.90)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.90)
- EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025 · similarity 0.90)
- DLF: Disentangled-Language-Focused Multimodal Sentiment Analysis (AAAI 2025 · similarity 0.90)
- SemMSA: Latent Semantic-Aided Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2026 · similarity 0.90)
- Towards Robust Multimodal Sentiment Analysis with Incomplete Data (NeurIPS 2024 · 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.
