Research map / Vision-language and multimodal / Cross-modal learning
Cross-modal Prompting for Balanced Incomplete Multi-modal Emotion Recognition
Wen-Jue He, Xiaofeng Zhu, Zheng Zhang
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 cross-modal knowledge propagation (KP) to concatenation baseline (ablation) | ComP · CMU-MOSI (missing rate 0.7) | accuracy (%): 68.75 -> 70.88 | Improved |
| add KP to concatenation baseline (ablation) | ComP · IEMOCAPFour (missing rate 0.7) | accuracy (%): 57.85 -> 71.83 | Improved |
| add prompt generation (PG) on top of KP (ablation) | ComP · CMU-MOSI (missing rate 0.7) | accuracy (%): 70.88 -> 71.65 | Improved |
| add PG on top of KP (ablation) | ComP · IEMOCAPFour (missing rate 0.7) | accuracy (%): 71.83 -> 72.99 | Improved |
| add coordinator (Cr) on top of KP+PG (ablation) | ComP · CMU-MOSI (missing rate 0.7) | accuracy (%): 71.65 -> 71.80 | No clear effect |
| add coordinator (Cr) on top of KP+PG (ablation) | ComP · IEMOCAPFour (missing rate 0.7) | accuracy (%): 72.99 -> 73.03 | No clear effect |
| add gradient modulation (GM) on top of KP+PG+Cr (ablation) | ComP · CMU-MOSI (missing rate 0.7) | accuracy (%): 71.80 -> 73.17 | Improved |
| add GM on top of KP+PG+Cr (ablation) | ComP · IEMOCAPFour (missing rate 0.7) | accuracy (%): 73.03 -> 73.41 | Improved |
| add KP when PG, Cr, GM present (ablation) | ComP · CMU-MOSI (missing rate 0.7) | accuracy (%): 69.97 -> 73.17 | Improved |
| add KP when PG, Cr, GM present (ablation) | ComP · IEMOCAPFour (missing rate 0.7) | accuracy (%): 57.36 -> 73.41 | Improved |
| ComP vs best baseline on IEMOCAPSix at MR 0.4 (UA) | ComP · IEMOCAPSix (missing rate 0.4) | UA (%): 56.22 vs 56.71 (SDR-GNN) | Mixed |
| ComP vs MoMKE on CMU-MOSEI at MR 0.1 (ACC) | ComP · CMU-MOSEI (missing rate 0.1) | accuracy (%): 85.88 -> 86.60 | Improved |
Closest papers by meaning
- EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025 · similarity 0.89)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.87)
- MODA: MOdular Duplex Attention for Multimodal Perception, Cognition, and Emotion Understanding (ICML 2025 · similarity 0.86)
- CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition (AAAI 2024 · similarity 0.85)
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data (ICLR 2024 · similarity 0.85)
- A Unified Self-Distillation Framework for Multimodal Sentiment Analysis with Uncertain Missing Modalities (AAAI 2024 · similarity 0.85)
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.
