Research map / Vision-language and multimodal / Cross-modal learning
Noise-Resistant Multimodal Transformer for Emotion Recognition
Yuanyuan Liu, Haoyu Zhang, Yibing Zhan, Zijing Chen, Guanghao Yin, Lin Wei, Zhe Chen
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 NRGF extractor (ablation) | NORM-TR · MOSI | Acc-7: 46.8 -> 48.5 | Improved |
| add NRGF extractor (ablation) | NORM-TR · MOSEI | Acc-7: 52.3 -> 54.6 | Improved |
| add MF extractor (ablation) | NORM-TR · MOSI | Acc-7: 48.1 -> 48.5 | Improved |
| add MF extractor (ablation) | NORM-TR · MOSEI | Acc-7: 53.6 -> 54.6 | Improved |
| add multimodal fusion Transformer (ablation) | NORM-TR · MOSI | Acc-7: 45.6 -> 48.5 | Improved |
| add multimodal fusion Transformer (ablation) | NORM-TR · MOSEI | Acc-7: 53.8 -> 54.6 | Improved |
| add noise-aware learning scheme (ablation) | NORM-TR · MOSI | Acc-7: 46.9 -> 48.5 | Improved |
| add noise-aware learning scheme (ablation) | NORM-TR · MOSEI | Acc-7: 53.2 -> 54.6 | Improved |
| add text modality (ablation) | NORM-TR · MOSI | Acc-7: 18.1 -> 48.5 | Improved |
| add audio modality (ablation) | NORM-TR · MOSI | Acc-7: 43.6 -> 48.5 | Improved |
| add video modality (ablation) | NORM-TR · MOSEI | Acc-7: 51.8 -> 54.6 | Improved |
| use NRGFs as query and MFs as key and value instead of the reverse (ablation) | NORM-TR · MOSI | Acc-7: 47.1 -> 48.5 | Improved |
Closest papers by meaning
- M3ER: Multiplicative Multimodal Emotion Recognition using Facial, Textual, and Speech Cues (AAAI 2020 · similarity 0.90)
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.89)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · similarity 0.88)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.88)
- Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning (NeurIPS 2024 · similarity 0.87)
- EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025 · similarity 0.86)
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.
