Research map / Vision-language and multimodal / Cross-modal learning
M3ER: Multiplicative Multimodal Emotion Recognition using Facial, Textual, and Speech Cues
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use M3ER's modified multiplicative fusion loss instead of the original loss (ablation) | M3ER · IEMOCAP, no ineffectual modalities | F1: 0.751 -> 0.824 | Helped |
| Use M3ER's modified multiplicative fusion loss instead of the original loss (ablation) | M3ER · CMU-MOSEI, no ineffectual modalities | F1: 0.878 -> 0.902 | Helped |
| Add a modality check step (ablation) | M3ER with corrupted or missing modalities · IEMOCAP | F1: 0.706 -> 0.741 | Helped |
| Add a modality check step (ablation) | M3ER with corrupted or missing modalities · CMU-MOSEI | F1: 0.764 -> 0.783 | Helped |
| Add proxy feature generation for filtered modalities (ablation) | M3ER with corrupted or missing modalities · IEMOCAP | F1: 0.741 -> 0.761 | Helped |
| Add proxy feature generation for filtered modalities (ablation) | M3ER with corrupted or missing modalities · CMU-MOSEI | F1: 0.783 -> 0.856 | Helped |
| Add modality checking and proxy feature generation (ablation) | M3ER · IEMOCAP with ineffectual modalities | mean accuracy: 71.6% -> 78.2% | Helped |
| Add modality checking and proxy feature generation (ablation) | M3ER · CMU-MOSEI with ineffectual modalities | mean accuracy: 75.6% -> 85.0% | Helped |
Closest papers by meaning
- Multi-to-Single: Reducing Multimodal Dependency in Emotion Recognition Through Contrastive Learning (AAAI 2025 · similarity 0.90)
- EMOE: Modality-Specific Enhanced Dynamic Emotion Experts (CVPR 2025 · similarity 0.89)
- Emotion-LLaMA: Multimodal Emotion Recognition and Reasoning with Instruction Tuning (NeurIPS 2024 · similarity 0.89)
- AffectGPT: A New Dataset, Model, and Benchmark for Emotion Understanding with Multimodal Large Language Models (ICML 2025 · similarity 0.88)
- OV-MER: Towards Open-Vocabulary Multimodal Emotion Recognition (ICML 2025 · similarity 0.87)
- CARAT: Contrastive Feature Reconstruction and Aggregation for Multi-Modal Multi-Label Emotion Recognition (AAAI 2024 · similarity 0.87)
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.