Research map / Vision-language and multimodal / Cross-modal learning
A Multimodal EEG-Eye Movement Model for Automatic Depression Detection
Hao-Long Yin, Jian-Ming Zhang, Ren-Jie Dai, Wei-Long Zheng, Qinyu Lv, Zhenghui Yi, Bao-Liang Lu
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 eye movements to EEG (multimodal fusion) | E2Mo · Depression detection | balanced accuracy (%): 62.96 -> 70.06 | Improved |
| add frequency reconstruction to EEG tokenizer (ablation) | E2Mo · Depression detection, EEG only | balanced accuracy (%): 60.45 -> 62.96 | Improved |
| add temporal reconstruction to EEG tokenizer (ablation) | E2Mo · Depression detection, EEG only | balanced accuracy (%): 62.22 -> 62.96 | Improved |
| add spectral encoder to EEG encoder (ablation) | E2Mo · Depression detection, EEG only | balanced accuracy (%): 60.22 -> 62.96 | Improved |
| add hand-crafted feature reconstruction to EYE tokenizer (ablation) | E2Mo · Depression detection, eye movement only | balanced accuracy (%): 64.05 -> 64.10 | No clear effect |
| add gaze velocity encoder (ablation) | E2Mo · Depression detection, eye movement only | balanced accuracy (%): 63.97 -> 64.10 | No clear effect |
| add EEG-EYE matching pretraining task (ablation) | E2Mo · Depression detection, multimodal EEG+eye | balanced accuracy (%): 68.71 -> 70.06 | Improved |
| add masked EEG-EYE modeling pretraining task (ablation) | E2Mo · Depression detection, multimodal EEG+eye | balanced accuracy (%): 66.18 -> 70.06 | Improved |
| add contrastive learning to masked modeling only (ablation) | E2Mo · Depression detection, multimodal EEG+eye | balanced accuracy (%): 68.34 -> 68.71 (with EEC); 70.06 with EEM | Improved |
Closest papers by meaning
- DMMR: Cross-Subject Domain Generalization for EEG-Based Emotion Recognition via Denoising Mixed Mutual Reconstruction (AAAI 2024 · similarity 0.86)
- What do EEG Foundation Models Capture from Human Brain Signals? (NeurIPS 2026 · similarity 0.85)
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces (NeurIPS 2026 · similarity 0.85)
- EEG2Video: Towards Decoding Dynamic Visual Perception from EEG Signals (NeurIPS 2024 · similarity 0.84)
- Multi-dataset Joint Pre-training of Emotional EEG Enables Generalizable Affective Computing (NeurIPS 2025 · similarity 0.84)
- FEEL: Quantifying Heterogeneity in Physiological Signals for Generalizable Emotion Recognition (NeurIPS 2025 · 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.
