Research map / Vision-language and multimodal / Human and embodied modeling
ViEEG: Hierarchical Visual Neural Representation for EEG Brain Decoding
Minxu Liu, Donghai Guan, Chuhang Zheng, Chunwei Tian, Jie Wen, Qi Zhu
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-attention hierarchical integration across the three EEG streams (ablation) | ViEEG · THINGS-EEG subject-dependent top-1 | top-1 accuracy (%): 38.6 -> 40.9 | Improved |
| add cross-attention hierarchical integration across the three EEG streams (ablation) | ViEEG · THINGS-EEG subject-independent top-1 | top-1 accuracy (%): 20.7 -> 22.9 | Improved |
| fuse contour, object and scene EEG embeddings instead of contour only (ablation) | ViEEG · THINGS-EEG subject-dependent top-1 | top-1 accuracy (%): 14.8 -> 40.9 | Improved |
| use object or scene embedding alone instead of the contour embedding alone (ablation) | ViEEG · THINGS-EEG subject-dependent top-1 | top-1 accuracy (%): 14.8 -> 28.9 (object), 28.6 (scene) | Improved |
| use contour->object->context order rather than other permutations (ablation) | ViEEG · THINGS-EEG subject-dependent top-1 | top-1 accuracy (%): best alternative 40.3 -> 40.9 | Improved |
| use ViEEG hierarchical encoder instead of NICE or ATM encoders (ablation) | ViEEG · THINGS-EEG subject-dependent top-1 | top-1 accuracy (%): 37.8 (NICE) / 37.6 (ATM) -> 40.9 | Improved |
| use one cross-attention layer instead of none or deeper stacks (ablation) | ViEEG · THINGS-EEG | top-1 accuracy | Improved |
| use 3 attention heads instead of other head counts (ablation) | ViEEG · THINGS-EEG subject-dependent | top-1 accuracy | Improved |
| concatenate mask, object and scene embeddings (triple) instead of a single embedding for retrieval (ablation) | ViEEG · THINGS-EEG zero-shot retrieval (Subject 8) | retrieval accuracy | Improved |
| replace NICE/ATM/CognitionCapturer with ViEEG for reconstruction | SDXL-Turbo + IP-Adapter · THINGS-EEG reconstruction | CLIP similarity: 0.792 (ATM) -> 0.798 | Improved |
| add hierarchical decomposition, at cost of more parameters and compute | ViEEG vs NICE · THINGS-EEG | parameters / FLOPs: 2630.940 K -> 7924.488 K params; 42.7354 M -> 127.973 M FLOPs | Hurt |
Closest papers by meaning
- What Does the Brain See? Multiview Neural Representation to Demystify the Brain-Visual Alignment (NeurIPS 2026 · similarity 0.91)
- MindAlign: Bridging EEG, Vision, and Language for Zero-Shot Visual Decoding (NeurIPS 2026 · similarity 0.90)
- Visual Decoding and Reconstruction via EEG Embeddings with Guided Diffusion (NeurIPS 2024 · similarity 0.90)
- Decoding Natural Images from EEG for Object Recognition (ICLR 2024 · similarity 0.90)
- Brain decoding: toward real-time reconstruction of visual perception (ICLR 2024 · similarity 0.89)
- Neuro-3D: Towards 3D Visual Decoding from EEG Signals (CVPR 2025 · similarity 0.88)
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.
