Research map / Video / Video segmentation and tracking
Modeling Spatiotemporal Neural Frames for High Resolution Brain Dynamic
Wanying Qu, Jianxiong Gao, Wei Wang, Yanwei Fu
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 null-space sampling at inference (ablation) | EEG-conditioned diffusion transformer · InterRecon (subject 1) | MSE: 0.272 -> 0.250 | Improved |
| add null-space sampling at inference (ablation) | EEG-conditioned diffusion transformer · InterRecon (subject 1) | Pearson r: 0.839 -> 0.852 | Improved |
| add null-space sampling at inference (ablation) | EEG-conditioned diffusion transformer · InterRecon (subject 1) | cosine similarity: 0.852 -> 0.865 | Improved |
| use diffusion model without null space instead of linear interpolation (ablation) | InterRecon · subject 1 | MSE: 0.280 -> 0.272 | Improved |
| use full model instead of linear interpolation | InterRecon · subject 1 | MSE: 0.280 -> 0.250 | Improved |
| extend window from 3 to 30 frames: proposed model (ablation) | EEG-to-fMRI diffusion transformer · whole brain | Pearson r: 0.822 -> 0.819 | No clear effect |
| extend window from 3 to 30 frames: E2FGAN baseline (ablation) | E2FGAN · whole brain | MSE: 0.280 -> 0.314 | Hurt |
| use diffusion transformer instead of E2FGAN, 3-frame | E2FGAN · whole brain | MSE: 0.280 vs 0.282 | No clear effect |
| use diffusion transformer instead of E2FGAN, 30-frame | E2FGAN · whole brain | MSE: 0.314 -> 0.281 | Improved |
| use diffusion transformer instead of E2FGAN | E2FGAN · visual cortex 10-frame | Pearson r: 0.836 -> 0.834 | Hurt |
| use diffusion transformer instead of E2FGAN | E2FGAN · visual+audio cortex 10-frame | MSE: 0.188 -> 0.197 | Hurt |
Closest papers by meaning
- NeuroBOLT: Resting-state EEG-to-fMRI Synthesis with Multi-dimensional Feature Mapping (NeurIPS 2024 · similarity 0.88)
- FAST-Brain: A Flow-Aligned Spatio-Temporal Surrogate Brain Model (NeurIPS 2026 · similarity 0.87)
- Brain-OF: An Omnifunctional Foundation Model for fMRI, EEG and MEG (NeurIPS 2026 · similarity 0.87)
- BrainVista: Modeling Naturalistic Brain Dynamics as Multimodal Next-Token Prediction (NeurIPS 2026 · similarity 0.87)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.87)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · 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.
