Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning
Cross-Subject Modeling for Widefield Calcium Imaging via Atlas-Aligned Spatiotemporal Tokenization
Mohammad Hosseini, Eray Erturk, Saba Hashemi, Maryam M. Shanechi
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 global spatial embeddings (ablation) | WiCAT (linear probing) · Musall zero-shot | R2: 0.1985 -> 0.3274 | Improved |
| add global spatial embeddings (ablation) | WiCAT (linear probing) · Kondo zero-shot | R2: 0.1316 -> 0.1840 | Improved |
| use shared parameters instead of session-specific parameters (ablation) | WiCAT (linear probing) · Musall zero-shot | R2: 0.1025 -> 0.3274 | Improved |
| use shared parameters instead of session-specific parameters (ablation) | WiCAT (linear probing) · Kondo zero-shot | R2: 0.0301 -> 0.1840 | Improved |
| add self-supervised multi-subject pretraining (ablation) | WiCAT · Musall zero-shot | R2: 0.0936 -> 0.3274 | Improved |
| add self-supervised multi-subject pretraining (ablation) | WiCAT · Kondo zero-shot | R2: 0.0985 -> 0.1840 | Improved |
| use masked autoencoding instead of JEPA pretraining (ablation) | WiCAT · Musall zero-shot | R2: 0.2604 -> 0.3274 | Improved |
| use masked autoencoding instead of JEPA pretraining (ablation) | WiCAT · Musall finetune set | R2: 0.4980 -> 0.5124 | Improved |
| pretrain on multiple subjects instead of single session (ablation) | WiCAT · Musall zero-shot | R2: 0.1249 -> 0.3274 | Improved |
| replace linear decoder with Kalman smoother on frozen embeddings | WiCAT · Kondo zero-shot | R2: 0.1840 -> 0.2869 | Improved |
| replace linear decoder with Kalman smoother on frozen embeddings | WiCAT · Musall zero-shot | R2: 0.3274 -> 0.4336 | Improved |
| full finetuning of backbone instead of linear probing | WiCAT · Kondo zero-shot | R2: 0.1840 -> 0.2398 | Improved |
Closest papers by meaning
- Dynamical Modeling of Behaviorally Relevant Spatiotemporal Patterns in Neural Imaging Data (ICML 2025 · similarity 0.87)
- SIM: Surface-based fMRI Analysis for Inter-Subject Multimodal Decoding from Movie-Watching Experiments (ICLR 2025 · similarity 0.86)
- BaRISTA: Brain Scale Informed Spatiotemporal Representation of Human Intracranial Neural Activity (NeurIPS 2025 · similarity 0.86)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.86)
- Leveraging unlabelled data for generalizable neural population decoding (NeurIPS 2026 · similarity 0.85)
- Dynamical modeling of nonlinear latent factors in multiscale neural activity with real-time inference (NeurIPS 2025 · similarity 0.85)
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.
