Research map / Probabilistic and scientific modeling / Molecules and proteins
Neuron Structure Modeling for Generalizable Remote Physiological Measurement
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 |
|---|---|---|---|
| Add NEST regularization to the RhythmNet baseline | RhythmNet · MSDG across UBFC, PURE, BUAA, VIPL, and V4V | HR MAE: UBFC 5.79 -> 4.67; PURE 7.39 -> 6.71; BUAA 3.38 -> 2.88; VIPL 8.97 -> 7.86; V4V 10.16 -> 9.27 | Helped |
| Add NEST regularization to the baseline | RhythmNet baseline · PURE and BUAA (SSDG; trained on UBFC) | HR MAE: PURE 7.54 -> 6.07; BUAA 2.97 -> 2.56 | Helped |
| Add NEST regularization to the baseline | RhythmNet baseline · VIPL-HR (5-fold cross-validation) | HR MAE: 5.21 -> 4.76 | Helped |
| Add NEST-CM (ablation) | NEST · MSDG; UBFC, PURE, BUAA, VIPL, and V4V | HR MAE: UBFC 4.92 -> 4.67; PURE 6.91 -> 6.71; BUAA 2.79 -> 2.88; VIPL 8.21 -> 7.86; V4V 9.58 -> 9.27 | Mixed |
| Add NEST-TA (ablation) | NEST · MSDG; UBFC, PURE, BUAA, VIPL, and V4V | HR MAE: UBFC 4.97 -> 4.67; PURE 6.81 -> 6.71; BUAA 3.03 -> 2.88; VIPL 8.19 -> 7.86; V4V 9.52 -> 9.27 | Helped |
| Add NEST-DM (ablation) | NEST · MSDG; UBFC, PURE, BUAA, VIPL, and V4V | HR MAE: UBFC 4.89 -> 4.67; PURE 6.87 -> 6.71; BUAA 2.93 -> 2.88; VIPL 8.14 -> 7.86; V4V 9.49 -> 9.27 | Helped |
| Set NEST-CM strength to rho=0.1 (ablation) | NEST-CM · MSDG, tested on UBFC | RMSE | Helped |
| Use sigma=5 to fuse neighboring samples into the NEST-TA prototype (ablation) | NEST-TA · MSDG, tested on UBFC | performance | Helped |
| Use the smallest tau for NEST-DM (ablation) | NEST-DM · MSDG | discriminant ability | Hurt |
Closest papers by meaning
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.79)
- NeurIPT: Foundation Model for Neural Interfaces (NeurIPS 2025 · similarity 0.78)
- BrainOmni: A Brain Foundation Model for Unified EEG and MEG Signals (NeurIPS 2025 · similarity 0.77)
- CSBrain: A Cross-scale Spatiotemporal Brain Foundation Model for EEG Decoding (NeurIPS 2025 · similarity 0.77)
- Neuroformer: Multimodal and Multitask Generative Pretraining for Brain Data (ICLR 2024 · similarity 0.77)
- NeuroAtlas: Benchmarking Foundation Models for Clinical EEG and Brain-Computer Interfaces (NeurIPS 2026 · similarity 0.77)
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.