Research map / Video / Video segmentation and tracking
The Way to My Heart Is Through Contrastive Learning: Remote Photoplethysmography From Unlabelled Video
John Gideon, Simon Stent
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 saliency sampler (ablation) | Our Contrastive · COHFACE | RMSE: 4.6 -> 5.5 | Hurt |
| add saliency sampler (ablation) | Our Contrastive · UBFC | RMSE: 4.6 -> 6.1 | Hurt |
| add saliency sampler (ablation) | Our Contrastive · MR-NIRP-Car | RMSE: 4.1 -> 5.2 | Hurt |
| add saliency sampler (ablation) | Our Contrastive · PURE | RMSE: 2.9 -> 3.0 | No clear effect |
| add saliency sampler (ablation) | Our Supervised · COHFACE | RMSE: 7.8 -> 7.6 | No clear effect |
| add saliency sampler (ablation) | Our Supervised · MR-NIRP-Car | RMSE: 1.6 -> 1.8 | No clear effect |
| add saliency sampler (ablation) | Our Supervised · UBFC | RMSE: 4.9 -> 5.0 | No clear effect |
| train contrastively without labels instead of supervised | PhysNet-style 3D-CNN · COHFACE | RMSE: 7.8 -> 4.6 | Improved |
| train contrastively without labels instead of supervised | PhysNet-style 3D-CNN · UBFC | RMSE: 4.9 -> 4.6 | Improved |
| train contrastively without labels instead of supervised | PhysNet-style 3D-CNN · MR-NIRP-Car | RMSE: 1.6 -> 4.1 | Hurt |
| use MCC loss instead of Pearson correlation under injected label desynchronization (ablation) | Our Supervised · COHFACE | RMSE | Improved |
| use MCC loss instead of SNR loss (ablation) | Our Supervised · COHFACE | RMSE | Improved |
Closest papers by meaning
- Contrast-Phys+: Unsupervised and Weakly-Supervised Video-Based Remote Physiological Measurement via Spatiotemporal Contrast (TPAMI 2024 · similarity 0.95)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.90)
- FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing (NeurIPS 2024 · similarity 0.89)
- FacePhys: State of the Heart Learning (NeurIPS 2026 · similarity 0.88)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.88)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 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.
