Research map / Label-efficient and robust learning / Recognition and long-tail
Self-Adaptive Matrix Completion for Heart Rate Estimation From Face Videos Under Realistic Conditions
Check 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 |
|---|---|---|---|
| use self-adaptive matrix completion instead of De Haan et al. | Heart-rate estimation from face video · MAHNOB-HCI | RMSE: 6.52 -> 6.23 | Helped |
| use self-adaptive matrix completion instead of De Haan et al. | Heart-rate estimation from face video · MMSE-HR | RMSE: 13.97 -> 11.37 | Helped |
| use self-adaptive matrix completion instead of De Haan et al. | Heart-rate estimation from face video · MMSE-HR | Pearson correlation: 0.55 -> 0.71 | Helped |
| use SAMC instead of De Haan et al. for short-window estimation | Heart-rate estimation from face video · MMSE-HR, 4-second windows | RMSE: 15.83 -> 11.66 | Helped |
| use SAMC instead of De Haan et al. for short-window estimation | Heart-rate estimation from face video · MMSE-HR, 6-second windows | RMSE: 19.27 -> 8.27 | Helped |
| use SAMC instead of De Haan et al. for short-window estimation | Heart-rate estimation from face video · MMSE-HR, 8-second windows | RMSE: 11.46 -> 9.76 | Helped |
| add self-adaptation to the mask rather than keeping it fixed (ablation) | Matrix completion for HR estimation · MMSE-HR, p=20 | RMSE: 65.99 -> 12.13 | Helped |
| add self-adaptation to the mask rather than keeping it fixed (ablation) | Matrix completion for HR estimation · MMSE-HR, p=40 | RMSE: 51.47 -> 12.23 | Helped |
| add self-adaptation to the mask rather than keeping it fixed (ablation) | Matrix completion for HR estimation · MMSE-HR, p=60 | RMSE: 37.06 -> 12.23 | Helped |
| add self-adaptation to the mask rather than keeping it fixed (ablation) | Matrix completion for HR estimation · MMSE-HR, p=80 | RMSE: 14.63 -> 12.23 | Helped |
| add self-adaptation to the mask rather than keeping it fixed (ablation) | Matrix completion for HR estimation · MMSE-HR, p=100 | RMSE: 15.13 -> 12.23 | Helped |
| vary the initialization percentile of the self-adaptive mask from p=20 to p=40-100 (ablation) | SAMC · MMSE-HR | RMSE: 12.13 -> 12.23 | No clear effect |
Closest papers by meaning
- FacePhys: State of the Heart Learning (NeurIPS 2026 · similarity 0.86)
- PhysDiff: Physiology-based Dynamicity Disentangled Diffusion Model for Remote Physiological Measurement (AAAI 2025 · similarity 0.84)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.84)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.83)
- FactorizePhys: Matrix Factorization for Multidimensional Attention in Remote Physiological Sensing (NeurIPS 2024 · similarity 0.83)
- WildPPG: A Real-World PPG Dataset of Long Continuous Recordings (NeurIPS 2024 · similarity 0.82)
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.