Research map / Video / Video segmentation and tracking
Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling
Xuesong Niu, Zitong Yu, Hu Han, Xiaobai Li, Shiguang Shan, Guoying Zhao
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 rPPG-signal supervision (multi-task) to HR-only training (ablation) | MSTmap network · VIPL-HR (5-fold, average HR) | MAE (bpm): 6.39 -> 5.55 | Improved |
| add rPPG-signal supervision (multi-task) to HR-only training (ablation) | MSTmap network · VIPL-HR (5-fold, average HR) | RMSE (bpm): 10.24 -> 9.03 | Improved |
| add cross-verified disentangling (CVD) (ablation) | MSTmap+MTL · VIPL-HR (5-fold, average HR) | RMSE (bpm): 9.03 -> 7.97 | Improved |
| add cross-verified disentangling (CVD) (ablation) | MSTmap+MTL · VIPL-HR (5-fold, average HR) | MAE (bpm): 5.55 -> 5.02 | Improved |
| add cross-verified disentangling (CVD) (ablation) | STmap+MTL · VIPL-HR (5-fold, average HR) | RMSE (bpm): 9.01 -> 8.51 | Improved |
| use MSTmap instead of STmap input (ablation) | MTL without CVD · VIPL-HR (5-fold, average HR) | MAE (bpm): 5.80 -> 5.55 | Improved |
| use MSTmap instead of STmap input (ablation) | MTL with CVD · VIPL-HR (5-fold, average HR) | RMSE (bpm): 8.51 -> 7.97 | Improved |
| add pre-defined head movement signal disentanglement (ablation) | MSTmap+MTL · VIPL-HR (5-fold, average HR) | RMSE (bpm): 9.03 -> 8.96 | Improved |
| add pre-defined face pixel std signal disentanglement (ablation) | MSTmap+MTL · VIPL-HR (5-fold, average HR) | RMSE (bpm): 9.03 -> 8.72 | Improved |
| use CVD instead of pre-defined non-physiological signals (ablation) | MSTmap+MTL · VIPL-HR (5-fold, average HR) | RMSE (bpm): 8.72 -> 7.97 | Improved |
| use proposed method instead of RhythmNet | RhythmNet · VIPL-HR (5-fold, average HR) | RMSE (bpm): 8.14 -> 7.97 | Improved |
| use proposed method instead of RhythmNet in large head movement scenario | RhythmNet · VIPL-HR (large head movement) | RMSE (bpm): 9.4 -> 7.44 | Improved |
Closest papers by meaning
- Facial Video-based Remote Physiological Measurement via Self-supervised Learning (TPAMI 2023 · similarity 0.92)
- Contrast-Phys+: Unsupervised and Weakly-Supervised Video-Based Remote Physiological Measurement via Spatiotemporal Contrast (TPAMI 2024 · similarity 0.90)
- Align the GAP: Prior-Based Unified Multi-task Remote Physiological Measurement Framework For Domain Generalization and Personalization (IJCV 2026 · similarity 0.90)
- RhythmMamba: Fast, Lightweight, and Accurate Remote Physiological Measurement (AAAI 2025 · similarity 0.88)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 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.
