Research map / Vision-language and multimodal / Cross-modal learning
FusionPhys: A Flexible Framework for Fusing Complementary Sensing Modalities in Remote Physiological Measurement
Chenhang Ying, Huiyu Yang, Jieyi Ge, Zhaodong Sun, Xu Cheng, Kui Ren, Xiaobai Li
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 near-infrared fusion to visible light | FusionPhys · OBF dark subset | MAE (bpm): 0.324 -> 0.281 | Improved |
| add radar fusion to visible light | FusionPhys · EquiPleth | T-Test gap (%): 4.6 -> 0.08 | Improved |
| add radar fusion to visible light | FusionPhys · EquiPleth | MAE (bpm): 1.49 -> 1.07 | Improved |
| add sub-modality decomposition of video regions | FusionPhys · UBFC-rPPG, PURE, MMSE-HR | MAE (bpm): 0.21 -> 0.15 | Improved |
| use FusionPhys instead of Contrast-Phys+ on OBF | Contrast-Phys+ · OBF | RMSE (bpm): 0.75 -> 1.11 | Hurt |
| increase wavelet decomposition level from 1 to 5 (ablation) | PIB · MMSE-HR | MAE (bpm): 1.26 -> 0.75 | Improved |
| use level 6 instead of level 5 Haar (ablation) | PIB · MMSE-HR | MAE (bpm): 0.75 -> 0.72 | No clear effect |
| change wavelet family Haar to coif1 or db2 (ablation) | PIB · MMSE-HR | MAE (bpm): 0.75 -> 0.86 | No clear effect |
| stack 4 PIB blocks instead of 1 (ablation) | FusionPhys · MMSE-HR | MAE (bpm): 3.63 -> 0.75 | Improved |
| use 64 sub-modalities instead of 4 (ablation) | FusionPhys · MMSE-HR | MAE (bpm): 1.16 -> 0.75 | Improved |
| use 64 sub-modalities instead of 256 (ablation) | FusionPhys · MMSE-HR | MAE (bpm): 1.09 -> 0.75 | Improved |
| use FusionPhys instead of Contrast-Phys+ in cross-dataset test | Contrast-Phys+ · UBFC-rPPG to MMSE-HR | MAE (bpm): 1.76 -> 1.03 | Improved |
Closest papers by meaning
- Fusion-Vital: Video-RF Fusion Transformer for Advanced Remote Physiological Measurement (AAAI 2024 · similarity 0.89)
- RPM-Distill: Physiology-guided Adaptive Cross-modal Distillation for Robust Remote Physiological Measurement (ECCV 2026 · similarity 0.88)
- FacePhys: State of the Heart Learning (NeurIPS 2026 · similarity 0.86)
- Remote Photoplethysmography in Real-World and Extreme Lighting Scenarios (CVPR 2025 · similarity 0.84)
- 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 0.83)
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.
