A new intervention-based SSL paradigm for rPPG uses video editing and falsifiability checks to learn the true physiological signal instead of dominant artifacts.
arXiv preprint arXiv:1905.02419 , year =
5 Pith papers cite this work. Polarity classification is still indexing.
5
Pith papers citing it
fields
cs.CV 5verdicts
UNVERDICTED 5representative citing papers
RhythmJEPA learns pulse-aware representations by joint-embedding prediction on masked videos, using cyclic rhythm-state planning and dual-order Mamba encoding to achieve competitive rPPG performance on standard datasets.
MS-rPPG combines multi-spectral video inputs with a cross-spectral modulation strategy and the MS-Mamba state space model to improve remote heart rate estimation accuracy and robustness on driving datasets.
LQ-rPPG introduces label quantization and coarse-to-fine hierarchical supervision to mitigate noise in contact PPG labels for improved remote photoplethysmography estimation.
DRP-Net extracts phase-shifted rPPG signals from facial and acral regions for heart rate; BBP-Net uses their temporal and phase features plus a bounded sigmoid to estimate SBP/DBP, reporting MAEs of 1.78 BPM / 10.19 mmHg / 7.09 mmHg on MMSE-HR.
citing papers explorer
-
Intervention-Based Self-Supervised Learning: A Causal Probe Paradigm for Remote Photoplethysmography
A new intervention-based SSL paradigm for rPPG uses video editing and falsifiability checks to learn the true physiological signal instead of dominant artifacts.
-
Rhythm-Structured Predictive Learning for Remote Photoplethysmography
RhythmJEPA learns pulse-aware representations by joint-embedding prediction on masked videos, using cyclic rhythm-state planning and dual-order Mamba encoding to achieve competitive rPPG performance on standard datasets.
-
MS-rPPG: Multi-spectral State Space Model for Remote Photoplethysmography in Driver Monitoring Systems
MS-rPPG combines multi-spectral video inputs with a cross-spectral modulation strategy and the MS-Mamba state space model to improve remote heart rate estimation accuracy and robustness on driving datasets.
-
LQ-rPPG: A Label-Quantized Coarse-to-Fine Learning Framework for Remote Physiological Measurement
LQ-rPPG introduces label quantization and coarse-to-fine hierarchical supervision to mitigate noise in contact PPG labels for improved remote photoplethysmography estimation.
-
Phase-shifted remote photoplethysmography for estimating heart rate and blood pressure from facial video
DRP-Net extracts phase-shifted rPPG signals from facial and acral regions for heart rate; BBP-Net uses their temporal and phase features plus a bounded sigmoid to estimate SBP/DBP, reporting MAEs of 1.78 BPM / 10.19 mmHg / 7.09 mmHg on MMSE-HR.