An end-to-end spatial-temporal transformer with illumination augmentation, Residual Temporal Standardization Module, and hybrid waveform-spectral loss achieves 0.79 bpm MAE and 0.982 correlation on a new varied-illumination dataset, outperforming PhysFormer by 93.6% in MAE.
Ro- bust and generalizable heart rate estimation via deep learning for remote photoplethysmography in complex scenarios.arXiv preprint, 2025
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Illumination-Robust Camera-Based Heart-Rate Estimation for Physiological Sensing in Robots
An end-to-end spatial-temporal transformer with illumination augmentation, Residual Temporal Standardization Module, and hybrid waveform-spectral loss achieves 0.79 bpm MAE and 0.982 correlation on a new varied-illumination dataset, outperforming PhysFormer by 93.6% in MAE.