# Promoting Generalization in Cross-Dataset Remote Photoplethysmography

arXiv: https://arxiv.org/abs/2305.15199 · HTML: https://mlsanity.com/paper/2305.15199/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 22 references that are in the map.
- First posted on arXiv 24 May 2023.

## Builds on (most cited first, 8 of 8)

- [MediaPipe: A Framework for Building Perception Pipelines](https://mlsanity.com/paper/1906.08172/) (2019)
- [DeepPhys: Video-Based Physiological Measurement Using Convolutional Attention Networks](https://mlsanity.com/paper/1805.07888/) (2018)
- [Multi-Task Temporal Shift Attention Networks for On-Device Contactless Vitals Measurement](https://mlsanity.com/paper/2006.03790/) (2020)
- [Remote Photoplethysmograph Signal Measurement from Facial Videos Using Spatio-Temporal Networks](https://mlsanity.com/paper/1905.02419/) (2019)
- [DeepRhythm: Exposing DeepFakes with Attentional Visual Heartbeat Rhythms](https://mlsanity.com/paper/2006.07634/) (2020)
- [PulseGAN: Learning to generate realistic pulse waveforms in remote photoplethysmography](https://mlsanity.com/paper/2006.02699/) (2020)
- [Deception Detection and Remote Physiological Monitoring: A Dataset and Baseline Experimental Results](https://mlsanity.com/paper/2106.06583/) (2021)
- [Remote Photoplethysmography: Rarely Considered Factors](https://mlsanity.com/paper/2004.12695/) (2020)

## Built on by (most cited first, 2 of 2)

- [Measuring Domain Shifts using Deep Learning Remote Photoplethysmography Model Similarity](https://mlsanity.com/paper/2404.08184/) (2024)
- [Refining Remote Photoplethysmography Architectures using CKA and Empirical Methods](https://mlsanity.com/paper/2401.04801/) (2024)

## Abstract (arXiv)

Remote Photoplethysmography (rPPG), or the remote monitoring of a subject's heart rate using a camera, has seen a shift from handcrafted techniques to deep learning models. While current solutions offer substantial performance gains, we show that these models tend to learn a bias to pulse wave features inherent to the training dataset. We develop augmentations to mitigate this learned bias by expanding both the range and variability of heart rates that the model sees while training, resulting in improved model convergence when training and cross-dataset generalization at test time. Through a 3-way cross dataset analysis we demonstrate a reduction in mean absolute error from over 13 beats per minute to below 3 beats per minute. We compare our method with other recent rPPG systems, finding similar performance under a variety of evaluation parameters.