# Cross-Dataset Transfer and Reliability of Explainable Artificial Intelligence for RhythmFormer Remote Photoplethysmography

arXiv: https://arxiv.org/abs/2609.03663 · HTML: https://mlsanity.com/paper/2609.03663/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 81 references that are in the map.
- First posted on arXiv 3 Sep 2026.

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

- [A Reproducible Study on Remote Heart Rate Measurement](https://mlsanity.com/paper/1709.00962/) (2017)
- [PhysFormer++: Facial Video-based Physiological Measurement with SlowFast Temporal Difference Transformer](https://mlsanity.com/paper/2302.03548/) (2023)
- [RhythmFormer: Extracting Patterned rPPG Signals based on Periodic Sparse Attention](https://mlsanity.com/paper/2402.12788/) (2024)
- [A Plug-and-Play Temporal Normalization Module for Robust Remote Photoplethysmography](https://mlsanity.com/paper/2411.15283/) (2024)
- [CodePhys: Robust Video-based Remote Physiological Measurement through Latent Codebook Querying](https://mlsanity.com/paper/2502.07526/) (2025)
- [FreqPhys: Repurposing Implicit Physiological Frequency Prior for Robust Remote Photoplethysmography](https://mlsanity.com/paper/2604.00534/) (2026)
- [Robust and Generalizable Heart Rate Estimation via Deep Learning for Remote Photoplethysmography in Complex Scenarios](https://mlsanity.com/paper/2507.07795/) (2025)
- [KDPhys: An Attention Guided 3D to 2D Knowledge Distillation for Real-time Video-Based Physiological Measurement](https://mlsanity.com/paper/2601.00714/) (2026)

## Abstract (arXiv)

Background. Remote photoplethysmography estimates the cardiovascular pulse from facial video, and its explanations have rested on inspecting heatmaps rather than on quantitative evidence about where a model reads it. We quantified the explanations and asked whether such explanations transfer between datasets and track model performance. Method. We trained eight condition-specific RhythmFormer models on NCKU-rPPG, recorded under three illumination levels, speaking, rotation, and cycling, estimated one heart rate per 5.12-second clip, and set them beside a UBFC-rPPG reproduction. Raw attention, rollout, attention flow, and Beyond Intuition were assessed by skin coverage and the Salience-guided Faithfulness Coefficient (SaCo). Results. Beyond Intuition ranked highest on both datasets, at median coverage 0.789 and SaCo 0.837 on Static level 3 against 0.826 and 0.917 on UBFC-rPPG; lower ranks differed. Within one participant of one condition, neither measure was related to a clip's heart-rate error, waveform correlation, or signal-to-noise ratio on either dataset: 186 of the 252 coefficients fell below |ρ|=0.10 and 28 reached p<0.05 against the 13 expected by chance. Across the eight scenarios only Beyond Intuition's coverage followed the three performance measures, at ρ=-0.43, +0.57, and +0.43, while the attention-only methods' SaCo ran opposite to each. It failed at 40 lux alone, its median coverage falling to 0.180 and its median SaCo to -0.178, whereas motion degraded the estimates far more without such a drop. Conclusions. Skin coverage and SaCo carry information complementary to the performance measures rather than a proxy for them: attributing to the skin does not guarantee an accurate estimate. What an attribution reveals about a condition is where the model looks rather than how faithfully its map is ordered.