HOT: Harmonic-Constrained Optimal Transport for Remote Photoplethysmography Domain Adaptation
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866917380082368512 |
|---|---|
| author | Nguyen, Ba-Thinh Ngo, Thi-Duyen Huynh, Thanh-Trung Le, Thanh-Ha Pham, Huy-Hieu |
| author_facet | Nguyen, Ba-Thinh Ngo, Thi-Duyen Huynh, Thanh-Trung Le, Thanh-Ha Pham, Huy-Hieu |
| contents | Remote photoplethysmography (rPPG) enables non-contact physiological measurement from facial videos; however, its practical deployment is often hindered by substantial performance degradation under domain shift. While recent deep learning-based rPPG methods have achieved strong performance on individual datasets, they frequently overfit to appearance-related factors, such as illumination, camera characteristics, and color response, that vary significantly across domains. To address this limitation, we introduce frequency domain adaptation (FDA) as a principled strategy for modeling appearance variation in rPPG. By transferring low-frequency spectral components that encode domain-dependent appearance characteristics, FDA encourages rPPG models to learn invariance to appearance variations while retaining cardiac-induced signals. To further support physiologically consistent alignment under such appearance variation, we propose Harmonic-Constrained Optimal Transport (HOT), which leverages the harmonic property of cardiac signals to guide alignment between original and FDA-transferred representations. Extensive cross-dataset experiments demonstrate that the proposed FDA and HOT framework effectively enhances the robustness and generalization of rPPG models across diverse datasets. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_01675 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | HOT: Harmonic-Constrained Optimal Transport for Remote Photoplethysmography Domain Adaptation Nguyen, Ba-Thinh Ngo, Thi-Duyen Huynh, Thanh-Trung Le, Thanh-Ha Pham, Huy-Hieu Computer Vision and Pattern Recognition Remote photoplethysmography (rPPG) enables non-contact physiological measurement from facial videos; however, its practical deployment is often hindered by substantial performance degradation under domain shift. While recent deep learning-based rPPG methods have achieved strong performance on individual datasets, they frequently overfit to appearance-related factors, such as illumination, camera characteristics, and color response, that vary significantly across domains. To address this limitation, we introduce frequency domain adaptation (FDA) as a principled strategy for modeling appearance variation in rPPG. By transferring low-frequency spectral components that encode domain-dependent appearance characteristics, FDA encourages rPPG models to learn invariance to appearance variations while retaining cardiac-induced signals. To further support physiologically consistent alignment under such appearance variation, we propose Harmonic-Constrained Optimal Transport (HOT), which leverages the harmonic property of cardiac signals to guide alignment between original and FDA-transferred representations. Extensive cross-dataset experiments demonstrate that the proposed FDA and HOT framework effectively enhances the robustness and generalization of rPPG models across diverse datasets. |
| title | HOT: Harmonic-Constrained Optimal Transport for Remote Photoplethysmography Domain Adaptation |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2604.01675 |