June 1, 2023

Neuron Structure Modeling for Generalizable Remote Physiological Measurement

Q: What is the clinical evidence from this study?

Study design: Other. Population: Remote physiological measurement (rPPG). Intervention: NEuron STructure modeling (NEST) vs. State-of-the-art methods. Primary outcome: Generalization capacity on cross-dataset and intra-dataset settings.

Resultado clave

The domain-label-free approach NEST outperformed state-of-the-art methods for remote photoplethysmography measurement on both cross-dataset and intra-dataset settings.

PICO estructurado

Población

Facial videos for remote photoplethysmography (rPPG) measurement

Intervención

NEuron STructure modeling (NEST) approach

Comparador

State-of-the-art domain generalization methods

Resultado

Generalization capacity (cross-dataset and intra-dataset performance)

The NEST approach improves the generalization capacity of remote photoplethysmography for extracting Blood Volume Pulse from facial videos across different environments.

Resumen

Remote photoplethysmography (rPPG) technology has drawn increasing attention in recent years. It can extract Blood Volume Pulse (BVP) from facial videos, making many applications like health monitoring and emotional analysis more accessible. However, as the BVP signal is easily affected by environmental changes, existing methods struggle to generalize well for unseen domains. In this paper, we systematically address the domain shift problem in the rPPG measurement task. We show that most domain generalization methods do not work well in this problem, as domain labels are ambiguous in complicated environmental changes. In light of this, we propose a domain-label-free approach called NEuron STructure modeling (NEST). NEST improves the generalization capacity by maximizing the coverage of feature space during training, which reduces the chance for under-optimized feature activation during inference. Besides, NEST can also enrich and enhance domain invariant features across multi-domain. We create and benchmark a large-scale domain generalization protocol for the rPPG measurement task. Extensive experiments show that our approach outperforms the state-of-the-art methods on both cross-dataset and intra-dataset settings. The codes are available at https://github.com/LuPaoPao/NEST.

Me gusta

Guardar

Cite This Study

Lu et al. (Thu,) conducted a other in Remote physiological measurement (rPPG). NEuron STructure modeling (NEST) vs. State-of-the-art methods was evaluated on Generalization capacity on cross-dataset and intra-dataset settings. The domain-label-free approach NEST outperformed state-of-the-art methods for remote photoplethysmography measurement on both cross-dataset and intra-dataset settings.

synapsesocial.com/papers/6a0a594597b2cd65685918ca https://doi.org/https://doi.org/10.1109/cvpr52729.2023.01783

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

Me gusta

Guardar