Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
July 15, 2025Knowledge-Based SystemsOpen Access

STREAM-Net: Spatio-temporal feature fusion network for robust rPPG signal measurement in remote health monitoring

View Full Paper
Ask AI
Bookmark
Share

Why the study?

Deep learning approaches are needed to address challenges such as motion artifacts, redundancy, and external noise in contactless video-based remote photoplethysmography signal extraction.

Population

Video frames from two benchmark datasets (UBFC and PURE)

Comparison

STREAM-Net bilateral spatio-temporal network evaluation

Design

Algorithm development and validation study

Authors

MSMilena SobotkaJRJacek Rumiński

Discussion

Loading...

Member takes

Overview

Should not yet change contactless monitoring practice; extends video rPPG networks but leaves open prospective clinical validation.

Structured PICO

P
Population
Two benchmark datasets (UBFC and PURE) containing video frames for remote photoplethysmography (rPPG) signal extraction
I
Intervention
STREAM-Net (a bilateral spatio-temporal network with lateral attention and multi-scale feature integration)
O
Outcome
Accuracy of blood volume pulse (BVP) signal estimation (measured by MAE, RMSE, and MAPE)surrogate

STREAM-Net provides a robust and reliable deep learning approach for non-invasive, video-based extraction of physiological signals like blood volume pulse.

Cite This Study

Sobotka et al. (2025) studied this question.

synapsesocial.com/papers/6a80dbfad7cc36764365e35ehttps://doi.org/10.1016/j.knosys.2025.114080
View Full Paper
Ask AI
Bookmark
Share

Also Consider

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

  1. 1MSSTNet: Multi-scale facial videos pulse extraction network based on separable spatiotemporal convolution and dimension separable attention2023 · 7 citations
  2. 2Noise-resilient spatial–channel refinement for robust remote photoplethysmography2026
  3. 3A Study on the Implementation of Temporal Noise-Robust Methods for Acquiring Vital Signs2024 · 4 citations
  4. 4STC-rPPG: A Remote Heart Rate Estimation Network Based on Spatiotemporal–Channel Feature Collaborative Learning2025
  5. 5A Dual-Branch Spatio-Temporal Feature Differencing Method for Robust rPPG Estimation2025