Search Results for author:
Found 7 papers, 3 papers with code
Analyzing Participants' Engagement during Online Meetings Using Unsupervised Remote Photoplethysmography with Behavioral Features
The use of physiological and behavioral features is viable, but the impracticality of traditional physiological measurement arises due to the need for contact sensors.
Contrast-Phys+: Unsupervised and Weakly-supervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast
In this paper, we propose Contrast-Phys+, a method that can be trained in both unsupervised and weakly-supervised settings.
Contrast-Phys: Unsupervised Video-based Remote Physiological Measurement via Spatiotemporal Contrast
However, supervised rPPG methods require face videos and ground truth physiological signals for model training.
Non-contact Atrial Fibrillation Detection from Face Videos by Learning Systolic Peaks
Results: Our proposed method can accurately extract systolic peaks from face videos for AF detection.
Solving Inverse Problems with Hybrid Deep Image Priors: the challenge of preventing overfitting
When the noise level is small, it does not considerably reduce the overfitting problem.
Uncertainty-Driven Adaptive Sampling via GANs
We propose an adaptive sampling method for the linear model, driven by the uncertainty estimation with a generative adversarial network (GAN) model.
Closed loop deep Bayesian inversion: Uncertainty driven acquisition for fast MRI
This work proposes a closed-loop, uncertainty-driven adaptive sampling frame- work (CLUDAS) for accelerating magnetic resonance imaging (MRI) via deep Bayesian inversion.
