RIS-iPPG models iPPG recovery as an inverse problem using regularized stochastic interpolants to sample BVP posteriors from video pixels, yielding superior reconstruction and uncertainty on three datasets.
Daniele Silvestro and Tobias Andermann
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 2years
2026 2verdicts
UNVERDICTED 2roles
background 1polarities
background 1representative citing papers
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.
citing papers explorer
-
Uncertainty-quantified Pulse Signal Recovery from Facial Video using Regularized Stochastic Interpolants
RIS-iPPG models iPPG recovery as an inverse problem using regularized stochastic interpolants to sample BVP posteriors from video pixels, yielding superior reconstruction and uncertainty on three datasets.
-
Dual-stream Spatio-Temporal GCN-Transformer Network for 3D Human Pose Estimation
MixTGFormer reports state-of-the-art 3D pose estimation errors of 37.6 mm on Human3.6M and 15.7 mm on MPI-INF-3DHP by using parallel GCN-Transformer streams with SE layers for local-global feature fusion.