AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

rPPG-Toolbox: Deep Remote PPG Toolbox

Xin Liu, Girish Narayanswamy, Akshay Paruchuri, Xiaoyu Zhang, Jiankai Tang, Yuzhe Zhang, Roni Sengupta, Shwetak Patel, Yuntao Wang, Daniel McDuff

NeurIPS 2023 · Label-efficient and robust learning › Recognition and long-tail · approach: Dense features and foundation priors · 34 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
use DiffNormalized frame input instead of raw frames for PhysNet (ablation)PhysNet · UBFC-rPPG test, trained on PUREMAE (bpm): 11.17 -> 0.98Improved
use DiffNormalized frame input instead of raw frames for PhysNet (ablation)PhysNet · PURE test, trained on UBFC-rPPGMAE (bpm): 19.25 -> 8.06Improved
tune learning rate (0.009 to 0.09) and bandpass for PhysNet with raw input (ablation)PhysNet-Raw · PURE test, trained on UBFC-rPPGMAE (bpm): 19.25 -> 4.80Improved
tune learning rate and bandpass for PhysNet with raw input (ablation)PhysNet-Raw · UBFC-rPPG test, trained on SCAMPSMAE (bpm): 10.57 -> 10.33Mixed
train on synthetic SCAMPS instead of real dataPhysNet · PURE testMAE (bpm): 8.06 -> 13.30Hurt
train on SCAMPS instead of UBFC-rPPGDeepPhys · PURE testMAE (bpm): 5.54 -> 3.95Improved
train on motion-augmented UBFC-rPPG instead of original UBFC-rPPGTS-CAN · PURE testMAE (bpm): 3.69 -> 1.07Improved
train on motion-augmented UBFC-rPPG instead of original UBFC-rPPGPhysNet · PURE testMAE (bpm): 8.06 -> 17.03Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy