AI Paper Atlas

Research map / Video / Video segmentation and tracking

Non-Contrastive Unsupervised Learning of Physiological Signals From Video

Jeremy Speth, Nathan Vance, Patrick Flynn, Adam Czajka

CVPR 2023 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis · 72 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
add the bandwidth, sparsity, and variance losses together (ablation)SiNC · UBFC-rPPGMAE (bpm): 0.59 ± 0.00 vs 3.08 ± 1.69 (L_b only)Improved
use only sparsity loss L_s (ablation)SiNC · UBFC-rPPGMAE (bpm): 0.59 ± 0.00 -> 45.50 ± 1.22Hurt
use only variance loss L_v (ablation)SiNC · UBFC-rPPGMAE (bpm): 0.59 ± 0.00 -> 22.89 ± 2.83Hurt
omit bandwidth loss L_b (ablation)SiNC · UBFC-rPPGMAE (bpm): 0.59 ± 0.00 -> 51.24 ± 5.36Hurt
omit variance loss L_v (ablation)SiNC · UBFC-rPPGMAE (bpm): 0.59 ± 0.00 -> 9.99 ± 2.55Hurt
omit sparsity loss L_s (ablation)SiNC · UBFC-rPPGMAE (bpm): 0.59 ± 0.00 -> 4.18 ± 2.88Hurt
allow energy in the second harmonic in the sparsity loss (ablation)SiNC · PUREMAE (bpm): 0.61 ± 0.06 -> 3.29 ± 1.69Hurt
vary batch size among 5, 10, 15, and 20 (ablation)SiNC · PUREMAE (bpm): 0.73 ± 0.08; 0.65 ± 0.09; 1.75 ± 1.39; 0.61 ± 0.06No clear effect
remove training augmentations (ablation)SiNC · PUREMAE (bpm): 0.61 ± 0.06 -> 33.86 ± 0.83Hurt
train on unlabeled HKBU-MARs videos rather than rPPG-specific labeled dataSiNC · UBFC-rPPG and PURE cross-dataset testingMAE (bpm): UBFC: 1.08 ± 0.03; PURE: 2.43 ± 0.20Improved
train on CelebV-HQ online videosSiNC · CelebV-HQ trainingpulse signal convergenceHurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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