AI Paper Atlas

Research map / Video / Video segmentation and tracking

Implicit Neural Models to Extract Heart Rate from Video

Pradyumna Chari, Anirudh Bindiganavale Harish, Adnan Armouti, Alexander Vilesov, Sanjit Sarda, Laleh Jalilian, Achuta Kadambi

ECCV 2024 · Video › Video segmentation and tracking · approach: Neural video representations · 3 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 A-B decomposition INR with neural signal strength masks instead of Green channel averagingrPPG heart rate estimation · Optically challenging OOD dataset (train on [53])MAE (bpm): 7.80 -> 5.10Improved
use proposed INR method instead of learning-based PhysFormer on OOD datarPPG heart rate estimation · Optically challenging OOD dataset (train on [49])MAE (bpm): 9.58 -> 4.61Improved
use proposed method versus deep learning baselines for cross-dataset generalizationrPPG heart rate estimation · Test on [53], train on [49]MAE (bpm): 5.27 -> 1.16Improved
proposed method versus PhysNet in in-distribution testrPPG heart rate estimation · Test on [53], train on [53]MAE (bpm): 0.94 -> 1.21No clear effect
proposed method versus PhysNet when trained on [53] and tested on [49]rPPG heart rate estimation · Test on [49], train on [53]Pearson r: 0.96 -> 0.94No clear effect
deep learning methods trained in-distribution then tested on OOD datasetDeepPhys / TS-CAN / PhysFormer · Optically challenging OOD datasetr-consistency: 0.03 and 0 for DeepPhys and TS-CAN (train on [53])Hurt

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