AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video-based Remote Physiological Measurement via Cross-verified Feature Disentangling

Xuesong Niu, Zitong Yu, Hu Han, Xiaobai Li, Shiguang Shan, Guoying Zhao

ECCV 2020 · Video › Video segmentation and tracking · approach: Sign language and physiological video analysis

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 rPPG-signal supervision (multi-task) to HR-only training (ablation)MSTmap network · VIPL-HR (5-fold, average HR)MAE (bpm): 6.39 -> 5.55Improved
add rPPG-signal supervision (multi-task) to HR-only training (ablation)MSTmap network · VIPL-HR (5-fold, average HR)RMSE (bpm): 10.24 -> 9.03Improved
add cross-verified disentangling (CVD) (ablation)MSTmap+MTL · VIPL-HR (5-fold, average HR)RMSE (bpm): 9.03 -> 7.97Improved
add cross-verified disentangling (CVD) (ablation)MSTmap+MTL · VIPL-HR (5-fold, average HR)MAE (bpm): 5.55 -> 5.02Improved
add cross-verified disentangling (CVD) (ablation)STmap+MTL · VIPL-HR (5-fold, average HR)RMSE (bpm): 9.01 -> 8.51Improved
use MSTmap instead of STmap input (ablation)MTL without CVD · VIPL-HR (5-fold, average HR)MAE (bpm): 5.80 -> 5.55Improved
use MSTmap instead of STmap input (ablation)MTL with CVD · VIPL-HR (5-fold, average HR)RMSE (bpm): 8.51 -> 7.97Improved
add pre-defined head movement signal disentanglement (ablation)MSTmap+MTL · VIPL-HR (5-fold, average HR)RMSE (bpm): 9.03 -> 8.96Improved
add pre-defined face pixel std signal disentanglement (ablation)MSTmap+MTL · VIPL-HR (5-fold, average HR)RMSE (bpm): 9.03 -> 8.72Improved
use CVD instead of pre-defined non-physiological signals (ablation)MSTmap+MTL · VIPL-HR (5-fold, average HR)RMSE (bpm): 8.72 -> 7.97Improved
use proposed method instead of RhythmNetRhythmNet · VIPL-HR (5-fold, average HR)RMSE (bpm): 8.14 -> 7.97Improved
use proposed method instead of RhythmNet in large head movement scenarioRhythmNet · VIPL-HR (large head movement)RMSE (bpm): 9.4 -> 7.44Improved

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