AI Paper Atlas

Research map / Label-efficient and robust learning / Semi-supervised learning

MONET: Multiview Semi-Supervised Keypoint Detection via Epipolar Divergence

Yuan Yao, Yasamin Jafarian, Hyun Soo Park

ICCV 2019 · Label-efficient and robust learning › Semi-supervised learning · approach: GAN-based semi-supervised learning · 52 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 3D-tracked spatial augmentation to supervised training (ablation)CPM supervised · Multiview Humanreprojection error: 77.8 -> 69.0Improved
add 3D-tracked spatial augmentation to supervised training (ablation)CPM supervised · Multiview Monkeyreprojection error: 31.1 -> 12.9Improved
add temporal tracking (spatiotemporal augmentation) to spatial augmentation (ablation)CPM · Multiview Monkeyreprojection error: 12.9 -> 8.10Improved
add temporal tracking (spatiotemporal augmentation) to spatial augmentation (ablation)CPM · Multiview Dogreprojection error: 37.5 -> 24.0Improved
add re-triangulation and retraining (Bootstrapping II) to Bootstrapping ICPM · Multiview Humanreprojection error: 28.5 -> 35.4Hurt
add re-triangulation and retraining (Bootstrapping II) to Bootstrapping ICPM · Multiview Dogreprojection error: 18.9 -> 17.1Improved
replace Bootstrapping II by epipolar divergence (MONET)CPM · Multiview Humanreprojection error: 35.4 -> 15.0Improved
replace Bootstrapping II by epipolar divergence (MONET)CPM · Multiview Monkeyreprojection error: 9.97 -> 5.45Improved
replace Bootstrapping II by epipolar divergence (MONET)CPM · CMU Panopticreprojection error: 13.7 -> 12.8Improved
add a second labeled subject (S1,5) to S1 (ablation)MONET · Human3.6Mmean pixel error: 5.5 -> 5.2Improved
add a third labeled subject (S1,5,6) to S1,5 (ablation)MONET · Human3.6Mmean pixel error: 5.2 -> 4.3Improved
add more labeled subjects (S1,5,6 instead of S1) (ablation)MONET · Human3.6M foot (L.Foot)mean pixel error: 6.2 -> 4.7Mixed

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