AI Paper Atlas

Research map / 3D vision / Human pose estimation

SemiHand: Semi-Supervised Hand Pose Estimation With Consistency

Linlin Yang, Shicheng Chen, Angela Yao

ICCV 2021 · 3D vision › Human pose estimation · approach: Monocular 2D-to-3D pose lifting · 36 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 view consistency loss to the synthetic-pretrained baseline (ablation)SemiHand baseline · STB test, mean EPE (mm)mean EPE: 23.83 -> 21.03Improved
add cross-modal consistency loss to the baseline (ablation)SemiHand baseline · STB test, mean EPE (mm)mean EPE: 23.83 -> 20.92Improved
add both consistency losses (vc+cc) to the baseline (ablation)SemiHand baseline · STB test, mean EPE (mm)mean EPE: 23.83 -> 19.93Improved
add pseudo-labelling with label correction and sample selection to the baseline (ablation)SemiHand baseline · STB test, mean EPE (mm)mean EPE: 7.52 mm improvement (23.83 -> 16.31)Improved
combine consistency training and pseudo-labelling (full SemiHand) (ablation)SemiHand baseline · STB test, mean EPE (mm)mean EPE: 9.23mm improvement (23.83 -> 14.60)Improved
add pseudo-labelling on top of both consistency losses (ablation)SemiHand · STB test, mean EPE (mm)mean EPE: 19.93 -> 14.60Improved
fine-tune on the unlabelled STB test images instead of train imagesSemiHand · STB test, mean EPE (mm)mean EPE: 14.60 -> 14.51Improved
fine-tune on unlabelled STB train and test togetherSemiHand · STB test, mean EPE (mm)mean EPE: 14.60 -> 13.95Improved
increase the percentage of unlabelled STB training dataSemiHand · STB test, mean EPE (mm)mean EPE: 17.31 -> 14.60Improved
semi-supervised fine-tuning on unlabelled real images across datasetsSemiHand baseline · Dexter+Object, mean EPEmean EPE: decrease of up to 22.4 mm on DOImproved
semi-supervised fine-tuning, AUC on STBSemiHand baseline · STB AUCAUC: 0.774 -> 0.927Improved
semi-supervised fine-tuning, AUC on Dexter+ObjectSemiHand baseline · Dexter+Object AUCAUC: 0.546 -> 0.747Improved

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