AI Paper Atlas

Research map / 3D vision / Human pose estimation

SO-HandNet: Self-Organizing Network for 3D Hand Pose Estimation With Semi-Supervised Learning

Yujin Chen, Zhigang Tu, Liuhao Ge, Dejun Zhang, Ruizhi Chen, Junsong Yuan

ICCV 2019 · 3D vision › Human pose estimation · approach: Depth-based hand pose regression · 94 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 unannotated data via point cloud autoencoder (semi-supervised) with 10% labels (ablation)SO-HandNet · HANDS 2017 Frame-basedmean joint error (mm): 40.03 mm -> 24.65 mmImproved
add semi-supervised training with unannotated data when only 25% labels are available (ablation)SO-HandNet · ICVL (25% annotated)mean joint error: 13.2%Improved
add semi-supervised training with unannotated data when 50% labels are available (ablation)SO-HandNet · ICVL (50% annotated)mean joint error: 11.7%Improved
add semi-supervised training with unannotated data when 75% labels are available (ablation)SO-HandNet · ICVL (75% annotated)mean joint error: 0.7%No clear effect
add node features to global feature in HPE input (v1 fusion) (ablation)SO-HandNet HPE · ICVLmean joint errorImproved
fuse global and node features in M channels (v1) instead of kN channels (v2) (ablation)SO-HandNet HPE · ICVLmean joint errorImproved
add point features to global+node fusion (ablation)SO-HandNet HPE · ICVLmean joint errorHurt
replace Crossing Nets with SO-HandNet at 25% labelssemi-supervised hand pose · NYU (25% annotated)mean joint error (mm): 16.1 -> 14.9Improved
replace Crossing Nets with SO-HandNet at 25% labelssemi-supervised hand pose · ICVL (25% annotated)mean joint error (mm): 10.5 -> 11.1Hurt
increase annotated data from 25% to 100% for SO-HandNet (ablation)SO-HandNet · NYUmean joint error (mm): 14.9 -> 11.2Improved
increase annotated data from 25% to 100% for Crossing Nets (ablation)Crossing Nets · ICVLmean joint error (mm): 10.5 -> 10.2No clear effect
use SO-HandNet instead of V2V-PoseNet for efficiencyhand pose estimator · ICVL (test, single GPU)parameters / speed: 457.5M -> 16.6M; 3.5fps -> 58fpsImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 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