AI Paper Atlas

Research map / 3D vision / Human pose estimation

Active Learning for Human Pose Estimation

Buyu Liu, Vittorio Ferrari

ICCV 2017 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 68 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 Multiple Peak Entropy instead of Highest Probability / Best-vs-Second-Best uncertainty (ablation)image-level active learning · MPII validationPCK-h accuracy vs annotation fractionImproved
select by active cues instead of Random (ablation)active learning · MPII validationPCK-h accuracy vs annotation fractionImproved
use Dynamic Combination of influence and uncertainty instead of Static Combination (W fixed at 0.5) (ablation)Inf + MPE · MPII validationPCK-h accuracy vs annotation fractionImproved
add influence cue early and uncertainty later (time-varying weight) (ablation)active selection · MPII validationPCK-h accuracyImproved
use DC instead of HP at 30% annotation budget (ablation)active selection · MPII validationPCK-h accuracy: 8% betterImproved
use DC instead of RM at 30% annotation budget (ablation)active selection · MPII validationPCK-h accuracy: 19% betterImproved
use DC with 90% of data annotated instead of HP/RM (ablation)active selection · MPII validationPCK-h accuracyNo clear effect
select individual joints (DC-jt) instead of whole images (DC-im) at low budget (ablation)DC · MPII validationPCK-h accuracy: half the annotation effort of RM-im for 40% of performanceImproved
apply DC-im active learning on a strong LSP-trained CPM, adding 10% MPIICPM · LSP testPCK-h accuracy: 84.3% -> 86.7%Improved
add 30% MPII images chosen by DC-imCPM · LSP testPCK-h accuracy: 84.3% -> 88.9%Improved
replace standard exact-click interface with VD-based region interfaceannotation process · MPII annotation timeannotation time per joint: about 33% time savedImproved
train on VD-based (peak-selected) annotations instead of exact ground truthDC-im · MPII validationPCK-h accuracy: within 3% gapNo clear effect

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