AI Paper Atlas

Research map / 3D vision / Human pose estimation

Adversarial PoseNet: A Structure-Aware Convolutional Network for Human Pose Estimation

Yu Chen, Chunhua Shen, Xiu-Shen Wei, Lingqiao Liu, Jian Yang

ICCV 2017 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 376 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 occlusion-heatmap multi-task output to the four-stacked generator (no GANs) (ablation)Adversarial PoseNet · MPII validationPCKh: +0.5%Improved
add body-structure-aware discriminators to a single-task generator (ablation)Adversarial PoseNet · MPII validationPCKh: +0.6%Improved
use full model (multi-task generator plus discriminators) vs four-stacked single-task network (ablation)Adversarial PoseNet · MPII testmean PCKh: 90.6 -> 92.1Improved
use adversarial multi-task model instead of stacked hourglass on visible partsAdversarial PoseNet · MPII validation (visible parts)detection rate: about 0.8% improvementImproved
use adversarial multi-task model instead of stacked hourglass on invisible wristsAdversarial PoseNet · MPII validation (invisible parts)detection rate: 67.2 -> 70.7Improved
use adversarial multi-task model instead of stacked hourglass on invisible elbowsAdversarial PoseNet · MPII validation (invisible parts)detection rate: 74.0 -> 77.6Improved

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