AI Paper Atlas

Research map / 3D vision / Human pose estimation

RMPE: Regional Multi-Person Pose Estimation

Hao-Shu Fang, Shuqin Xie, Yu-Wing Tai, Cewu Lu

ICCV 2017 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 2,025 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 symmetric STN (SSTN) and parallel SPPE (ablation)RMPE · MPII multi-person validationtotal mAP: 78.2 -> 80.8Improved
add parallel SPPE to SSTN (ablation)RMPE · MPII multi-person validationtotal mAP: 79.1 -> 80.8Improved
add pose-guided proposals generator (PGPG) (ablation)RMPE · MPII multi-person validationtotal mAP: 73.0 -> 80.8Improved
use PGPG instead of random jittering of boxes (ablation)RMPE · MPII multi-person validationtotal mAP: 77.9 -> 80.8Improved
add parametric pose NMS (ablation)RMPE · MPII multi-person validationtotal mAP: 75.7 -> 80.8Improved
use parametric pose NMS instead of prior pose NMS (variant 1) (ablation)RMPE · MPII multi-person validationtotal mAP: 79.1 -> 80.8Improved
use parametric pose NMS instead of prior pose NMS (variant 2) (ablation)RMPE · MPII multi-person validationtotal mAP: 79.9 -> 80.8Improved
use RMPE instead of straight forward two-step pipeline (ablation)RMPE · MPII multi-person validationtotal mAP: 71.7 -> 80.8Improved
replace detector proposals with ground truth boxes (ablation)RMPE · MPII multi-person validationtotal mAP: 80.8 -> 84.2Improved
use faster-rcnn with softnms and PyraNet instead of SSD-512 and hourglassRMPE · MPII multi-person testtotal mAP: 76.7 -> 82.1Improved
use parametric pose NMS rather than prior implementation (speed)pose NMS · MPII multi-person validationtime on 1300 images: 62.2 seconds -> 1.8 secondsImproved
use stronger detector and pose estimator on COCORMPE · MSCOCO keypoints test-devAP: 61.8 -> 72.3Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 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