AI Paper Atlas

Research map / 3D vision / Human pose estimation

Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos

Umer Rafi, Andreas Doering, Bastian Leibe, Juergen Gall

ECCV 2020 · 3D vision › Human pose estimation · approach: Multi-person pose estimation · 58 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 keypoint correspondences instead of optical flow for track association (ablation)pose tracking · PoseTrack 2017 val (GT boxes)MOTA: 68.4 -> 70.5Improved
use keypoint correspondences instead of person re-ID for association (ablation)pose tracking · PoseTrack 2017 val (GT boxes)MOTA: 67.1 -> 70.5Improved
use keypoint correspondences instead of OKS similarity (ablation)pose tracking · PoseTrack 2017 val (detected boxes)MOTA: 60.4 -> 67.9Improved
use keypoint correspondences instead of optical flow (ablation)pose tracking · PoseTrack 2017 val (GT boxes)IDSW: 4419 -> 3583Improved
add the refinement module for affinity maps (ablation)correspondence tracking · PoseTrack 2017 valMOTA: 66.9 -> 67.9Improved
add duplicate removal (ablation)correspondence tracking · PoseTrack 2017 valMOTA: 64.5 -> 67.9Improved
add recovery of missed detections via correspondences (ablation)top-down pose estimator · PoseTrack 2018 val (threshold 0.3)mAP: 77.7 -> 79.2Improved
add recovery of missed detections via correspondences (ablation)top-down pose estimator · PoseTrack 2018 val (threshold 0.3)MOTA: 67.6 -> 68.8Improved
raise joint detection threshold from 0.0 to 0.3 (ablation)pose tracking · PoseTrack 2018 val (detected poses only)mAP and MOTA: mAP 80.1 -> 77.7; MOTA 48.1 -> 67.6Mixed
vary tau_corr from 0.1 to 0.5 (ablation)correspondence tracking · PoseTrack 2017 valMOTA: 67.9 -> 67.8No clear effect
add track merging post-processingcorrespondence tracking · PoseTrack 2017 valMOTA: 67.9 -> 68.3Improved
add track merging post-processingcorrespondence tracking · PoseTrack 2018 valMOTA: 68.8 -> 69.1Improved

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