AI Paper Atlas

Research map / 3D vision / Human pose estimation

Multi-target Tracking in Multiple Non-overlapping Cameras Using Fast-Constrained Dominant Sets

Yonatan Tariku Tesfaye, Eyasu Zemene, Andrea Prati, Marcello Pelillo, Mubarak A. Shah

IJCV 2019 · 3D vision › Human pose estimation · approach: Temporal video pose estimation · 111 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
rank by constrained dominant set membership score instead of pairwise Euclidean distance (ablation)CDSC on MARS (CNN+XQDA) · MARS across-camera ReIDaverage precision: 0.42 -> 0.45Improved
rank by membership score instead of pairwise distance (ablation)CDSC on MARS (CNN+XQDA) · MARS within-camera ReIDaverage precision: 0.65 -> 0.68Improved
rank by membership score instead of pairwise distance (ablation)CDSC on MARS (CNN+KISSME) · MARS across-camera ReIDaverage precision: 0.41 -> 0.44Improved
rank by membership score instead of pairwise distance (ablation)CDSC on MARS (CNN+Eucl) · MARS across-camera ReIDaverage precision: 0.29 -> 0.29No clear effect
use constrained dominant set tracking instead of prior trackerCDSC tracker · DukeMTMC Test-EasyMOTA: 59.4 -> 70.9Improved
use constrained dominant set tracking instead of prior trackerCDSC tracker · DukeMTMC Test-HardMOTA: 54.6 -> 59.6Improved
use constrained dominant set tracking instead of prior trackerCDSC tracker · DukeMTMC Test-Easyidentity switches: 300 -> 693Hurt
use constrained dominant set tracking instead of prior trackerCDSC tracker · DukeMTMC Test-Hardidentity switches: 652 -> 1637Hurt
use across-camera constrained dominant sets instead of prior methodCDSC tracker · DukeMTMC Test-Easy multi-cameraIDF1: 56.2 -> 60.0Improved
use across-camera constrained dominant sets instead of prior methodCDSC tracker · DukeMTMC Test-Hard multi-cameraIDF1: 47.3 -> 50.9Improved
use constrained dominant sets instead of CNN+XQDA baselineCDSC ReID · MARSrank-1 accuracy: 65.30 -> 68.22Improved
speed up CDSC with fast InfImDyn-based local solver (FCDSC)CDSC · MARS track associationCPU time ratio: 2000x faster to above 4500xImproved

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