AI Paper Atlas

Research map / Detection and segmentation / Tracking

Efficient Global MOT Under Minimum-Cost Circulation Framework

Congchao Wang, Yizhi Wang, Guoqiang Yu

TPAMI 2020 · Detection and segmentation › Tracking · approach: Association cues for online MOT · 13 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
replace min-cost flow with min-cost circulation (no search for object number)global data association · 40 efficiency experimentsrunning time: 53 times faster than MCFImproved
use CINDA instead of successive shortest pathglobal data association · 40 efficiency experimentsrunning time: 1,192 times faster than SSPImproved
use CINDA instead of dynamic SSPglobal data association · 40 efficiency experimentsrunning time: 592 times faster than dSSPImproved
use CINDA instead of best competing methodglobal data association · 40 efficiency experimentsrunning time: 29 times faster than the best competing methodImproved
use CINDA instead of MCFglobal data association · Embryorunning time: 5.8h -> 398.45Improved
use CINDA instead of SSP/dSSPglobal data association · Embryorunning time: >1d -> 398.45Improved
use CINDA as Frank-Wolfe subroutine instead of MCFquadratic programming identity inference · PETS09 S1.L1running time: 643.1 -> 27.5Improved
use CINDA instead of SSPglobal data association · KITTI(DPM) seq00 affinity (c)running time: 1.2h -> 0.52Improved
use CINDA instead of dSSPglobal data association · PTC-Lowrunning time: 40.4 -> 0.05Improved
use CINDA instead of MCFglobal data association · CVPR19 seq06 affinity (a)running time: 799.2 -> 22.9Improved
use CINDA instead of MCFglobal data association · KITTI(DPM) seq00 affinity (a)running time: 11.8 -> 0.26Improved
longer history for identity inference enabled by fast solvercar tracking · KITTI-CarMOT accuracyImproved

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