Papers › Lifted Disjoint Paths with Application in Multiple Object Tracking

Lifted Disjoint Paths with Application in Multiple Object Tracking

25 Jun 2020ICML 2020 1arXiv:2006.14550archive 2025-07-28

Andrea Hornakova, Roberto Henschel, Bodo Rosenhahn, Paul Swoboda

We present an extension to the disjoint paths problem in which additional \emph{lifted} edges are introduced to provide path connectivity priors. We call the resulting optimization problem the lifted disjoint paths problem. We show that this problem is NP-hard by reduction from integer multicommodity flow and 3-SAT. To enable practical global optimization, we propose several classes of linear inequalities that produce a high-quality LP-relaxation. Additionally, we propose efficient cutting plane algorithms for separating the proposed linear inequalities. The lifted disjoint path problem is a natural model for multiple object tracking and allows an elegant mathematical formulation for long range temporal interactions. Lifted edges help to prevent id switches and to re-identify persons. Our lifted disjoint paths tracker achieves nearly optimal assignments with respect to input detections. As a consequence, it leads on all three main benchmarks of the MOT challenge, improving significantly over state-of-the-art.

PaperPDFConference PDFCode

In Syntology Open this paper in Syntology's Atlas, the map of the papers in Syntology's graph and their citations.

Code

AndreaHor/LifT_Solver officialmentioned in papermentioned on GitHub report

Repository list and official/mentioned flags are the archive's, frozen 2025-07-28. Reachability, where shown, is from one Syntology probe window (2026-09-16 to 2026-09-18); repositories not probed show nothing. GitHub stars are not tracked.

Code Syntology ran Syntology

Not run by Syntology. Nothing on this page verifies that the listed code works.

Tasks

Multiple Object TrackingObjectObject Trackingglobal-optimization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking 2D MOT 2015 Lif_T IDF1 60.0 #2 of 4 Archive leaderboard report
Multi-Object Tracking 2D MOT 2015 Lif_T MOTA 52.5 #2 of 4 Archive leaderboard report
Multi-Object Tracking MOT16 Lif_T IDF1 64.7 #16 of 24 Archive leaderboard report
Multi-Object Tracking MOT16 Lif_T MOTA 61.3 #16 of 24 Archive leaderboard report
Multi-Object Tracking MOT17 Lif_T IDF1 65.6 #41 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 Lif_T MOTA 60.5 #41 of 48 Archive leaderboard report

Ranks are positions in the archive's leaderboards as they stood at the 2025-07-28 snapshot. Results published since then are not among these rows, so a rank here is not a current standing.

Report a problem or propose a change · a person checks every report against the paper or source before anything changes; decisions are listed on /corrections