Papers › Learning a Neural Solver for Multiple Object Tracking

Learning a Neural Solver for Multiple Object Tracking

1 Jun 2020CVPR 2020 6archive 2025-07-28

Guillem Braso, Laura Leal-Taixe

Graphs offer a natural way to formulate Multiple Object Tracking (MOT) within the tracking-by-detection paradigm. However, they also introduce a major challenge for learning methods, as defining a model that can operate on such structured domain is not trivial. As a consequence, most learning-based work has been devoted to learning better features for MOT and then using these with well-established optimization frameworks. In this work, we exploit the classical network flow formulation of MOT to define a fully differentiable framework based on Message Passing Networks (MPNs). By operating directly on the graph domain, our method can reason globally over an entire set of detections and predict final solutions. Hence, we show that learning in MOT does not need to be restricted to feature extraction, but it can also be applied to the data association step. We show a significant improvement in both MOTA and IDF1 on three publicly available benchmarks. Our code is available at https://bit.ly/motsolv.

PaperPDFCode

Syntology This paper has no arXiv id in the archive, and this site joins papers to Syntology's graph by arXiv id, so this page does not say whether the graph holds it.

Code

dvl-tum/mot_neural_solver pytorchMITSyntology: no sample linked to this paper (harvested for another paper). Syntology's graph links these samples to Learning a Neural Solver for Multiple Object Tracking (arXiv:1912.07515; that paper's own run record: 16 ran (of which 0 constructed an object rather than computing a result; 11 with no instrument failure: 1 honoured, 1 violated, 9 with no contract checked; 5 where Syntology's instrument failed) · 4 unverified); nothing checks that they implement this paper's method. 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.

A paper named beside a repository with no sample linked to this paper is shown with that paper's own run record, not this paper's: “ran” means executed on a synthesized input, not that the code is correct, and “where Syntology's instrument failed” counts failures of Syntology's instrument, not of the code. Papers are listed in arXiv-id order, at most three per repository.

Code Syntology ran Syntology

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

Tasks

Multi-Object TrackingMultiple Object TrackingObjectObject Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking 2D MOT 2015 MPNTrack IDF1 58.6 #3 of 4 Archive leaderboard report
Multi-Object Tracking 2D MOT 2015 MPNTrack MOTA 51.5 #3 of 4 Archive leaderboard report
Multi-Object Tracking MOT16 MPNTrack IDF1 61.7 #17 of 24 Archive leaderboard report
Multi-Object Tracking MOT16 MPNTrack MOTA 58.6 #17 of 24 Archive leaderboard report
Multi-Object Tracking MOT17 MPNTrack IDF1 61.7 #42 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 MPNTrack MOTA 58.8 #42 of 48 Archive leaderboard report
Multi-Object Tracking MOT20 MPNTrack IDF1 59.1 #26 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 MPNTrack MOTA 57.6 #26 of 27 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