Papers › Learning Data Association for Multi-Object Tracking using Only Coordinates

Learning Data Association for Multi-Object Tracking using Only Coordinates

12 Mar 2024arXiv:2403.08018archive 2025-07-28

Mehdi Miah, Guillaume-Alexandre Bilodeau, Nicolas Saunier

We propose a novel Transformer-based module to address the data association problem for multi-object tracking. From detections obtained by a pretrained detector, this module uses only coordinates from bounding boxes to estimate an affinity score between pairs of tracks extracted from two distinct temporal windows. This module, named TWiX, is trained on sets of tracks with the objective of discriminating pairs of tracks coming from the same object from those which are not. Our module does not use the intersection over union measure, nor does it requires any motion priors or any camera motion compensation technique. By inserting TWiX within an online cascade matching pipeline, our tracker C-TWiX achieves state-of-the-art performance on the DanceTrack and KITTIMOT datasets, and gets competitive results on the MOT17 dataset. The code will be made available upon publication.

PaperPDFCode

Code

Guepardow/TWiX officialmentioned on GitHubpytorch 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

Multi-Object TrackingMultiple Object TrackingObject Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack C-TWiX AssA 47.2 #19 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack C-TWiX DetA 81.8 #19 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack C-TWiX HOTA 62.1 #19 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack C-TWiX IDF1 63.6 #19 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack C-TWiX MOTA 91.4 #19 of 37 Archive leaderboard report
Multi-Object Tracking MOT17 C-TWiX AssA 62.5 #16 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 C-TWiX DetA 64.1 #16 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 C-TWiX HOTA 63.1 #16 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 C-TWiX IDF1 76.3 #16 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 C-TWiX MOTA 78.1 #16 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 C-TWiX Speed (FPS) 50 #16 of 48 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) C-TWiX HOTA 77.58 #9 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) C-TWiX IDSW 381 #9 of 34 Archive leaderboard report
Multiple Object Tracking KITTI Test (Online Methods) C-TWiX MOTA 89.68 #9 of 34 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.

Methods

Transformer

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