Papers › A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking

A Confidence-Aware Matching Strategy For Generalized Multi-Object Tracking

27 Sep 2024IEEE International Conference on Image Processing (ICIP) 2024 9archive 2025-07-28

Kyujin Shim, Jubi Hwang, Kangwook Ko, Changick Kim

Multi-object tracking (MOT), a crucial task in computer vision, has broad applicability, and recently, tracking-by-detection-based trackers, which separate the processes of object detection and association, are showing state-of-the-art performance. However, while techniques like feature enhancement and distance measures have been extensively explored, the matching strategy itself remains an area that requires more in-depth study. As a result, many trackers still require manual adjustment of sensitive hyper-parameters for each tracking scenario, limiting their adaptability and robustness in dynamic environments. To address these limitations, we introduce CMTrack, a new tracker featuring a novel confidence-aware matching strategy comprised of three modules: confidence-aware cascade matching (CCM), confidence-aware metric fusion (CMF), and confidence-aware feature update (CFU). Our matching strategy enables the tracker to be a generalized and practical solution for various tracking scenarios within a unified framework while obviating manual calibration of hyper-parameters. The effectiveness of CMTrack is demonstrated through comprehensive assessments of three prominent MOT datasets: MOT17, MOT20, and DanceTrack. Notably, our CMTrack consistently surpasses existing state-of-the-art trackers, showcasing its superior generalization capabilities. The source codes and models are open at https://github.com/kamkyu94/CMTrack.

PaperPDFCode

Code

kamkyu94/CMTrack mentioned in paperpytorch 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 TrackingObject DetectionObject Trackingobject-detection

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack CMTrack AssA 46.4 #20 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CMTrack HOTA 61.8 #20 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CMTrack IDF1 63.3 #20 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack CMTrack MOTA 92.5 #20 of 37 Archive leaderboard report
Multi-Object Tracking MOT17 CMTrack AssA 66.1 #6 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 CMTrack DetA 65.1 #6 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 CMTrack HOTA 65.5 #6 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 CMTrack IDF1 81.5 #6 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 CMTrack MOTA 80.7 #6 of 48 Archive leaderboard report
Multi-Object Tracking MOT20 CMTrack AssA 66.7 #5 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 CMTrack HOTA 64.8 #5 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 CMTrack IDF1 79.9 #5 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 CMTrack MOTA 76.2 #5 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