Papers › Focusing on Tracks for Online Multi-Object Tracking

Focusing on Tracks for Online Multi-Object Tracking

15 Jun 2025CVPR 2025 1archive 2025-07-28

Kyujin Shim, Kangwook Ko, YuJin Yang, Changick Kim

Multi-object tracking (MOT) is a critical task in computer vision, requiring the accurate identification and continuous tracking of multiple objects across video frames. However, current state-of-the-art methods mainly rely on a global optimization technique and multi-stage cascade association strategy, and those approaches often overlook the specific characteristics of assignment task in MOT and useful detection results that may represent occluded objects. To address these challenges, we propose a novel Track-Focused Online Multi-Object Tracker (TrackTrack) with two key strategies: Track-Perspective-Based Association (TPA) and Track-Aware Initialization (TAI). The TPA strategy associates each track with the most suitable detection result by choosing the one with the minimum distance from all available detection results in a track-perspective manner. On the other hand, the TAI method precludes the generation of spurious tracks in the track-aware aspect by suppressing track initialization of detection results that heavily overlap with current active tracks and more confident detection results. Extensive experiments on MOT17, MOT20, and DanceTrack demonstrate that our TrackTrack outperforms current state-of-the-art trackers, offering improved robustness and accuracy across diverse and challenging tracking scenarios.

PaperPDFConference PDFCode

Code

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 TrackingOnline Multi-Object Trackingglobal-optimization

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack TrackTrack AssA 52.9 #12 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TrackTrack HOTA 66.5 #12 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TrackTrack IDF1 67.8 #12 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack TrackTrack MOTA 93.6 #12 of 37 Archive leaderboard report
Multi-Object Tracking MOT17 TrackTrack AssA 68.2 #1 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 TrackTrack HOTA 67.1 #1 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 TrackTrack IDF1 83.1 #1 of 48 Archive leaderboard report
Multi-Object Tracking MOT17 TrackTrack MOTA 81.8 #1 of 48 Archive leaderboard report
Multi-Object Tracking MOT20 TrackTrack AssA 67.3 #3 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 TrackTrack HOTA 65.7 #3 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 TrackTrack IDF1 80.9 #3 of 27 Archive leaderboard report
Multi-Object Tracking MOT20 TrackTrack MOTA 78.0 #3 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