Papers › Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

Hybrid-SORT: Weak Cues Matter for Online Multi-Object Tracking

1 Aug 2023arXiv:2308.00783archive 2025-07-28

Mingzhan Yang, Guangxin Han, Bin Yan, Wenhua Zhang, Jinqing Qi, Huchuan Lu, Dong Wang

Multi-Object Tracking (MOT) aims to detect and associate all desired objects across frames. Most methods accomplish the task by explicitly or implicitly leveraging strong cues (i.e., spatial and appearance information), which exhibit powerful instance-level discrimination. However, when object occlusion and clustering occur, spatial and appearance information will become ambiguous simultaneously due to the high overlap among objects. In this paper, we demonstrate this long-standing challenge in MOT can be efficiently and effectively resolved by incorporating weak cues to compensate for strong cues. Along with velocity direction, we introduce the confidence and height state as potential weak cues. With superior performance, our method still maintains Simple, Online and Real-Time (SORT) characteristics. Also, our method shows strong generalization for diverse trackers and scenarios in a plug-and-play and training-free manner. Significant and consistent improvements are observed when applying our method to 5 different representative trackers. Further, with both strong and weak cues, our method Hybrid-SORT achieves superior performance on diverse benchmarks, including MOT17, MOT20, and especially DanceTrack where interaction and severe occlusion frequently happen with complex motions. The code and models are available at https://github.com/ymzis69/HybridSORT.

PaperPDFCode

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

Code

ymzis69/HybridSORT officialmentioned in papermentioned on GitHubpytorchMIT report
mikel-brostrom/boxmot mentioned on GitHubpytorchAGPL-3.0 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 TrackingOnline Multi-Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Multi-Object Tracking DanceTrack Hybrid-SORT-ReID AssA 52.6 #14 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT-ReID DetA 82.2 #14 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT-ReID HOTA 65.7 #14 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT-ReID IDF1 67.4 #14 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT-ReID MOTA 91.8 #14 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT AssA 47.4 #18 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT DetA 81.9 #18 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT HOTA 62.2 #18 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT IDF1 63.0 #18 of 37 Archive leaderboard report
Multi-Object Tracking DanceTrack Hybrid-SORT MOTA 91.6 #18 of 37 Archive leaderboard report
Object Tracking QuadTrack HybridSORT HOTA 16.64 #6 of 8 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