Papers › NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets

NeighborTrack: Improving Single Object Tracking by Bipartite Matching with Neighbor Tracklets

12 Nov 2022arXiv:2211.06663archive 2025-07-28

Yu-Hsi Chen, Chien-Yao Wang, Cheng-Yun Yang, Hung-Shuo Chang, Youn-Long Lin, Yung-Yu Chuang, Hong-Yuan Mark Liao

We propose a post-processor, called NeighborTrack, that leverages neighbor information of the tracking target to validate and improve single-object tracking (SOT) results. It requires no additional data or retraining. Instead, it uses the confidence score predicted by the backbone SOT network to automatically derive neighbor information and then uses this information to improve the tracking results. When tracking an occluded target, its appearance features are untrustworthy. However, a general siamese network often cannot tell whether the tracked object is occluded by reading the confidence score alone, because it could be misled by neighbors with high confidence scores. Our proposed NeighborTrack takes advantage of unoccluded neighbors' information to reconfirm the tracking target and reduces false tracking when the target is occluded. It not only reduces the impact caused by occlusion, but also fixes tracking problems caused by object appearance changes. NeighborTrack is agnostic to SOT networks and post-processing methods. For the VOT challenge dataset commonly used in short-term object tracking, we improve three famous SOT networks, Ocean, TransT, and OSTrack, by an average of 1.92% EAO and 2.11% robustness. For the mid- and long-term tracking experiments based on OSTrack, we achieve state-of-the-art 72.25% AUC on LaSOT and 75.7% AO on GOT-10K. Code duplication can be found in https://github.com/franktpmvu/NeighborTrack.

PaperPDFCode

Code

franktpmvu/NeighborTrack officialmentioned in papermentioned 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

ObjectObject TrackingVideo Object TrackingVisual Object Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Video Object Tracking NT-VOT211 Neighbor- Track(OSTrack) AUC 38.32 #9 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 Neighbor- Track(OSTrack) Precision 52.54 #9 of 43 Archive leaderboard report
Visual Object Tracking GOT-10k NeighborTrack-OSTrack Average Overlap 75.7 #19 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k NeighborTrack-OSTrack Success Rate 0.5 85.72 #19 of 42 Archive leaderboard report
Visual Object Tracking GOT-10k NeighborTrack-OSTrack Success Rate 0.75 73.3 #19 of 42 Archive leaderboard report
Visual Object Tracking LaSOT NeighborTrack-OSTrack AUC 72.2 #20 of 46 Archive leaderboard report
Visual Object Tracking LaSOT NeighborTrack-OSTrack Normalized Precision 81.8 #20 of 46 Archive leaderboard report
Visual Object Tracking LaSOT NeighborTrack-OSTrack Precision 78.0 #20 of 46 Archive leaderboard report
Visual Object Tracking TrackingNet NeighborTrack-OSTrack Accuracy 83.79 #21 of 40 Archive leaderboard report
Visual Object Tracking TrackingNet NeighborTrack-OSTrack Normalized Precision 88.30 #21 of 40 Archive leaderboard report
Visual Object Tracking UAV123 NeighborTrack-OSTrack AUC 0.725 #2 of 16 Archive leaderboard report
Visual Object Tracking UAV123 NeighborTrack-OSTrack Precision 0.9337 #2 of 16 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

AOCycle Consistency LossSiamese NetworkSoft-NMSTransformer

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