Papers › Learning Target Candidate Association to Keep Track of What Not to Track

Learning Target Candidate Association to Keep Track of What Not to Track

30 Mar 2021ICCV 2021 10arXiv:2103.16556archive 2025-07-28

Christoph Mayer, Martin Danelljan, Danda Pani Paudel, Luc van Gool

The presence of objects that are confusingly similar to the tracked target, poses a fundamental challenge in appearance-based visual tracking. Such distractor objects are easily misclassified as the target itself, leading to eventual tracking failure. While most methods strive to suppress distractors through more powerful appearance models, we take an alternative approach. We propose to keep track of distractor objects in order to continue tracking the target. To this end, we introduce a learned association network, allowing us to propagate the identities of all target candidates from frame-to-frame. To tackle the problem of lacking ground-truth correspondences between distractor objects in visual tracking, we propose a training strategy that combines partial annotations with self-supervision. We conduct comprehensive experimental validation and analysis of our approach on several challenging datasets. Our tracker sets a new state-of-the-art on six benchmarks, achieving an AUC score of 67.1% on LaSOT and a +5.8% absolute gain on the OxUvA long-term dataset.

PaperPDFConference PDFCode

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

Code

visionml/pytracking 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

Object TrackingVideo Object TrackingVisual Object TrackingVisual Tracking

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Tracking COESOT KeepTrack Precision Rate 66.1 #9 of 12 Archive leaderboard report
Object Tracking COESOT KeepTrack Success Rate 59.6 #9 of 12 Archive leaderboard report
Video Object Tracking NT-VOT211 KeepTrack AUC 39.59 #3 of 43 Archive leaderboard report
Video Object Tracking NT-VOT211 KeepTrack Precision 55.50 #3 of 43 Archive leaderboard report
Visual Object Tracking DiDi KeepTrack Tracking quality 0.502 #10 of 11 Archive leaderboard report
Visual Object Tracking LaSOT KeepTrack AUC 67.1 #34 of 46 Archive leaderboard report
Visual Object Tracking LaSOT KeepTrack Normalized Precision 77.2 #34 of 46 Archive leaderboard report
Visual Object Tracking LaSOT KeepTrack Precision 70.2 #34 of 46 Archive leaderboard report
Visual Object Tracking LaSOT-ext KeepTrack AUC 48.2 #17 of 18 Archive leaderboard report
Visual Object Tracking OTB-2015 KeepTrack AUC 0.709 #8 of 18 Archive leaderboard report
Visual Object Tracking UAV123 KeepTrack AUC 0.697 #11 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.

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