Papers › Probabilistic Regression for Visual Tracking

Probabilistic Regression for Visual Tracking

27 Mar 2020CVPR 2020 6arXiv:2003.12565archive 2025-07-28

Martin Danelljan, Luc van Gool, Radu Timofte

Visual tracking is fundamentally the problem of regressing the state of the target in each video frame. While significant progress has been achieved, trackers are still prone to failures and inaccuracies. It is therefore crucial to represent the uncertainty in the target estimation. Although current prominent paradigms rely on estimating a state-dependent confidence score, this value lacks a clear probabilistic interpretation, complicating its use. In this work, we therefore propose a probabilistic regression formulation and apply it to tracking. Our network predicts the conditional probability density of the target state given an input image. Crucially, our formulation is capable of modeling label noise stemming from inaccurate annotations and ambiguities in the task. The regression network is trained by minimizing the Kullback-Leibler divergence. When applied for tracking, our formulation not only allows a probabilistic representation of the output, but also substantially improves the performance. Our tracker sets a new state-of-the-art on six datasets, achieving 59.8% AUC on LaSOT and 75.8% Success on TrackingNet. The code and models are available at https://github.com/visionml/pytracking.

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
open-mmlab/mmtracking mentioned on GitHubpytorchApache-2.0 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

Object TrackingVisual Trackingregression

Results from the paper archive 2025-07-28

TaskDatasetModelMetricValueRank at snapshotLeaderboardReport
Object Tracking FE108 PrDiMP Averaged Precision 87.7 #4 of 8 Archive leaderboard report
Object Tracking FE108 PrDiMP Success Rate 59.0 #4 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