A Universal Update-pacing Framework For Visual Tracking
Zexi Hu, Yuefang Gao, Dong Wang, Xuhong Tian

TL;DR
This paper introduces a universal update-pacing framework for visual tracking that uses paced updates and trajectory selection to reduce model drift and improve robustness in tracking objects across video frames.
Contribution
It presents a novel framework that generates an ensemble of trackers with paced updates and selects the most robust one based on trajectory self-examination, enhancing tracking stability.
Findings
Achieves superior performance on standard benchmarks.
Effectively leverages temporal context to avoid learning corrupted information.
Reduces model drift in visual tracking.
Abstract
This paper proposes a novel framework to alleviate the model drift problem in visual tracking, which is based on paced updates and trajectory selection. Given a base tracker, an ensemble of trackers is generated, in which each tracker's update behavior will be paced and then traces the target object forward and backward to generate a pair of trajectories in an interval. Then, we implicitly perform self-examination based on trajectory pair of each tracker and select the most robust tracker. The proposed framework can effectively leverage temporal context of sequential frames and avoid to learn corrupted information. Extensive experiments on the standard benchmark suggest that the proposed framework achieves superior performance against state-of-the-art trackers.
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsVideo Surveillance and Tracking Methods · Human Pose and Action Recognition · Fire Detection and Safety Systems
