A Universal Update-pacing Framework For Visual Tracking
This work addresses model drift for visual tracking applications, presenting an incremental improvement over existing methods.
The paper tackles model drift in visual tracking by introducing a framework that paces updates and selects robust trackers based on trajectory pairs, achieving superior performance on standard benchmarks.
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.