ACTrack: Adding Spatio-Temporal Condition for Visual Object Tracking

arXiv:2403.07914v1 Announce Type: new
Abstract: Efficiently modeling spatio-temporal relations of objects is a key challenge in visual object tracking (VOT). Existing methods track by appearance-based similarity or long-term relation modeling, resulting in rich temporal contexts between consecutive frames being easily overlooked. Moreover, training trackers from scratch or fine-tuning large pre-trained models needs more time and memory consumption. In this paper, we present ACTrack, a new tracking framework with additive spatio-temporal conditions. It preserves the quality and capabilities of the pre-trained …

abstract arxiv challenge cs.cv fine-tuning key long-term modeling object objects pre-trained models relations scratch temporal tracking training type visual