Search papers, labs, and topics across Lattice.
This paper introduces SATATrack, a Semantic-Aware Temporal Adaptation framework designed for UAV Anti-UAV tracking, which addresses the challenges of simultaneous movement and rapid viewpoint changes that complicate reliable appearance matching. By leveraging stable target language descriptions as semantic anchors and employing online feature-distribution alignment, SATATrack effectively preserves target identity and improves tracking robustness in dynamic environments. The proposed method achieves state-of-the-art performance on the UAV-Anti-UAV benchmark, demonstrating its efficacy in both Anti-UAV and UAV object tracking tasks.
SATATrack uses stable semantic descriptions to anchor tracking in rapidly changing environments, achieving state-of-the-art results in UAV Anti-UAV scenarios.
UAV Anti-UAV tracking is an emerging low-altitude security task for localizing an adversarial UAV using the onboard camera of a moving observer UAV. It differs from conventional UAV tracking and ground-based Anti-UAV tracking because both the camera platform and the target move simultaneously. This dual-dynamic setting induces rapid viewpoint changes, motion blur, scale variation, and visually similar distractors, making reliable appearance matching difficult. Under such rapidly changing conditions, fixed visual representations are often insufficient because target appearance becomes unreliable and feature distributions may deviate from the training domain. The target language description remains stable across frames and can therefore serve as a semantic anchor for temporal state propagation, while online feature-distribution alignment can reduce video-specific test-time shifts. In this paper, we propose \emph{SATATrack}, a Semantic-Aware Temporal Adaptation framework for UAV Anti-UAV tracking. SATATrack introduces Semantic-Aware Context Propagation (SACP), which uses the target description to guide temporal context propagation across backbone stages and preserve target identity under rapid appearance changes. An auxiliary contrastive regularizer is used during training to discourage responses to semantically similar background regions. During inference, Temporal-Aware Distribution Alignment (TADA) aligns feature distributions online without updating model parameters, combining recent-frame estimates with training-time statistics for stability. SATATrack achieves state-of-the-art performance on the UAV-Anti-UAV benchmark while remaining competitive in Anti-UAV and UAV object tracking tasks. The code will be available at https://github.com/XiaozhenQiao/SATATrack.
