{"ID":2887312,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2508.01730","arxiv_id":"2508.01730","title":"Tracking the Unstable: Appearance-Guided Motion Modeling for Robust Multi-Object Tracking in UAV-Captured Videos","abstract":"Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affinity measurement and ambiguous association. Existing methods typically model motion and appearance cues separately, overlooking their spatio-temporal interplay and resulting in suboptimal tracking performance. In this work, we propose AMOT, which jointly exploits appearance and motion cues through two key components: an Appearance-Motion Consistency (AMC) matrix and a Motion-aware Track Continuation (MTC) module. Specifically, the AMC matrix computes bi-directional spatial consistency under the guidance of appearance features, enabling more reliable and context-aware identity association. The MTC module complements AMC by reactivating unmatched tracks through appearance-guided predictions that align with Kalman-based predictions, thereby reducing broken trajectories caused by missed detections. Extensive experiments on three UAV benchmarks, including VisDrone2019, UAVDT, and VT-MOT-UAV, demonstrate that our AMOT outperforms current state-of-the-art methods and generalizes well in a plug-and-play and training-free manner.","short_abstract":"Multi-object tracking (MOT) aims to track multiple objects while maintaining consistent identities across frames of a given video. In unmanned aerial vehicle (UAV) recorded videos, frequent viewpoint changes and complex UAV-ground relative motion dynamics pose significant challenges, which often lead to unstable affini...","url_abs":"https://arxiv.org/abs/2508.01730","url_pdf":"https://arxiv.org/pdf/2508.01730v2","authors":"[\"Jianbo Ma\",\"Hui Luo\",\"Qi Chen\",\"Yuankai Qi\",\"Yumei Sun\",\"Amin Beheshti\",\"Jianlin Zhang\",\"Ming-Hsuan Yang\"]","published":"2025-08-03T12:06:47Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}