{"ID":6267015,"CreatedAt":"2026-07-10T01:11:38.759438437Z","UpdatedAt":"2026-07-12T02:56:01.035875985Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2607.08075","arxiv_id":"2607.08075","title":"UAV-OVVIS: Unmanned Aerial Vehicles Also Need Open-Vocabulary Video Instance Segmentation","abstract":"Unmanned Aerial Vehicle (UAV) videos are widely used in traffic monitoring, urban management, and emergency rescue. However, existing UAV video perception mainly relies on box-level localization and trajectory association under predefined categories, making it difficult to simultaneously support flexible queries and fine-grained instance-level dynamic understanding in open scenarios. To this end, we introduce a new task, UAV Open-Vocabulary Video Instance Segmentation (UAV-OVVIS), which discovers targets in UAV videos according to open-vocabulary queries and outputs instance-level segmentation trajectories with globally consistent identities. Considering the scarcity of instance-level annotations in UAV scenarios, we propose AeroTrack, a training-free unified framework. AeroTrack centers on periodic open-vocabulary detection, short-segment mask propagation, and cross-segment identity unification, reusing existing visual foundation models to enable UAV-OVVIS. Based on this framework, we instantiate five AeroTrack variants and construct AeroVIS, an evaluation benchmark for UAV-OVVIS containing 9 UAV object categories and 8,279 trajectories. Experiments show that AeroTrack substantially outperforms existing general video instance segmentation methods in UAV scenarios and demonstrates strong open-vocabulary robustness and generalization. To support future research, we release AeroTrack and AeroVIS as a unified framework and benchmark for UAV-OVVIS.","short_abstract":"Unmanned Aerial Vehicle (UAV) videos are widely used in traffic monitoring, urban management, and emergency rescue. However, existing UAV video perception mainly relies on box-level localization and trajectory association under predefined categories, making it difficult to simultaneously support flexible queries and fi...","url_abs":"https://arxiv.org/abs/2607.08075","url_pdf":"https://arxiv.org/pdf/2607.08075v1","authors":"[\"Mingyu Dou\",\"Shi Qiu\",\"Ming Hu\",\"Yifan Chen\",\"Zhe Sun\"]","published":"2026-07-09T03:08:33Z","proceeding":"cs.CV","tasks":"[\"cs.CV\"]","methods":"[]","has_code":false}