Metraipolis › archive › dc_7dee426cd064

Drone-PUR: From Visual Clue Discovery to Understanding and Reasoning in UAV Scenes — arXiv:2610.40801

Source: arXiv (en)
Original: https://arxiv.org/abs/2610.40801
License (as archived): CC0-1.0
Archived: 2026-11-03T05:45:41.148Z
SHA-256 of the archived text: 8f748a0a6da69b695e23e04ebd91119f28a5287683f871f478f487365de4d03c
Stable URL of this page: https://metraipolis.com/documento/dc_7dee426cd064

How to cite

Drone-PUR: From Visual Clue Discovery to Understanding and Reasoning in UAV Scenes — arXiv:2610.40801 — arXiv (en), https://arxiv.org/abs/2610.40801 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_7dee426cd064 (Metraipolis archive dc_7dee426cd064, sha256 8f748a0a6da69b695e23e04ebd91119f28a5287683f871f478f487365de4d03c)

BibTeX

@misc{dc7dee426cd064,
  title = {Drone-PUR: From Visual Clue Discovery to Understanding and Reasoning in UAV Scenes — arXiv:2610.40801},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.40801},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_7dee426cd064; sha256 8f748a0a6da69b695e23e04ebd91119f28a5287683f871f478f487365de4d03c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.40801. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

The reasoning capabilities of vision-language models (VLMs) can be limited by incomplete or inaccurate visual observations in the general domain. In unmanned aerial vehicle (UAV) scenes, small targets, subtle attributes, and changing viewpoints further complicate perception and understanding. Therefore, we introduce Drone-PUR, a dataset and benchmark organized around visual clue discovery, interpretation, and integration, corresponding to the three capability dimensions of perception, understanding, and reasoning. Reasoning samples are designed to require models to combine multiple visual clues to derive visually grounded conclusions. Its 11 tasks provide 175k training and 20k test samples spanning single images, image sequences, cross-modal images, and multiple viewpoints. All test samples undergo human review. Evaluating 22 general-purpose VLMs reveals persistent limitations in spatial judgment and cross-modal and cross-view reasoning. Across models, stronger perception is associated with better reasoning, while single-task fine-tuning further reveals selective bidirectional transfer between these capabilities. To examine domain adaptation, we develop UAV-PUR from Qwen3-VL through staged fine-tuning with auxiliary supervision. Its 4B and 8B variants improve overall multiple-choice accuracy by 18.33 and 17.52 percentage points over their pretrained counterparts, respectively. The dataset and project resources are available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (elenco arXiv cs.CV, nuovi lavori del giorno).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2610.40801 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-11-03T05:33:32.258Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).