Metraipolis › archive › dc_b30f8bb74ae8

GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views — arXiv:2608.09270

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.09270
License (as archived)
CC0-1.0
Archived
2026-10-19T09:15:44.943Z
SHA-256 of the archived text
5e048919361992736a51eb508b49b1d1ba61c3383b9887d6ab3de23ac6b1f62a
Stable URL of this page
https://metraipolis.com/documento/dc_b30f8bb74ae8

How to cite

GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views — arXiv:2608.09270 — arXiv (en), https://arxiv.org/abs/2608.09270 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_b30f8bb74ae8 (Metraipolis archive dc_b30f8bb74ae8, sha256 5e048919361992736a51eb508b49b1d1ba61c3383b9887d6ab3de23ac6b1f62a)
BibTeX
@misc{dcb30f8bb74ae8,
  title = {GRASP: Granularity-Aware Region Alignment and Semantic Prototype Learning for Fine-Grained Cross-Modal Understanding in Drone Views — arXiv:2608.09270},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.09270},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_b30f8bb74ae8; sha256 5e048919361992736a51eb508b49b1d1ba61c3383b9887d6ab3de23ac6b1f62a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.09270. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Fine-grained cross-modal understanding in drone views is essential for aerial vision-language navigation. However, the inherent wide field of view and overhead perspective of drone scenarios impose dual challenges on vision-language understanding. At the macro level, overwhelming background clutter in visual representations leads to Cross-Modal Focus Misalignment, where the model prioritizes global environmental similarities over specific object details. At the micro level, Visual Isomorphism creates ambiguity, where candidates share similar geometric structures yet differ only in subtle attributes. To address these challenges, we propose the Granularity-Aware Region Alignment and Semantic Prototype (GRASP) learning framework, enhancing discriminative capability through two synergistic strategies. Specifically, we introduce Region-Focused Alignment (RFA) to promote object-centric cross-modal alignment while suppressing background interference. Concurrently, to tackle visual isomorphism, we propose Semantic Perturbation Enhanced Matching (SPEM), which leverages a foreground-purified Semantic Prototype Codebook (SPC) to construct semantically perturbed negatives for fine-grained semantic discrimination. Extensive experiments on the GeoText-1652 benchmark and the unseen ERA dataset demonstrate that GRASP achieves competitive performance in drone-view fine-grained image-text retrieval, validating its effectiveness for cross-modal understanding in aerial scenarios. Our code implementation is available at this https URL .

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-08-11 in cs.MM).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Information Retrieval (cs.IR); Multimedia (cs.MM).
Pagina del lavoro: https://arxiv.org/abs/2608.09270 — 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 2026-10-19T09:13:27.085Z dalla pagina https://arxiv.org/catchup/cs.MM/2026-08-11?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).