Metraipolis › archive › dc_0cd8940ecf3e

ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting — arXiv:2611.03339

Source
arXiv (en)
Original
https://arxiv.org/abs/2611.03339
License (as archived)
CC0-1.0
Archived
2026-11-03T11:43:24.044Z
SHA-256 of the archived text
76bf91cf917839fbdf1c01ef46a6f5520f5234c30a40e5a621b91bc66551f29a
Stable URL of this page
https://metraipolis.com/documento/dc_0cd8940ecf3e

How to cite

ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting — arXiv:2611.03339 — arXiv (en), https://arxiv.org/abs/2611.03339 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_0cd8940ecf3e (Metraipolis archive dc_0cd8940ecf3e, sha256 76bf91cf917839fbdf1c01ef46a6f5520f5234c30a40e5a621b91bc66551f29a)
BibTeX
@misc{dc0cd8940ecf3e,
  title = {ArabGeoText: Tool-Augmented Vision-Language Models for Arabic Geospatial Text Spotting — arXiv:2611.03339},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2611.03339},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_0cd8940ecf3e; sha256 76bf91cf917839fbdf1c01ef46a6f5520f5234c30a40e5a621b91bc66551f29a},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.03339. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Geospatial text spotting involves locating and transcribing geographic labels, such as road names, district names, and landmarks, in raster maps. These labels are often small, densely arranged, and arbitrarily oriented. Although Arabic text recognition has been studied extensively in documents and natural scenes, Arabic geospatial text spotting remains underexplored. We introduce ARABGEOTEXT, an Arabic-centric benchmark covering 970 geographic locations in Riyadh and Jeddah, with 17,875 manually annotated text instances per view type. For each location, we pair an OpenStreetMap (OSM) rendering with a composite created by overlaying that rendering on the corresponding remote sensing (RS) imagery. The paired views preserve label content and pixel geometry, allowing evaluation across different backgrounds. Geographic partitions support in-city and city-disjoint evaluation of detection, recognition, and end-to-end spotting. Experiments with direct Qwen3.5-4B spotting show difficulties in recovering all labels within a tile. We therefore propose a tool-augmented vision-language framework that combines YOLO26 localization and crop rectification with Qwen3.5-4B recognition adapted through low-rank adaptation (LoRA). The framework outperforms direct LoRA-adapted Qwen3.5-4B spotting across both image views and test cities. With localization held fixed, reader adaptation further improves recognition over the pretrained zero-shot reader. The dataset and code will be made publicly 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/2611.03339 — 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 2026-11-03T11:06:37.635Z dalla pagina https://arxiv.org/list/cs.CV/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).