Metraipolis › archive › dc_ec69a8a7827c

GeoContext: One Context Ladder, Two Failure Modes in Vision-Language Geolocation: Flat Reliance on User-Provided Location Context and False Confirmation of Location… — arXiv:2609.05761

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.05761
License (as archived)
CC0-1.0
Archived
2026-10-16T15:06:36.857Z
SHA-256 of the archived text
ebf5c75740e3ca6cba36c42c9962228d48d9e1a3d0b166a666b01103c8f63ab7
Stable URL of this page
https://metraipolis.com/documento/dc_ec69a8a7827c

How to cite

GeoContext: One Context Ladder, Two Failure Modes in Vision-Language Geolocation: Flat Reliance on User-Provided Location Context and False Confirmation of Location… — arXiv:2609.05761 — arXiv (en), https://arxiv.org/abs/2609.05761 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_ec69a8a7827c (Metraipolis archive dc_ec69a8a7827c, sha256 ebf5c75740e3ca6cba36c42c9962228d48d9e1a3d0b166a666b01103c8f63ab7)
BibTeX
@misc{dcec69a8a7827c,
  title = {GeoContext: One Context Ladder, Two Failure Modes in Vision-Language Geolocation: Flat Reliance on User-Provided Location Context and False Confirmation of Location… — arXiv:2609.05761},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.05761},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_ec69a8a7827c; sha256 ebf5c75740e3ca6cba36c42c9962228d48d9e1a3d0b166a666b01103c8f63ab7},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.05761. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Visual geolocation benchmarks typically ask a model where an image was captured without accounting for the location context that users often provide. We introduce GeoContext, a resource supporting two complementary tasks: GeoHint, open-ended localization given a true but coarse location hint, and GeoVerify, binary verification of whether an image was taken within 150 m of a claimed place. GeoContext constructs a context ladder by stratifying nearby reference points according to distance and referenceability, allowing the image to remain fixed while the supplied context varies. The benchmark covers 109 sites in 30 cities and evaluates five vision-language models using 21,933 GeoHint responses and 6,270 GeoVerify responses. Our evaluation reveals three main patterns. First, hint repetition varies by only 1.5 percentage points across referenceability tiers and by less than 3 points across distance bands, while the resulting localization error increases steadily with hint distance. Second, behavior depends strongly on no-context performance: at sites with low no-context accuracy, the median ratio between localization error and hint distance is approximately 1.00, whereas at higher-accuracy sites it ranges from 0.24 to 0.69. After correcting for bias introduced by the site grouping procedure, only one of the five models retains a negative accuracy estimate when given a nearby hint. Third, in GeoVerify, no model reaches d' = 1 for decoys immediately beyond the 150 m tolerance. Model rankings also change when sensitivity is separated from response bias, and 83.8% of false acceptances are reported with confidence of at least 0.8. We release the benchmark, construction pipeline, audit decisions, and scoring code.

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-09-09 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI).
Pagina del lavoro: https://arxiv.org/abs/2609.05761 — 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 2026-10-16T14:49:56.999Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-09-09?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).