Assessing the spatial accuracy of geocoding flood-related imagery using Vision Language Models

• Published in: Spatial information research (Online) Vol. 33; no. 2; p. 15
• Main Authors: Schmidt, Sebastian, Díaz Fragachan, Eleonor, Arifi, Dorian, Hanny, David, Resch, Bernd
• Format: Journal Article
• Language: English
• Published: 대한공간정보학회 01.04.2025
• Subjects: 공학일반

While the capabilities of large language models and visual language models for various classification tasks have advanced significantly, their potential for location inference remains largely underexplored. Therefore, this study evaluates the performance of four prominent models — BLIP-2, LLaVA1.6,...