Geolocation with Real Human Gameplay Data: A Large-Scale Dataset and Human-Like Reasoning Framework

TL;DR

This paper introduces a large-scale human gameplay dataset for geolocation, a novel reasoning framework called GeoCoT, and an evaluation metric, significantly advancing the accuracy and interpretability of geolocation models.

Contribution

The paper presents a comprehensive geolocation framework with a new large-scale dataset, a multi-step reasoning method, and an evaluation metric, addressing key limitations of existing approaches.

Findings

GeoComp dataset contains 25 million entries and 3 million geo-tagged locations.

GeoCoT improves geolocation accuracy by up to 25%.

The framework enhances interpretability of geolocation reasoning.

Abstract

Geolocation, the task of identifying an image's location, requires complex reasoning and is crucial for navigation, monitoring, and cultural preservation. However, current methods often produce coarse, imprecise, and non-interpretable localization. A major challenge lies in the quality and scale of existing geolocation datasets. These datasets are typically small-scale and automatically constructed, leading to noisy data and inconsistent task difficulty, with images that either reveal answers too easily or lack sufficient clues for reliable inference. To address these challenges, we introduce a comprehensive geolocation framework with three key components: GeoComp, a large-scale dataset; GeoCoT, a novel reasoning method; and GeoEval, an evaluation metric, collectively designed to address critical challenges and drive advancements in geolocation research. At the core of this framework is GeoComp (Geolocation Competition Dataset), a large-scale dataset collected from a geolocation game platform involving 740K users over two years. It comprises 25 million entries of metadata and 3 million geo-tagged locations spanning much of the globe, with each location annotated thousands to tens of thousands of times by human users. The dataset offers diverse difficulty levels for detailed analysis and highlights key gaps in current models. Building on this dataset, we propose Geographical Chain-of-Thought (GeoCoT), a novel multi-step reasoning framework designed to enhance the reasoning capabilities of Large Vision Models (LVMs) in geolocation tasks. GeoCoT improves performance by integrating contextual and spatial cues through a multi-step process that mimics human geolocation reasoning. Finally, using the GeoEval metric, we demonstrate that GeoCoT significantly boosts geolocation accuracy by up to 25% while enhancing interpretability.