Lune

EMNLP Findings2022

G3: Geolocation via Guidebook Grounding

Grace Luo, Giscard Biamby, Trevor Darrell, Daniel Fried, Anna Rohrbach

Abstract

We demonstrate how language can improve geolocation: the task of predicting the location where an image was taken. Here we study explicit knowledge from human-written guidebooks that describe the salient and classdiscriminative visual features humans use for geolocation. We propose the task of Geolocation via Guidebook Grounding that uses a dataset of StreetView images from a diverse set of locations and an associated textual guidebook for GeoGuessr, a popular interactive geolocation game. Our approach predicts a country for each image by attending over the clues automatically extracted from the guidebook. Supervising attention with country-level pseudo labels achieves the best performance. Our approach substantially outperforms a state-of-the-art image-only geolocation method, with an improvement of over 5% in Top-1 accuracy. Our dataset and code can be found at https://github.com/g-luo/ geolocation_via_guidebook_grounding.

Ask Lune

Know this paper in minutes, not an afternoon.

Lune can read every page of it and the top-tier papers that cite it, and gives you its claims, its evidence and its limits, each one cited to the paper it comes from. No skimming, no AI slop.

4 top-tier papers have cited it since. Know what they found before your reviewers do.

Questions to start from

Lune can draw on

the full paper · the top-tier papers that cite it · related work

Get the answer

Free to start. No credit card required.

Lineage

  • GeoRC: A Benchmark for Geolocation Reasoning Chains cites GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
  • GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings cites GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model
  • GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings cites PIGEON: Predicting Image Geolocations
  • GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings cites Learning Transferable Visual Models From Natural Language Supervision
  • GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model cites Per-Pixel Classification is Not All You Need for Semantic Segmentation
  • GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model cites Learning Transferable Visual Models From Natural Language Supervision
  • PIGEON: Predicting Image Geolocations cites Learning Transferable Visual Models From Natural Language Supervision
  • Learning Transferable Visual Models From Natural Language Supervision cites End-to-End Learning of Visual Representations From Uncurated Instructional Videos
Builds onCited byLeft to right by year; the more cited, the higher.

Cited by top-tier papers4

  1. GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language ModelLing Li, Yu Ye, Bingchuan Jiang, Wei ZengICML 2024 · 35 citations
  2. GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic EmbeddingsAngel Daruna, Nicholas Meegan, Han-Pang Chiu, Supun Samarasekera et al.CVPR 2026 · 2 citations
  3. GeoRC: A Benchmark for Geolocation Reasoning ChainsMohit Talreja, Joshua Diao, Jim James, Radu Casapu et al.ACL 2026 · 1 citation
  4. PIGEON: Predicting Image GeolocationsLukas Haas, Michal Skreta, Silas Alberti, Chelsea FinnCVPR 2024

Builds on5

  1. Learning Transferable Visual Models From Natural Language SupervisionAlec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh et al.ICML 2021 · 47,906 citations
  2. Per-Pixel Classification is Not All You Need for Semantic SegmentationBowen Cheng, Alexander G. Schwing, Alexander KirillovNeurIPS 2021 · 2,196 citations
  3. Advisable Learning for Self-Driving Vehicles by Internalizing Observation-to-Action RulesJinkyu Kim, Suhong Moon, Anna Rohrbach, Trevor Darrell et al.CVPR 2020
  4. KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQAKenneth Marino, Xinlei Chen, Devi Parikh, Abhinav Gupta et al.CVPR 2021
  5. End-to-End Learning of Visual Representations From Uncurated Instructional VideosAntoine Miech, Jean-Baptiste Alayrac, Lucas Smaira, Ivan Laptev et al.CVPR 2020

Related papers

  1. Recognition through Reasoning: Reinforcing Image Geo-localization with Large Vision-Language ModelsLing Li, Yao Zhou, Yuxuan Liang, Fugee Tsung et al.NeurIPS 2025 · 30 citations
  2. Where We Are and What We're Looking At: Query Based Worldwide Image Geo-localization Using Hierarchies and ScenesBrandon Clark, Alec Kerrigan, Parth Parag Kulkarni, Vicente Vivanco Cepeda et al.CVPR 2023
  3. GeoRanker: Distance-Aware Ranking for Worldwide Image GeolocalizationPengyue Jia, Seongheon Park, Song Gao, Xiangyu Zhao et al.NeurIPS 2025 · 22 citations
  4. Where am I? Cross-View Geo-localization with Natural Language DescriptionsJunyan Ye, Honglin Lin, Leyan Ou, Dairong Chen et al.ICCV 2025 · 11 citations
  5. GRE Suite: Geo-localization Inference via Fine-Tuned Vision-Language Models and Enhanced Reasoning ChainsChun Wang, Xiaojun Ye, Xiaoran Pan, Zihao Pan et al.NeurIPS 2025 · 18 citations
Dusk over the sea between two cliffs drawn in fine vertical lines