# G^3: Geolocation via Guidebook Grounding

arXiv: https://arxiv.org/abs/2211.15521 · HTML: https://mlsanity.com/paper/2211.15521/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 31 references that are in the map.
- First posted on arXiv 28 Nov 2022.

## Builds on (most cited first, 16 of 16)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [Per-Pixel Classification is Not All You Need for Semantic Segmentation](https://mlsanity.com/paper/2107.06278/) (2021)
- [Effective Approaches to Attention-based Neural Machine Translation](https://mlsanity.com/paper/1508.04025/) (2015)
- [Quantifying the Carbon Emissions of Machine Learning](https://mlsanity.com/paper/1910.09700/) (2019)
- [End-to-End Learning of Visual Representations from Uncurated Instructional Videos](https://mlsanity.com/paper/1912.06430/) (2019)
- [An Empirical Study of GPT-3 for Few-Shot Knowledge-Based VQA](https://mlsanity.com/paper/2109.05014/) (2021)
- [KRISP: Integrating Implicit and Symbolic Knowledge for Open-Domain Knowledge-Based VQA](https://mlsanity.com/paper/2012.11014/) (2020)
- [PlaNet - Photo Geolocation with Convolutional Neural Networks](https://mlsanity.com/paper/1602.05314/) (2016)
- [Learning with Latent Language](https://mlsanity.com/paper/1711.00482/) (2017)
- [Good News, Everyone! Context driven entity-aware captioning for news images](https://mlsanity.com/paper/1904.01475/) (2019)
- [Learning to Win by Reading Manuals in a Monte-Carlo Framework](https://mlsanity.com/paper/1401.5390/) (2014)
- [RTFM: Generalising to Novel Environment Dynamics via Reading](https://mlsanity.com/paper/1910.08210/) (2019)
- [Interpretable Semantic Photo Geolocation](https://mlsanity.com/paper/2104.14995/) (2021)
- [Shaping Visual Representations with Language for Few-shot Classification](https://mlsanity.com/paper/1911.02683/) (2019)
- [Guide Me: Interacting with Deep Networks](https://mlsanity.com/paper/1803.11544/) (2018)

## Built on by (most cited first, 12 of 12)

- [PIGEON: Predicting Image Geolocations](https://mlsanity.com/paper/2307.05845/) (2023)
- [Learning Generalized Zero-Shot Learners for Open-Domain Image Geolocalization](https://mlsanity.com/paper/2302.00275/) (2023)
- [OpenStreetView-5M: The Many Roads to Global Visual Geolocation](https://mlsanity.com/paper/2404.18873/) (2024)
- [GeoReasoner: Geo-localization with Reasoning in Street Views using a Large Vision-Language Model](https://mlsanity.com/paper/2406.18572/) (2024)
- [Towards Interactive Global Geolocation Assistant](https://mlsanity.com/paper/2412.08907/) (2024)
- [NAVIG: Natural Language-guided Analysis with Vision Language Models for Image Geo-localization](https://mlsanity.com/paper/2502.14638/) (2025)
- [Diffusion Models as Data Mining Tools](https://mlsanity.com/paper/2408.02752/) (2024)
- [Image-based Geo-localization for Robotics: Are Black-box Vision-Language Models there yet?](https://mlsanity.com/paper/2501.16947/) (2025)
- [PuzzleGPT: Emulating Human Puzzle-Solving Ability for Time and Location Prediction](https://mlsanity.com/paper/2501.14210/) (2025)
- [GeoSURGE: Geo-localization using Semantic Fusion with Hierarchy of Geographic Embeddings](https://mlsanity.com/paper/2510.01448/) (2025)
- [Beyond Memorization: A Multi-Modal Ordinal Regression Benchmark to Expose Popularity Bias in Vision-Language Models](https://mlsanity.com/paper/2512.21337/) (2025)
- [Enhancing Worldwide Image Geolocation by Ensembling Satellite-Based Ground-Level Attribute Predictors](https://mlsanity.com/paper/2407.13862/) (2024)

## Abstract (arXiv)

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 class-discriminative 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.