{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/deep-learning-the-city-quantifying-urban","title":"Deep Learning the City : Quantifying Urban Perception At A Global Scale","arxiv_id":"1608.01769","date":"2016-08-05","proceeding":null,"authors":["Abhimanyu Dubey","Nikhil Naik","Devi Parikh","Ramesh Raskar","César A. Hidalgo"],"abstract":"Computer vision methods that quantify the perception of urban environment are\nincreasingly being used to study the relationship between a city's physical\nappearance and the behavior and health of its residents. Yet, the throughput of\ncurrent methods is too limited to quantify the perception of cities across the\nworld. To tackle this challenge, we introduce a new crowdsourced dataset\ncontaining 110,988 images from 56 cities, and 1,170,000 pairwise comparisons\nprovided by 81,630 online volunteers along six perceptual attributes: safe,\nlively, boring, wealthy, depressing, and beautiful. Using this data, we train a\nSiamese-like convolutional neural architecture, which learns from a joint\nclassification and ranking loss, to predict human judgments of pairwise image\ncomparisons. Our results show that crowdsourcing combined with neural networks\ncan produce urban perception data at the global scale.","url_abs":"http://arxiv.org/abs/1608.01769v2","url_pdf":"http://arxiv.org/pdf/1608.01769v2.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"deep-learning-the-city-quantifying-urban","repo_url":"https://github.com/aleksandrskoselevs/place-pulse-dataset","is_official":0,"mentioned_in_paper":0,"mentioned_in_github":1,"framework":"pytorch","reach":null}],"tasks":[{"task_slug":"classification","task_name":"General Classification"}],"methods":[],"datasets_introduced":[{"slug":"place-pulse-2-0","name":"Place Pulse 2.0","full_name":""}],"methods_introduced":[],"results":[],"syntology":{"atlas_url":"https://app.syntology.ai/?focus=1608.01769","mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}