{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T20:09:20Z","timestamp":1784059760349,"version":"3.55.0"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,11,1]],"date-time":"2026-11-01T00:00:00Z","timestamp":1793491200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T00:00:00Z","timestamp":1783296000000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000016","name":"U.S. Department of Health and Human Services","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000016","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000002","name":"National Institutes of Health","doi-asserted-by":"publisher","award":["ZIA NR000043"],"award-info":[{"award-number":["ZIA NR000043"]}],"id":[{"id":"10.13039\/100000002","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,11]]},"DOI":"10.1016\/j.neucom.2026.134443","type":"journal-article","created":{"date-parts":[[2026,7,6]],"date-time":"2026-07-06T15:51:21Z","timestamp":1783353081000},"page":"134443","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Robust and scalable representation learning for google street view\u2013based neighborhood indicators"],"prefix":"10.1016","volume":"700","author":[{"given":"Xiaoya","family":"Tang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaohe","family":"Yue","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Heran","family":"Mane","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Daniel","family":"Smolyak","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dapeng","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Quynh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tolga","family":"Tasdizen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134443_bib0005","author":"Bao"},{"key":"10.1016\/j.neucom.2026.134443_bib0010","series-title":"Communities, Neighborhoods, and Health: Expanding the Boundaries of Place","volume":"vol. 1","year":"2011"},{"key":"10.1016\/j.neucom.2026.134443_bib0015","doi-asserted-by":"crossref","first-page":"4623","DOI":"10.1007\/s11263-025-02401-x","article-title":"Multi-source domain adaptation by causal-guided adaptive multimodal diffusion networks","volume":"133","author":"Cai","year":"2025","journal-title":"Int. J. Comput. Vis."},{"key":"10.1016\/j.neucom.2026.134443_bib0020","article-title":"Make source-free transfer great: dynamic uncertainty-driven confident fusion for multi-source-free domain adaptation","author":"Cai","year":"2025","journal-title":"Inf. Fusion"},{"key":"10.1016\/j.neucom.2026.134443_bib0025","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9650","article-title":"Emerging properties in self-supervised vision transformers","author":"Caron","year":"2021"},{"key":"10.1016\/j.neucom.2026.134443_bib0030","first-page":"1","article-title":"RSMamba: remote sensing image classification with state space model","volume":"21","author":"Chen","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.neucom.2026.134443_bib0035","series-title":"International Conference on Machine Learning","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","author":"Chen","year":"2020"},{"key":"10.1016\/j.neucom.2026.134443_bib0040","author":"Chen"},{"key":"10.1016\/j.neucom.2026.134443_bib0045","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"9640","article-title":"An empirical study of training self-supervised vision transformers","author":"Chen","year":"2021"},{"key":"10.1016\/j.neucom.2026.134443_bib0050","first-page":"3965","article-title":"Coatnet: marrying convolution and attention for all data sizes","volume":"34","author":"Dai","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134443_bib0055","series-title":"Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision","first-page":"6878","article-title":"Limited data, unlimited potential: a study on vits augmented by masked autoencoders","author":"Das","year":"2024"},{"key":"10.1016\/j.neucom.2026.134443_bib0060","author":"Deng"},{"key":"10.1016\/j.neucom.2026.134443_bib0065","doi-asserted-by":"crossref","first-page":"125","DOI":"10.1111\/j.1749-6632.2009.05333.x","article-title":"Neighborhoods and health","volume":"1186","author":"Diez Roux","year":"2010","journal-title":"Ann. N. Y. Acad. Sci."},{"key":"10.1016\/j.neucom.2026.134443_bib0070","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12124","article-title":"Cswin transformer: a general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2022"},{"key":"10.1016\/j.neucom.2026.134443_bib0075","author":"Dosovitskiy"},{"key":"10.1016\/j.neucom.2026.134443_bib0080","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"6824","article-title":"Multiscale vision transformers","author":"Fan","year":"2021"},{"key":"10.1016\/j.neucom.2026.134443_bib0085","doi-asserted-by":"crossref","DOI":"10.1016\/j.buildenv.2023.111126","article-title":"Examining the role of passive design indicators in energy burden reduction: insights from a machine learning and deep learning approach","volume":"250","author":"Ghorbany","year":"2024","journal-title":"Build. Environ."},{"key":"10.1016\/j.neucom.2026.134443_bib0090","first-page":"21271","article-title":"Bootstrap your own latent-a new approach to self-supervised learning","volume":"33","author":"Grill","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134443_bib0095","series-title":"First Conference on Language Modeling","article-title":"Mamba: linear-time sequence modeling with selective state spaces","author":"Gu","year":"2024"},{"key":"10.1016\/j.neucom.2026.134443_bib0100","author":"Hassani"},{"key":"10.1016\/j.neucom.2026.134443_bib0105","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6185","article-title":"Neighborhood attention transformer","author":"Hassani","year":"2023"},{"key":"10.1016\/j.neucom.2026.134443_bib0110","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"16000","article-title":"Masked autoencoders are scalable vision learners","author":"He","year":"2022"},{"key":"10.1016\/j.neucom.2026.134443_bib0115","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"9729","article-title":"Momentum contrast for unsupervised visual representation learning","author":"He","year":"2020"},{"key":"10.1016\/j.neucom.2026.134443_bib0120","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.neucom.2026.134443_bib0125","author":"Kaplan"},{"key":"10.1016\/j.neucom.2026.134443_bib0130","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4015","article-title":"Segment anything","author":"Kirillov","year":"2023"},{"key":"10.1016\/j.neucom.2026.134443_bib0135","article-title":"Imagenet classification with deep convolutional neural networks","volume":"25","author":"Krizhevsky","year":"2012","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134443_bib0140","author":"Lee"},{"key":"10.1016\/j.neucom.2026.134443_bib0145","author":"Li"},{"key":"10.1016\/j.neucom.2026.134443_bib0150","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"4804","article-title":"Mvitv2: improved multiscale vision transformers for classification and detection","author":"Li","year":"2022"},{"key":"10.1016\/j.neucom.2026.134443_bib0155","doi-asserted-by":"crossref","first-page":"103031","DOI":"10.52202\/079017-3273","article-title":"VMamba: visual state space model","volume":"37","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134443_bib0160","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134443_bib0165","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"181","article-title":"Exploring the limits of weakly supervised pretraining","author":"Mahajan","year":"2018"},{"key":"10.1016\/j.neucom.2026.134443_bib0170","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"6894","article-title":"Vim4path: self-supervised vision Mamba for histopathology images","author":"Nasiri-Sarvi","year":"2024"},{"key":"10.1016\/j.neucom.2026.134443_bib0175","doi-asserted-by":"crossref","first-page":"377","DOI":"10.1136\/ip-2023-045153","article-title":"Leveraging computer vision for predicting collision risks: a cross-sectional analysis of 2019\u20132021 fatal collisions in the USA","volume":"31","author":"Nguyen","year":"2025","journal-title":"Injury prevention"},{"key":"10.1016\/j.neucom.2026.134443_bib0180","article-title":"Using Google street view to examine associations between built environment characteristics and US health outcomes","volume":"14","author":"Nguyen","year":"2019","journal-title":"Prev. Med. Rep."},{"key":"10.1016\/j.neucom.2026.134443_bib0185","doi-asserted-by":"crossref","DOI":"10.2196\/publichealth.5869","article-title":"Building a national neighborhood dataset from geotagged twitter data for indicators of happiness, diet, and physical activity","volume":"2","author":"Nguyen","year":"2016","journal-title":"JMIR public health and surveillance"},{"key":"10.1016\/j.neucom.2026.134443_bib0190","author":"Oquab"},{"key":"10.1016\/j.neucom.2026.134443_bib0195","series-title":"International Conference on Machine Learning","first-page":"4055","article-title":"Image transformer","author":"Parmar","year":"2018"},{"key":"10.1016\/j.neucom.2026.134443_bib0200","author":"Patro"},{"key":"10.1016\/j.neucom.2026.134443_bib0205","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2025.111279","article-title":"Mamba-360: survey of state space models as transformer alternative for long sequence modelling: methods, applications, and challenges","volume":"159","author":"Patro","year":"2025","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.neucom.2026.134443_bib0210","first-page":"12116","article-title":"Do vision transformers see like convolutional neural networks?","volume":"34","author":"Raghu","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134443_bib0215","doi-asserted-by":"crossref","first-page":"20","DOI":"10.1186\/s12942-016-0050-z","article-title":"Emerging technologies to measure neighborhood conditions in public health: implications for interventions and next steps","volume":"15","author":"Schootman","year":"2016","journal-title":"Int. J. Health Geogr."},{"key":"10.1016\/j.neucom.2026.134443_bib0220","author":"Sim\u00e9oni"},{"key":"10.1016\/j.neucom.2026.134443_bib0225","doi-asserted-by":"crossref","first-page":"79","DOI":"10.1023\/A:1016021108513","article-title":"How neighborhood features affect quality of life","volume":"59","author":"Sirgy","year":"2002","journal-title":"Soc. Indic. Res."},{"key":"10.1016\/j.neucom.2026.134443_bib0230","author":"Tang"},{"key":"10.1016\/j.neucom.2026.134443_bib0235","series-title":"Medical Imaging with Deep Learning-Short Papers","article-title":"Dynamic scale for transformer","author":"Tang","year":"2025"},{"key":"10.1016\/j.neucom.2026.134443_bib0240","author":"Tang"},{"key":"10.1016\/j.neucom.2026.134443_bib0245","series-title":"2024 IEEE 7th International Conference on Multimedia Information Processing and Retrieval (MIPR)","first-page":"267","article-title":"Uu-Mamba: uncertainty-aware u-mamba for cardiac image segmentation","author":"Tsai","year":"2024"},{"key":"10.1016\/j.neucom.2026.134443_bib0250","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134443_bib0255","doi-asserted-by":"crossref","first-page":"3123","DOI":"10.1109\/TPAMI.2023.3341806","article-title":"Crossformer++: a versatile vision transformer hinging on cross-scale attention","volume":"46","author":"Wang","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2026.134443_bib0260","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"568","article-title":"Pyramid vision transformer: a versatile backbone for dense prediction without convolutions","author":"Wang","year":"2021"},{"key":"10.1016\/j.neucom.2026.134443_bib0265","doi-asserted-by":"crossref","first-page":"415","DOI":"10.1007\/s41095-022-0274-8","article-title":"Pvt v2: improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"10.1016\/j.neucom.2026.134443_bib0270","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"22","article-title":"Cvt: introducing convolutions to vision transformers","author":"Wu","year":"2021"},{"key":"10.1016\/j.neucom.2026.134443_bib0275","doi-asserted-by":"crossref","DOI":"10.1016\/j.cities.2025.105890","article-title":"Do protected cycle lanes make cities more bike-friendly? Integrating street view images with deep learning techniques","volume":"161","author":"Xu","year":"2025","journal-title":"Cities"},{"key":"10.1016\/j.neucom.2026.134443_bib0280","author":"Xu"},{"key":"10.1016\/j.neucom.2026.134443_bib0285","series-title":"International Conference on Medical Image Computing and Computer-Assisted Intervention","first-page":"134","article-title":"Cardiovascular disease detection from multi-view chest x-rays with bi-Mamba","author":"Yang","year":"2024"},{"key":"10.1016\/j.neucom.2026.134443_bib0290","author":"Ye"},{"key":"10.1016\/j.neucom.2026.134443_bib0295","doi-asserted-by":"crossref","DOI":"10.3390\/ijerph191912095","article-title":"Using convolutional neural networks to derive neighborhood built environments from Google street view images and examine their associations with health outcomes","volume":"19","author":"Yue","year":"2022","journal-title":"Int. J. Environ. Res. Public Health"},{"key":"10.1016\/j.neucom.2026.134443_bib0300","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"12104","article-title":"Scaling vision transformers","author":"Zhai","year":"2022"},{"key":"10.1016\/j.neucom.2026.134443_bib0305","first-page":"1","article-title":"Structured adversarial self-supervised learning for robust object detection in remote sensing images","volume":"62","author":"Zhang","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134443_bib0310","first-page":"1","article-title":"Integrally mixing pyramid representations for anchor-free object detection in aerial imagery","volume":"21","author":"Zhang","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.neucom.2026.134443_bib0315","article-title":"Dynamic mutual learning for object detection in aerial imagery","volume":"64","author":"Zhang","year":"2026","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.neucom.2026.134443_bib0320","series-title":"European Conference on Computer Vision","first-page":"649","article-title":"Colorful image colorization","author":"Zhang","year":"2016"},{"key":"10.1016\/j.neucom.2026.134443_bib0325","author":"Zhou"},{"key":"10.1016\/j.neucom.2026.134443_bib0330","author":"Zhu"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018412?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226018412?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,14]],"date-time":"2026-07-14T19:34:33Z","timestamp":1784057673000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226018412"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,11]]},"references-count":66,"alternative-id":["S0925231226018412"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134443","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,11]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Robust and scalable representation learning for google street view\u2013based neighborhood indicators","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134443","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier B.V.","name":"copyright","label":"Copyright"}],"article-number":"134443"}}