{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T06:37:15Z","timestamp":1768891035803,"version":"3.49.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031773884","type":"print"},{"value":"9783031773891","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-77389-1_19","type":"book-chapter","created":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:32:20Z","timestamp":1737484340000},"page":"243-254","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Leveraging Zero-Shot Learning on\u00a0Street-View Imagery for\u00a0Built Environment Variable Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4093-193X","authenticated-orcid":false,"given":"Siyuan","family":"Yao","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9588-0527","authenticated-orcid":false,"given":"Siavash","family":"Ghorbany","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4141-9655","authenticated-orcid":false,"given":"Matthew","family":"Sisk","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2583-1161","authenticated-orcid":false,"given":"Ming","family":"Hu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0859-3619","authenticated-orcid":false,"given":"Chaoli","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,1,22]]},"reference":[{"key":"19_CR1","doi-asserted-by":"crossref","unstructured":"Alhasoun, F., Gonz\u00e1lez, M.: Urban street contexts classification using convolutional neural networks and streets imagery. In: Proceedings of IEEE International Conference on Machine Learning and Applications, pp. 1198\u20131204 (2019)","DOI":"10.1109\/ICMLA.2019.00198"},{"key":"19_CR2","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. In: Proceedings of International Conference on Learning Representations (2021)"},{"issue":"50","key":"19_CR3","doi-asserted-by":"publisher","first-page":"13108","DOI":"10.1073\/pnas.1700035114","volume":"114","author":"T Gebru","year":"2017","unstructured":"Gebru, T., et al.: Using deep learning and Google street view to estimate the demographic makeup of neighborhoods across the United States. Proc. Natl. Acad. Sci. 114(50), 13108\u201313113 (2017)","journal-title":"Proc. Natl. Acad. Sci."},{"key":"19_CR4","volume":"114","author":"S Ghorbany","year":"2024","unstructured":"Ghorbany, S., Hu, M., Sisk, M., Yao, S., Wang, C.: Passive over active: how low-cost strategies influence urban energy equity. Sustain. Urban Areas 114, 105723 (2024)","journal-title":"Sustain. Urban Areas"},{"key":"19_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2023.111126","volume":"250","author":"S Ghorbany","year":"2024","unstructured":"Ghorbany, S., et al.: Examining the role of passive design indicators in energy burden reduction: Insights from a machine learning and deep learning approach. Build. Environ. 250, 111126 (2024)","journal-title":"Build. Environ."},{"key":"19_CR6","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1016\/j.buildenv.2018.02.042","volume":"134","author":"FY Gong","year":"2018","unstructured":"Gong, F.Y., Zeng, Z.C., Zhang, F., Li, X., Ng, E., Norford, L.K.: Mapping sky, tree, and building view factors of street canyons in a high-density urban environment. Build. Environ. 134, 155\u2013167 (2018)","journal-title":"Build. Environ."},{"key":"19_CR7","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"19_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.buildenv.2019.106424","volume":"167","author":"CB Hu","year":"2020","unstructured":"Hu, C.B., Zhang, F., Gong, F.Y., Ratti, C., Li, X.: Classification and mapping of urban canyon geometry using Google street view images and deep multitask learning. Build. Environ. 167, 106424 (2020)","journal-title":"Build. Environ."},{"issue":"3","key":"19_CR9","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0212814","volume":"14","author":"L Ilic","year":"2019","unstructured":"Ilic, L., Sawada, M., Zarzelli, A.: Deep mapping gentrification in a large Canadian city using deep learning and Google street view. PLoS ONE 14(3), e0212814 (2019)","journal-title":"PLoS ONE"},{"key":"19_CR10","doi-asserted-by":"crossref","unstructured":"Kang, J., K\u00f6rner, M., Wang, Y., Taubenb\u00f6ck, H., Zhu, X.X.: Building instance classification using street view images. ISPRS J. Photogrammetry Remote Sens. 145(A), 44\u201359 (2018)","DOI":"10.1016\/j.isprsjprs.2018.02.006"},{"key":"19_CR11","unstructured":"Kim, W., Son, B., Kim, I.: ViLT: vision-and-language transformer without convolution or region supervision. In: Proceedings of the IEEE International Conference on Machine Learning, pp. 5583\u20135594 (2021)"},{"key":"19_CR12","doi-asserted-by":"crossref","unstructured":"Law, S., Paige, B., Russell, C.: Take a look around: Using street view and satellite images to estimate house prices. ACM Trans. Intell. Syst. Technol. 10(5), 54:1\u201354:19 (2019)","DOI":"10.1145\/3342240"},{"issue":"4","key":"19_CR13","doi-asserted-by":"publisher","first-page":"681","DOI":"10.1080\/13658816.2018.1555832","volume":"34","author":"S Law","year":"2020","unstructured":"Law, S., Seresinhe, C.I., Shen, Y., Gutierrez-Roig, M.: Street-frontage-net: urban image classification using deep convolutional neural networks. Int. J. Geogr. Inf. Sci. 34(4), 681\u2013707 (2020)","journal-title":"Int. J. Geogr. Inf. Sci."},{"key":"19_CR14","unstructured":"Li, J., Li, D., Xiong, C., Hoi, S.: BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In: Proceedings of International Conference on Machine Learning, pp. 12888\u201312900 (2022)"},{"key":"19_CR15","unstructured":"Li, L., Tompkin, J., Michalatos, P., Pfister, H.: Hierarchical visual feature analysis for city street view datasets. In: Proceedings of IEEE VIS Workshop on Visual Analytics for Deep Learning (2017)"},{"issue":"6","key":"19_CR16","doi-asserted-by":"publisher","first-page":"819","DOI":"10.1080\/15481603.2017.1338389","volume":"54","author":"X Li","year":"2017","unstructured":"Li, X., Zhang, C., Li, W.: Building block level urban land-use information retrieval based on Google street view images. GIScience Remote Sens. 54(6), 819\u2013835 (2017)","journal-title":"GIScience Remote Sens."},{"key":"19_CR17","doi-asserted-by":"publisher","unstructured":"Lindenthal, T., Johnson, E.B.: Machine learning, architectural styles and property values. J. Real Estate Finan. Econ. (2021). https:\/\/doi.org\/10.1007\/s11146-021-09845-1","DOI":"10.1007\/s11146-021-09845-1"},{"key":"19_CR18","unstructured":"Liu, H., Li, C., Wu, Q., Lee, Y.J.: Visual instruction tuning. In: Proceedings of Advances in Neural Information Processing Systems (2023)"},{"key":"19_CR19","doi-asserted-by":"crossref","unstructured":"Liu, S., et al.: Grounding DINO: marrying DINO with grounded pre-training for open-set object detection. arXiv preprint arXiv:2303.05499 (2023)","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"19_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"19_CR21","doi-asserted-by":"crossref","unstructured":"Liu, Z., Mao, H., Wu, C.Y., Feichtenhofer, C., Darrell, T., Xie, S.: A ConvNet for the 2020s. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 11976\u201311986 (2022)","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"19_CR22","doi-asserted-by":"publisher","first-page":"657","DOI":"10.1109\/TIP.2019.2932502","volume":"29","author":"W Min","year":"2020","unstructured":"Min, W., Mei, S., Liu, L., Wang, Y., Jiang, S.: Multi-task deep relative attribute learning for visual urban perception. IEEE Trans. Image Process. 29, 657\u2013669 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"19_CR23","doi-asserted-by":"crossref","unstructured":"Naik, N., Philipoom, J., Raskar, R., Hidalgo, C.: Streetscore \u2013 predicting the perceived safety of one million streetscapes. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 793\u2013799 (2014)","DOI":"10.1109\/CVPRW.2014.121"},{"key":"19_CR24","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: Proceedings of International Conference on Machine Learning, pp. 8748\u20138763 (2021)"},{"key":"19_CR25","doi-asserted-by":"crossref","unstructured":"Redmon, J., Divvala, S., Girshick, R., Farhadi, A.: You only look once: unified, real-time object detection. In: Proceedings of IEEE Conference on Computer Vision and Pattern Recognition, pp. 779\u2013788 (2016)","DOI":"10.1109\/CVPR.2016.91"},{"key":"19_CR26","unstructured":"Ren, S., He, K., Girshick, R., Sun, J.: Faster R-CNN: towards real-time object detection with region proposal networks. In: Proceedings of Advances in Neural Information Processing Systems, pp. 91\u201399 (2015)"},{"key":"19_CR27","doi-asserted-by":"crossref","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: Proceedings of International Conference on Learning Representations (2015)","DOI":"10.1109\/ICCV.2015.314"},{"key":"19_CR28","doi-asserted-by":"crossref","unstructured":"Starzy\u0144ska-Grze\u015b, M.B., Roussel, R., Jacoby, S., Asadipour, A.: Computer vision-based analysis of buildings and built environments: a systematic review of current approaches. ACM Comput. Surv. 55(13s), 284:1\u2013284:25 (2023)","DOI":"10.1145\/3578552"},{"key":"19_CR29","doi-asserted-by":"crossref","unstructured":"Suel, E., Polak, J.W., Bennett, J.E., Ezzati, M.: Measuring social, environmental and health inequalities using deep learning and street imagery. Sci. Rep. 9, 6229:1\u20136229:10 (2019)","DOI":"10.1038\/s41598-019-42036-w"},{"key":"19_CR30","unstructured":"Tan, M., Le, Q.: EfficientNet: rethinking model scaling for convolutional neural networks. In: Proceedings of International Conference on Machine Learning, pp. 6105\u20136114 (2019)"},{"issue":"15","key":"19_CR31","doi-asserted-by":"publisher","first-page":"3118","DOI":"10.1177\/0042098020957198","volume":"58","author":"M Wang","year":"2021","unstructured":"Wang, M., Vermeulen, F.: Life between buildings from a street view image: what do big data analytics reveal about neighbourhood organisational vitality? Urban Studies 58(15), 3118\u20133139 (2021)","journal-title":"Urban Studies"},{"issue":"8","key":"19_CR32","first-page":"1439","volume":"46","author":"Y Ye","year":"2019","unstructured":"Ye, Y., Zeng, W., Shen, Q., Zhang, X., Lu, Y.: The visual quality of streets: a human-centered continuous measurement based on machine learning algorithms and street view images. Environ. Plann. B: Urban Anal. City Sci. 46(8), 1439\u20131457 (2019)","journal-title":"Environ. Plann. B: Urban Anal. City Sci."},{"key":"19_CR33","doi-asserted-by":"publisher","first-page":"147","DOI":"10.1016\/j.apgeog.2016.09.024","volume":"76","author":"L Yin","year":"2016","unstructured":"Yin, L., Wang, Z.: Measuring visual enclosure for street walkability: using machine learning algorithms and Google street view imagery. Appl. Geogr. 76, 147\u2013153 (2016)","journal-title":"Appl. Geogr."},{"key":"19_CR34","doi-asserted-by":"publisher","first-page":"5912","DOI":"10.1109\/TIP.2020.2986894","volume":"29","author":"Z Zeng","year":"2020","unstructured":"Zeng, Z., Wu, M., Zeng, W., Fu, C.W.: Deep recognition of vanishing-point-constrained building planes in urban street views. IEEE Trans. Image Process. 29, 5912\u20135923 (2020)","journal-title":"IEEE Trans. Image Process."},{"key":"19_CR35","doi-asserted-by":"crossref","unstructured":"Zhong, T., Ye, C., Wang, Z., Tang, G., Zhang, W., Ye, Y.: City-scale mapping of urban fa\u00e7ade color using street-view imagery. Remote Sens. 13(8), 1591:1\u20131591:17 (2021)","DOI":"10.3390\/rs13081591"}],"container-title":["Lecture Notes in Computer Science","Advances in Visual Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-77389-1_19","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,21]],"date-time":"2025-01-21T18:32:41Z","timestamp":1737484361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-77389-1_19"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9783031773884","9783031773891"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-77389-1_19","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"22 January 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ISVC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Symposium on Visual Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lake Tahoe, NV","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"USA","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21 October 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"19","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"isvc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.isvc.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}