{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T07:07:10Z","timestamp":1788937630602,"version":"build-2803163510"},"publisher-location":"Cham","reference-count":49,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032371317","type":"print"},{"value":"9783032371324","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-3-032-37132-4_18","type":"book-chapter","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:42:08Z","timestamp":1788936128000},"page":"314-331","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["UrbanAlign: Post-hoc Semantic Calibration for VLM-Human Preference Alignment"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4151-2737","authenticated-orcid":false,"given":"Yecheng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rong","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhizhou","family":"Sha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7067-3732","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ce","family":"Hou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wen","family":"Ji","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Huang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunshan","family":"Wan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junhao","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuru","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chunlei","family":"Shi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,9,10]]},"reference":[{"key":"18_CR1","doi-asserted-by":"publisher","first-page":"11","DOI":"10.1023\/A:1006559212014","volume":"11","author":"CG Atkeson","year":"1997","unstructured":"Atkeson, C.G., Moore, A.W., Schaal, S.: Locally weighted learning. Artif. Intell. Rev. 11, 11\u201373 (1997)","journal-title":"Artif. Intell. Rev."},{"key":"18_CR2","unstructured":"Bai, S., et al.: Qwen2.5-VL technical report. arXiv preprint arXiv:2502.13923 (2025)"},{"issue":"3\u20134","key":"18_CR3","first-page":"324","volume":"39","author":"RA Bradley","year":"1952","unstructured":"Bradley, R.A., Terry, M.E.: Rank analysis of incomplete block designs: I. The method of paired comparisons. Biometrika 39(3\u20134), 324\u2013345 (1952)","journal-title":"Biometrika"},{"issue":"3","key":"18_CR4","doi-asserted-by":"publisher","first-page":"331","DOI":"10.1007\/s10208-006-0196-8","volume":"7","author":"A Caponnetto","year":"2007","unstructured":"Caponnetto, A., De Vito, E.: Optimal rates for the regularized least-squares algorithm. Found. Comput. Math. 7(3), 331\u2013368 (2007)","journal-title":"Found. Comput. Math."},{"key":"18_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L.C., Zhu, Y., Papandreou, G., Schroff, F., Adam, H.: Encoder-decoder with atrous separable convolution for semantic image segmentation. In: ECCV, pp. 801\u2013818 (2018)","DOI":"10.1007\/978-3-030-01234-2_49"},{"issue":"368","key":"18_CR6","doi-asserted-by":"publisher","first-page":"829","DOI":"10.1080\/01621459.1979.10481038","volume":"74","author":"WS Cleveland","year":"1979","unstructured":"Cleveland, W.S.: Robust locally weighted regression and smoothing scatterplots. J. Am. Stat. Assoc. 74(368), 829\u2013836 (1979)","journal-title":"J. Am. Stat. Assoc."},{"key":"18_CR7","unstructured":"Du, Y., Li, S., Torralba, A., Tenenbaum, J.B., Mordatch, I.: Improving factuality and reasoning in language models through multiagent debate. In: ICML (2024)"},{"key":"18_CR8","doi-asserted-by":"crossref","unstructured":"Dubey, A., Naik, N., Parikh, D., Raskar, R., Hidalgo, C.A.: Deep learning the city: quantifying urban perception at a global scale. In: ECCV, pp. 196\u2013212 (2016)","DOI":"10.1007\/978-3-319-46448-0_12"},{"key":"18_CR9","unstructured":"Guo, C., Pleiss, G., Sun, Y., Weinberger, K.Q.: On calibration of modern neural networks. In: ICML, vol. 70, pp. 1321\u20131330 (2017)"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Herbrich, R., Minka, T., Graepel, T.: TrueSkill: a Bayesian skill rating system. In: NeurIPS, pp. 569\u2013576 (2006)","DOI":"10.7551\/mitpress\/7503.003.0076"},{"key":"18_CR11","doi-asserted-by":"crossref","unstructured":"Huang, W., Wang, J., Cong, G.: Zero-shot urban function inference with street view images through prompting a pretrained vision-language model. Int. J. Geogr. Inf. Sci. 38(7) (2024)","DOI":"10.1080\/13658816.2024.2347322"},{"key":"18_CR12","unstructured":"Jacobs, J.: The Death and Life of Great American Cities. Random House (1961)"},{"key":"18_CR13","doi-asserted-by":"publisher","first-page":"598","DOI":"10.1177\/000276427101400409","volume":"14","author":"CR Jeffery","year":"1971","unstructured":"Jeffery, C.R.: Crime prevention through environmental design. Am. Behav. Sci. 14, 598\u2013610 (1971)","journal-title":"Am. Behav. Sci."},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Jin, R., Cai, C.: Plausible or misleading? Evaluating the adaption of the Place Pulse 2.0 dataset for predicting subjective perception in Chinese urban landscapes. Habitat Int. 157 (2025)","DOI":"10.1016\/j.habitatint.2025.103333"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Joachims, T.: Optimizing search engines using clickthrough data. In: ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, pp. 133\u2013142 (2002)","DOI":"10.1145\/775047.775067"},{"key":"18_CR16","unstructured":"Koch, G., Zemel, R., Salakhutdinov, R.: Siamese neural networks for one-shot image recognition. In: ICML Deep Learning Workshop (2015)"},{"key":"18_CR17","unstructured":"Koh, P.W., et al.: Concept bottleneck models. In: ICML, pp. 5338\u20135348 (2020)"},{"key":"18_CR18","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: NeurIPS, pp. 9459\u20139474 (2020)"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Liang, T., et al.: Encouraging divergent thinking in large language models through multi-agent debate. In: EMNLP (2024)","DOI":"10.18653\/v1\/2024.emnlp-main.992"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Liu, Y., Zhang, T., Gu, S.: Hybrid concept bottleneck models. In: CVPR (2025)","DOI":"10.1109\/CVPR52734.2025.01879"},{"key":"18_CR21","unstructured":"Liu, Y., Cao, J., Li, Z., He, R., Tan, T.: Breaking mental set to improve reasoning through diverse multi-agent debate. In: ICLR (2025)"},{"key":"18_CR22","unstructured":"Liu, Y., et al.: Aligning with human judgement: the role of pairwise preference in large language model evaluators. In: COLM (2024)"},{"key":"18_CR23","unstructured":"Meng, Y., Michalski, M., Huang, J., Zhang, Y., Abdelzaher, T., Han, J.: Tuning language models as training data generators for augmentation-enhanced few-shot learning. In: ICML (2023)"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Murray, N., Marchesotti, L., Perronnin, F.: AVA: a large-scale database for aesthetic visual analysis. In: CVPR, pp. 2408\u20132415 (2012)","DOI":"10.1109\/CVPR.2012.6247954"},{"key":"18_CR25","unstructured":"Mushkani, R.: Do vision-language models see urban scenes as people do? An urban perception benchmark. arXiv preprint arXiv:2509.14574 (2025)"},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Naik, N., Philipoom, J., Raskar, R., Hidalgo, C.A.: Streetscore\u2014predicting the perceived safety of one million streetscapes. In: CVPR Workshop on Web-scale Vision and Social Media (2014)","DOI":"10.1109\/CVPRW.2014.121"},{"key":"18_CR27","unstructured":"Oikarinen, T., Das, S., Nguyen, L.M., Weng, T.W.: Label-free concept bottleneck models. In: ICLR (2023)"},{"key":"18_CR28","unstructured":"OpenAI: GPT-4o system card. arXiv preprint arXiv:2410.21276 (2024)"},{"key":"18_CR29","doi-asserted-by":"crossref","unstructured":"Ouyang, L., et al.: Training language models to follow instructions with human feedback. In: NeurIPS, pp. 27730\u201327744 (2022)","DOI":"10.52202\/068431-2011"},{"issue":"11","key":"18_CR30","doi-asserted-by":"publisher","first-page":"1092","DOI":"10.1038\/s44284-025-00330-x","volume":"2","author":"M Quintana","year":"2025","unstructured":"Quintana, M., et al.: Global urban visual perception varies across demographics and personalities. Nat. Cities 2(11), 1092\u20131106 (2025)","journal-title":"Nat. Cities"},{"key":"18_CR31","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision. In: ICML, pp. 8748\u20138763 (2021)"},{"issue":"3","key":"18_CR32","doi-asserted-by":"publisher","first-page":"1346","DOI":"10.1214\/aos\/1176325632","volume":"22","author":"D Ruppert","year":"1994","unstructured":"Ruppert, D., Wand, M.P.: Multivariate locally weighted least squares regression. Ann. Stat. 22(3), 1346\u20131370 (1994)","journal-title":"Ann. Stat."},{"issue":"7","key":"18_CR33","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0068400","volume":"8","author":"P Salesses","year":"2013","unstructured":"Salesses, P., Schechtner, K., Hidalgo, C.A.: The collaborative image of the city: mapping the inequality of urban perception. PLoS ONE 8(7), e68400 (2013)","journal-title":"PLoS ONE"},{"key":"18_CR34","doi-asserted-by":"crossref","unstructured":"Srivastava, D., Yan, G., Weng, T.W.: VLG-CBM: training concept bottleneck models with vision-language guidance. In: NeurIPS (2024)","DOI":"10.52202\/079017-2510"},{"key":"18_CR35","doi-asserted-by":"crossref","unstructured":"Sun, Z., et al.: Aligning large multimodal models with factually augmented RLHF. In: Findings of ACL (2024)","DOI":"10.18653\/v1\/2024.findings-acl.775"},{"key":"18_CR36","doi-asserted-by":"crossref","unstructured":"Tan, Z., etal.: Aligning large language models with implicit preferences from user-generated content. In: ACL (2025)","DOI":"10.18653\/v1\/2025.acl-long.384"},{"issue":"4","key":"18_CR37","doi-asserted-by":"publisher","first-page":"273","DOI":"10.1037\/h0070288","volume":"34","author":"LL Thurstone","year":"1927","unstructured":"Thurstone, L.L.: A law of comparative judgment. Psychol. Rev. 34(4), 273\u2013286 (1927)","journal-title":"Psychol. Rev."},{"key":"18_CR38","doi-asserted-by":"crossref","unstructured":"Wang, C., et al.: RoVRM: a robust visual reward model optimized via auxiliary textual preference data. In: AAAI (2025)","DOI":"10.1609\/aaai.v39i24.34721"},{"key":"18_CR39","unstructured":"Wang, X., et al.: Self-consistency improves chain of thought reasoning in language models. In: ICLR (2023)"},{"issue":"3","key":"18_CR40","first-page":"29","volume":"249","author":"JQ Wilson","year":"1982","unstructured":"Wilson, J.Q., Kelling, G.L.: Broken windows: the police and neighborhood safety. Atl. Mon. 249(3), 29\u201338 (1982)","journal-title":"Atl. Mon."},{"key":"18_CR41","unstructured":"Wu, H., et al.: Q-Align: teaching LMMs for visual scoring via discrete text-defined levels. In: ICML (2024)"},{"key":"18_CR42","doi-asserted-by":"crossref","unstructured":"Yan, Y., et al.: UrbanCLIP: learning text-enhanced urban region profiling with contrastive language-image pretraining from the web. In: WWW (2024)","DOI":"10.1145\/3589334.3645378"},{"key":"18_CR43","doi-asserted-by":"crossref","unstructured":"Yang, Y., et al.: Language in a bottle: language model guided concept bottlenecks for interpretable image classification. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01839"},{"key":"18_CR44","doi-asserted-by":"crossref","unstructured":"Ye, J., et al.: ZeroGen: efficient zero-shot learning via dataset generation. In: EMNLP (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.801"},{"key":"18_CR45","unstructured":"Yuksekgonul, M., Wang, M., Zou, J.: Post-hoc concept bottleneck models. In: ICLR. (2023)"},{"key":"18_CR46","unstructured":"Zhan, Y., et al.: Vision-R1: evolving human-free alignment in large vision-language models via vision-guided reinforcement learning. arXiv preprint arXiv:2503.18013 (2025)"},{"key":"18_CR47","doi-asserted-by":"publisher","first-page":"148","DOI":"10.1016\/j.landurbplan.2018.08.020","volume":"180","author":"F Zhang","year":"2018","unstructured":"Zhang, F., et al.: Measuring human perceptions of a large-scale urban region using machine learning. Landsc. Urban Plan. 180, 148\u2013160 (2018)","journal-title":"Landsc. Urban Plan."},{"key":"18_CR48","unstructured":"Zhang, Y., Zhao, R., Huang, Z., Wang, X., Ma, Y., Long, Y.: GenAI models capture urban science but oversimplify complexity. arXiv preprint arXiv:2505.13803 (2025)"},{"key":"18_CR49","unstructured":"Zhao, Y., et al.: Object-level verbalized confidence calibration in vision-language models via semantic perturbation. arXiv preprint arXiv:2504.14848 (2025)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2026"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-37132-4_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T06:42:18Z","timestamp":1788936138000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-37132-4_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9783032371317","9783032371324"],"references-count":49,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-37132-4_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"10 September 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Malm\u00f6","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Sweden","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 September 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2026","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":"eccv2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}