{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T11:10:01Z","timestamp":1755861001360,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":45,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-sa\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2036, 62302261, 62272260"],"award-info":[{"award-number":["U21B2036, 62302261, 62272260"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,29]]},"DOI":"10.1145\/3678717.3691278","type":"proceedings-article","created":{"date-parts":[[2024,11,22]],"date-time":"2024-11-22T06:29:21Z","timestamp":1732256961000},"page":"270-281","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["M3 LUC: Multi-modal Model for Urban Land-Use Classification"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-3421-3387","authenticated-orcid":false,"given":"Sibo","family":"Li","sequence":"first","affiliation":[{"name":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2506-7370","authenticated-orcid":false,"given":"Xin","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0442-7071","authenticated-orcid":false,"given":"Yuming","family":"Lin","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5617-1659","authenticated-orcid":false,"given":"Yong","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, BNRist, Tsinghua University, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,11,22]]},"reference":[{"key":"e_1_3_2_1_1_1","unstructured":"2024. POIs Dataset. https:\/\/www.poi86.com\/."},{"key":"e_1_3_2_1_2_1","volume-title":"Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al.","author":"Achiam Josh","year":"2023","unstructured":"Josh Achiam, Steven Adler, Sandhini Agarwal, Lama Ahmad, Ilge Akkaya, Florencia Leoni Aleman, Diogo Almeida, Janko Altenschmidt, Sam Altman, Shyamal Anadkat, et al. 2023. Gpt-4 technical report. arXiv preprint arXiv:2303.08774 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01957"},{"key":"e_1_3_2_1_4_1","unstructured":"Arnap. 2024. Arnap API. https:\/\/lbs.amap.com\/api\/webservice\/guide\/api\/search\/."},{"key":"e_1_3_2_1_5_1","unstructured":"Jinze Bai Shuai Bai Yunfei Chu Zeyu Cui Kai Dang Xiaodong Deng Yang Fan Wenbin Ge Yu Han Fei Huang et al. 2023. Qwen technical report. arXiv preprint arXiv:2309.16609 (2023)."},{"key":"e_1_3_2_1_6_1","unstructured":"Baidu. 2024. EasyData smart data platform. http:\/\/cloud.baidu.com\/."},{"key":"e_1_3_2_1_7_1","volume-title":"Understanding dropout. Advances in neural information processing systems 26","author":"Baldi Pierre","year":"2013","unstructured":"Pierre Baldi and Peter J Sadowski. 2013. Understanding dropout. Advances in neural information processing systems 26 (2013)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1080\/20964471.2021.1939243"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_10_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_11_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_12_1","unstructured":"Esri. 2022. World Imagery. https:\/\/www.arcgis.com\/home\/item.html?id=10df2279f9684e4a9f6a7f08febac2a9%2F."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3091848"},{"key":"e_1_3_2_1_14_1","volume-title":"Measuring nominal scale agreement among many raters. Psychological bulletin 76, 5","author":"Fleiss Joseph L","year":"1971","unstructured":"Joseph L Fleiss. 1971. Measuring nominal scale agreement among many raters. Psychological bulletin 76, 5 (1971), 378."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.scib.2019.12.007"},{"key":"e_1_3_2_1_16_1","volume-title":"Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models. arXiv preprint arXiv:2401.09083","author":"Guo Haonan","year":"2024","unstructured":"Haonan Guo, Xin Su, Chen Wu, Bo Du, Liangpei Zhang, and Deren Li. 2024. Remote Sensing ChatGPT: Solving Remote Sensing Tasks with ChatGPT and Visual Models. arXiv preprint arXiv:2401.09083 (2024)."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_18_1","volume-title":"Rsgpt: A remote sensing vision language model and benchmark. arXiv preprint arXiv:2307.15266","author":"Hu Yuan","year":"2023","unstructured":"Yuan Hu, Jianlong Yuan, Congcong Wen, Xiaonan Lu, and Xiang Li. 2023. Rsgpt: A remote sensing vision language model and benchmark. arXiv preprint arXiv:2307.15266 (2023)."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3382507.3418840"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.1524261113"},{"key":"e_1_3_2_1_21_1","volume-title":"Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950","author":"Kiela Douwe","year":"2019","unstructured":"Douwe Kiela, Suvrat Bhooshan, Hamed Firooz, Ethan Perez, and Davide Testuggine. 2019. Supervised multimodal bitransformers for classifying images and text. arXiv preprint arXiv:1909.02950 (2019)."},{"key":"e_1_3_2_1_22_1","volume-title":"International conference on machine learning. PMLR","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. In International conference on machine learning. PMLR, 19730--19742."},{"key":"e_1_3_2_1_23_1","volume-title":"Analysis of regression in game theory approach. Applied stochastic models in business and industry 17, 4","author":"Lipovetsky Stan","year":"2001","unstructured":"Stan Lipovetsky and Michael Conklin. 2001. Analysis of regression in game theory approach. Applied stochastic models in business and industry 17, 4 (2001), 319--330."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2306.11029"},{"key":"e_1_3_2_1_25_1","volume-title":"A unified approach to interpreting model predictions. Advances in neural information processing systems 30","author":"Lundberg Scott M","year":"2017","unstructured":"Scott M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_26_1","volume-title":"Geollm: Extracting geospatial knowledge from large language models. arXiv preprint arXiv:2310.06213","author":"Manvi Rohin","year":"2023","unstructured":"Rohin Manvi, Samar Khanna, Gengchen Mai, Marshall Burke, David Lobell, and Stefano Ermon. 2023. Geollm: Extracting geospatial knowledge from large language models. arXiv preprint arXiv:2310.06213 (2023)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"e_1_3_2_1_28_1","unstructured":"OpenStreetMap Foundation & Contributors. 2022. OpenStreetMap. https:\/\/www.openstreetmap.org\/."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 8748--8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al. 2021. Learning transferable visualmodels from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_30_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_31_1","volume-title":"open data for spatial demography. Scientific data 4, 1","author":"Tatem Andrew J","year":"2017","unstructured":"Andrew J Tatem. 2017. WorldPop, open data for spatial demography. Scientific data 4, 1 (2017), 1--4."},{"key":"e_1_3_2_1_32_1","volume-title":"Attention is all you need. Advances in neural information processing systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, \u0141ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in neural information processing systems 30 (2017)."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"e_1_3_2_1_34_1","volume-title":"Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079","author":"Wang Weihan","year":"2023","unstructured":"Weihan Wang, Qingsong Lv, Wenmeng Yu, Wenyi Hong, Ji Qi, Yan Wang, Junhui Ji, Zhuoyi Yang, Lei Zhao, and Xixuan Song. 2023. Cogvlm: Visual expert for pretrained language models. arXiv preprint arXiv:2311.03079 (2023)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044655"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.compenvurbsys.2022.101921"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113578"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3589334.3645378"},{"key":"e_1_3_2_1_39_1","volume-title":"How to improve urban transportation planning in big data era? A practice in the study of traffic analysis zone delineation. Transport policy 127","author":"Yang Binyu","year":"2022","unstructured":"Binyu Yang, Yuan Tian, Jian Wang, Xiaowei Hu, and Shi An. 2022. How to improve urban transportation planning in big data era? A practice in the study of traffic analysis zone delineation. Transport policy 127 (2022), 1--14."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102753"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1080\/13658816.2016.1244608"},{"key":"e_1_3_2_1_42_1","volume-title":"Skyeyegpt: Unifying remote sensing vision-language tasks via instruction tuning with large language model. arXiv preprint arXiv:2401.09712","author":"Zhan Yang","year":"2024","unstructured":"Yang Zhan, Zhitong Xiong, and Yuan Yuan. 2024. Skyeyegpt: Unifying remote sensing vision-language tasks via instruction tuning with large language model. arXiv preprint arXiv:2401.09712 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1038\/s43588-023-00503-5"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113758"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2023.113767"}],"event":{"name":"SIGSPATIAL '24: The 32nd ACM International Conference on Advances in Geographic Information Systems","sponsor":["SIGSPATIAL ACM Special Interest Group on Spatial Information"],"location":"Atlanta GA USA","acronym":"SIGSPATIAL '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Advances in Geographic Information Systems"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678717.3691278","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3678717.3691278","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T10:41:50Z","timestamp":1755859310000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3678717.3691278"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"references-count":45,"alternative-id":["10.1145\/3678717.3691278","10.1145\/3678717"],"URL":"https:\/\/doi.org\/10.1145\/3678717.3691278","relation":{},"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"2024-11-22","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}