{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:30:13Z","timestamp":1742913013931,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819756179"},{"type":"electronic","value":"9789819756186"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":[[2024]]},"DOI":"10.1007\/978-981-97-5618-6_35","type":"book-chapter","created":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T16:04:18Z","timestamp":1722528258000},"page":"417-429","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Estimating Socioeconomic Proxy Variables Using Multimodal Deep Learning Models"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5223-9425","authenticated-orcid":false,"given":"Yanbing","family":"Bai","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zelan","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huixue","family":"Su","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liangzhi","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,8,1]]},"reference":[{"key":"35_CR1","doi-asserted-by":"crossref","unstructured":"Abitbol, J.L., Karsai, M.: Interpretable socioeconomic status inference from aerial imagery through urban patterns. Nat. Mach. Intell. 2(11), 684\u2013692 (2020)","DOI":"10.1038\/s42256-020-00243-5"},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Aiken, E., Rolf, E., Blumenstock, J.: Fairness and representation in satellite-based poverty maps: evidence of urban-rural disparities and their impacts on downstream policy. arXiv preprint arXiv:2305.01783 (2023)","DOI":"10.24963\/ijcai.2023\/653"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Chefer, H., Gur, S., Wolf, L.: Transformer interpretability beyond attention visualization. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 782\u2013791 (2021)","DOI":"10.1109\/CVPR46437.2021.00084"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Chen, B., et al.: Multi-modal fusion of satellite and street-view images for urban village classification based on a dual-branch deep neural network. Int. J. Appl. Earth Obs. Geoinf. 109, 102794 (2022)","DOI":"10.1016\/j.jag.2022.102794"},{"key":"35_CR5","doi-asserted-by":"crossref","unstructured":"Chen, C.F.R., Fan, Q., Panda, R.: CrossViT: cross-attention multi-scale vision transformer for image classification. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 357\u2013366 (2021)","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"35_CR6","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"35_CR7","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"35_CR8","unstructured":"Esp\u0131n-Noboa, L., Kert\u00e9sz, J., Karsai, M.: Challenges of inferring high-resolution poverty maps with multimodal data (2022)"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Fan, Z., Zhang, F., Loo, B.P., Ratti, C.: Urban visual intelligence: uncovering hidden city profiles with street view images. Proc. Natl. Acad. Sci. 120 (27), e2220417120 (2023)","DOI":"10.1073\/pnas.2220417120"},{"key":"35_CR10","doi-asserted-by":"publisher","unstructured":"Geng, Z., Ziqing, G., Chihsu, T., Jiamin, L.: CGPM: poverty mapping framework based on\u00a0multi-modal geographic knowledge integration and\u00a0macroscopic social network mining. In: Amini, M.R., Canu, S., Fischer, A., Guns, T., Kralj Novak, P., Tsoumakas, G. (eds.) ECML PKDD 2022. LNCS, vol. 13717, pp. 549\u2013564. Springer, Cham (2023). https:\/\/doi.org\/10.1007\/978-3-031-26419-1_33","DOI":"10.1007\/978-3-031-26419-1_33"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Gibson, J., Olivia, S., Boe-Gibson, G., Li, C.: Which night lights data should we use in economics, and where? J. Dev. Econ. 149, 102602 (2021)","DOI":"10.1016\/j.jdeveco.2020.102602"},{"key":"35_CR12","doi-asserted-by":"crossref","unstructured":"Hall, O., Ohlsson, M., R\u00f6gnvaldsson, T.: Satellite image and machine learning based knowledge extraction in the poverty and welfare domain. arXiv preprint arXiv:2203.01068 (2022)","DOI":"10.2139\/ssrn.4102620"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Han, S., et al.: Learning to score economic development from satellite imagery. In: Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 2970\u20132979 (2020)","DOI":"10.1145\/3394486.3403347"},{"key":"35_CR14","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"35_CR15","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and pattern recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Jaidka, K., Giorgi, S., Schwartz, H.A., Kern, M.L., Ungar, L.H., Eichstaedt, J.C.: Estimating geographic subjective well-being from twitter: A comparison of dictionary and data-driven language methods. Proc. Natl. Acad. Sci. 117(19), 10165\u201310171 (2020)","DOI":"10.1073\/pnas.1906364117"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Jean, N., Burke, M., Xie, M., Davis, W.M., Lobell, D.B., Ermon, S.: Combining satellite imagery and machine learning to predict poverty. Science 353(6301), 790\u2013794 (2016)","DOI":"10.1126\/science.aaf7894"},{"key":"35_CR18","doi-asserted-by":"crossref","unstructured":"Lee, J., et al.: Predicting livelihood indicators from community-generated street-level imagery. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 268\u2013276 (2021)","DOI":"10.1609\/aaai.v35i1.16101"},{"key":"35_CR19","unstructured":"Sun, Y., et al.: ERNIE: enhanced representation through knowledge integration. corr abs\/1904.09223 (2019). arXiv preprint arXiv:1904.09223 (2019)"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-5618-6_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,1]],"date-time":"2024-08-01T16:22:16Z","timestamp":1722529336000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-5618-6_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819756179","9789819756186"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-5618-6_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"1 August 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tianjin","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"5 August 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"8 August 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"20","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/2024\/index.htm","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}