{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,24]],"date-time":"2026-01-24T13:13:16Z","timestamp":1769260396396,"version":"3.49.0"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3769748.3773353","type":"proceedings-article","created":{"date-parts":[[2025,12,8]],"date-time":"2025-12-08T10:33:15Z","timestamp":1765189995000},"page":"1-6","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Integrating Multimodal Geo-Semantic Contexts for Traffic Prediction"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2490-9557","authenticated-orcid":false,"given":"Shuntaro","family":"Masuda","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0594-5600","authenticated-orcid":false,"given":"Fumiya","family":"Matsuno","sequence":"additional","affiliation":[{"name":"MD Inc., Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-4536-4446","authenticated-orcid":false,"given":"Itsuki","family":"Hirai","sequence":"additional","affiliation":[{"name":"MD Inc., Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1784-2314","authenticated-orcid":false,"given":"Toshihiko","family":"Yamasaki","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2025,12,8]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"crossref","unstructured":"Filip Biljecki and Kazuto Ito. 2021. Street view imagery in urban analytics and GIS: A review. Landscape and Urban Planning 215 (2021) 104217.","DOI":"10.1016\/j.landurbplan.2021.104217"},{"key":"e_1_3_3_1_3_2","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, et\u00a0al. 2021. An image is worth 16x16 words: Transformers for image recognition at scale. In International Conference on Learning Representations."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Ahmad Ganji Mengying Zhang and Marianne Hatzopoulou. 2022. Traffic volume prediction using aerial imagery and sparse data from road counts. Transportation Research Part C: Emerging Technologies 141 (2022) 103739.","DOI":"10.1016\/j.trc.2022.103739"},{"key":"e_1_3_3_1_5_2","unstructured":"Xusen Guo Qiming Zhang Mingxing Peng et\u00a0al. 2024. Explainable traffic flow prediction with large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2404.02937 (2024)."},{"key":"e_1_3_3_1_6_2","doi-asserted-by":"crossref","unstructured":"Neal Jean Marshall Burke Michael Xie W\u00a0Matthew Davis David\u00a0B Lobell and Stefano Ermon. 2016. Combining satellite imagery and machine learning to predict poverty. Science 353 6301 (2016) 790\u2013794.","DOI":"10.1126\/science.aaf7894"},{"key":"e_1_3_3_1_7_2","first-page":"12888","volume-title":"International Conference on Machine Learning","author":"Li Junnan","year":"2022","unstructured":"Junnan Li, Dongxu Li, Caiming Xiong, and Steven Hoi. 2022. BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation. In International Conference on Machine Learning. 12888\u201312900."},{"key":"e_1_3_3_1_8_2","doi-asserted-by":"crossref","unstructured":"Yaguang Li and Cyrus Shahabi. 2018. A brief overview of machine learning methods for short-term traffic forecasting and future directions. SIGSPATIAL Special 10 1 (2018) 3\u20139.","DOI":"10.1145\/3231541.3231544"},{"key":"e_1_3_3_1_9_2","doi-asserted-by":"publisher","DOI":"10.1145\/3637528.3671578"},{"key":"e_1_3_3_1_10_2","doi-asserted-by":"crossref","unstructured":"Yuebing Liang Yichao Liu Xiaohan Wang and Zhan Zhao. 2024. Exploring large language models for human mobility prediction under public events. Computers Environment and Urban Systems 112 (2024) 102153.","DOI":"10.1016\/j.compenvurbsys.2024.102153"},{"key":"e_1_3_3_1_11_2","volume-title":"Advances in Neural Information Processing Systems","author":"Lundberg Scott\u00a0M","year":"2017","unstructured":"Scott\u00a0M Lundberg and Su-In Lee. 2017. A unified approach to interpreting model predictions. In Advances in Neural Information Processing Systems, Vol.\u00a030."},{"key":"e_1_3_3_1_12_2","unstructured":"Ziyuan Ma Yilong Ren Yue Chen Shuai Liu Defu Yao Chengzhe Chen Gai Yang et\u00a0al. 2025. TPLLM: A traffic prediction framework based on pretrained Large Language Models. Applied Soft Computing 148 (2025) 110823."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"crossref","unstructured":"Benjamin Marx Thomas\u00a0M Stoker and Tavneet Suri. 2019. There is no free house: Ethnic patronage in a Kenyan slum. American Economic Journal: Applied Economics 11 4 (2019) 36\u201370.","DOI":"10.1257\/app.20160484"},{"key":"e_1_3_3_1_14_2","unstructured":"Ministry of Land Infrastructure Transport and Tourism. 2023. National Land Information Download Service: Land Price Data (Reiwa 5 Standard Year). https:\/\/nlftp.mlit.go.jp\/ksj\/. Japan National Spatial Planning and Regional Policy Bureau."},{"key":"e_1_3_3_1_15_2","unstructured":"Ministry of Land Infrastructure Transport and Tourism. 2023. National Road and Street Traffic Census. https:\/\/www.mlit.go.jp\/road\/census\/r3\/. Japan."},{"key":"e_1_3_3_1_16_2","unstructured":"OpenStreetMap contributors. 2017. Planet dump retrieved from https:\/\/planet.osm.org. https:\/\/www.openstreetmap.org."},{"key":"e_1_3_3_1_17_2","first-page":"8748","volume-title":"International Conference on Machine Learning","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong\u00a0Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et\u00a0al. 2021. Learning transferable visual representations from natural language supervision. In International Conference on Machine Learning. 8748\u20138763."},{"key":"e_1_3_3_1_18_2","volume-title":"bert-base-japanese-v3","year":"2024","unstructured":"TohokuNLPGroup. 2024. bert-base-japanese-v3. https:\/\/huggingface.co\/tohoku-nlp\/bert-base-japanese-v3"},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Eleni\u00a0I Vlahogianni Matthew\u00a0G Karlaftis and John\u00a0C Golias. 2014. Short-term traffic forecasting: Where we are and where we\u2019re going. Transportation Research Part C: Emerging Technologies 43 (2014) 3\u201319.","DOI":"10.1016\/j.trc.2014.01.005"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"crossref","unstructured":"Huihai Wang and Junfeng Jiao. 2023. Forecasting Traffic Speed during Daytime from Google Street View Images using Deep Learning. Transportation Research Record 2677 12 (2023) 743\u2013753.","DOI":"10.1177\/03611981231169531"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","unstructured":"Christopher Yeh Anthony Perez Anne Driscoll George Azzari Zhongyi Tang David Lobell Stefano Ermon and Marshall Burke. 2020. Using publicly available satellite imagery and deep learning to understand economic well-being in Africa. Nature Communications 11 1 (2020) 2583.","DOI":"10.1038\/s41467-020-16185-w"},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Jie Yin Tian Cheng Zheng Wang Weiguo Shao and Ross Maciejewski. 2015. \u2019Big data\u2019 for pedestrian volume: Exploring the use of Google Street View images for pedestrian counts. Applied Geography 63 (2015) 337\u2013345.","DOI":"10.1016\/j.apgeog.2015.07.010"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.424"}],"event":{"name":"MMAsia '25 Workshops: ACM Multimedia Asia Workshops","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25 Workshops","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3769748.3773353","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T22:03:26Z","timestamp":1769205806000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3769748.3773353"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,8]]},"references-count":22,"alternative-id":["10.1145\/3769748.3773353","10.1145\/3769748"],"URL":"https:\/\/doi.org\/10.1145\/3769748.3773353","relation":{},"subject":[],"published":{"date-parts":[[2025,12,8]]},"assertion":[{"value":"2025-12-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}