{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:44:56Z","timestamp":1780418696538,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":47,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Guangzhou-HKUST (GZ) Joint Funding Program","award":["2024A03J0620"],"award-info":[{"award-number":["2024A03J0620"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680604","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:27Z","timestamp":1729925967000},"page":"6307-6315","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":7,"title":["UrbanCross: Enhancing Satellite Image-Text Retrieval with Cross-Domain Adaptation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4465-8686","authenticated-orcid":false,"given":"Siru","family":"Zhong","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0728-1944","authenticated-orcid":false,"given":"Xixuan","family":"Hao","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2546-1403","authenticated-orcid":false,"given":"Yibo","family":"Yan","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6411-4486","authenticated-orcid":false,"given":"Ying","family":"Zhang","sequence":"additional","affiliation":[{"name":"Northwestern Polytechnical University, Xi'an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7818-6090","authenticated-orcid":false,"given":"Yangqiu","family":"Song","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2817-7337","authenticated-orcid":false,"given":"Yuxuan","family":"Liang","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Abbas Sharifi, Ali Tarlani Beris, Mohammadsadegh Nouri, and Amir Sharifzadeh Javidi.","author":"Ahmadi Mohsen","year":"2023","unstructured":"Mohsen Ahmadi, Ahmad Gholizadeh Lonbar, Abbas Sharifi, Ali Tarlani Beris, Mohammadsadegh Nouri, and Amir Sharifzadeh Javidi. 2023. Application of segment anything model for civil infrastructure defect assessment. arXiv preprint arXiv:2304.12600 (2023)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"e_1_3_2_1_3_1","volume-title":"Image-text retrieval: A survey on recent research and development. arXiv preprint arXiv:2203.14713","author":"Cao Min","year":"2022","unstructured":"Min Cao, Shiping Li, Juntao Li, Liqiang Nie, and Min Zhang. 2022. Image-text retrieval: A survey on recent research and development. arXiv preprint arXiv:2203.14713 (2022)."},{"key":"e_1_3_2_1_4_1","volume-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478","author":"Chen Jun","year":"2023","unstructured":"Jun Chen, Deyao Zhu, Xiaoqian Shen, Xiang Li, Zechun Liu, Pengchuan Zhang, Raghuraman Krishnamoorthi, Vikas Chandra, Yunyang Xiong, and Mohamed Elhoseiny. 2023. Minigpt-v2: large language model as a unified interface for vision-language multi-task learning. arXiv preprint arXiv:2310.09478 (2023)."},{"key":"e_1_3_2_1_5_1","volume-title":"RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model","author":"Chen Keyan","year":"2024","unstructured":"Keyan Chen, Chenyang Liu, Hao Chen, Haotian Zhang, Wenyuan Li, Zhengxia Zou, and Zhenwei Shi. 2024. RSPrompter: Learning to prompt for remote sensing instance segmentation based on visual foundation model. IEEE Transactions on Geoscience and Remote Sensing (2024)."},{"key":"e_1_3_2_1_6_1","volume-title":"Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic. arXiv preprint arXiv:2306.15195","author":"Chen Keqin","year":"2023","unstructured":"Keqin Chen, Zhao Zhang, Weili Zeng, Richong Zhang, Feng Zhu, and Rui Zhao. 2023. Shikra: Unleashing Multimodal LLM's Referential Dialogue Magic. arXiv preprint arXiv:2306.15195 (2023)."},{"key":"e_1_3_2_1_7_1","volume-title":"Multiscale Salient Alignment Learning for Remote Sensing Image-Text Retrieval","author":"Chen Yaxiong","year":"2023","unstructured":"Yaxiong Chen, Jinghao Huang, Xiaoyu Li, Shengwu Xiong, and Xiaoqiang Lu. 2023. Multiscale Salient Alignment Learning for Remote Sensing Image-Text Retrieval. IEEE Transactions on Geoscience and Remote Sensing (2023)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"e_1_3_2_1_9_1","volume-title":"Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi.","author":"Dai Wenliang","year":"2023","unstructured":"Wenliang Dai, Junnan Li, Dongxu Li, Anthony Meng Huat Tiong, Junqi Zhao, Weisheng Wang, Boyang Li, Pascale Fung, and Steven Hoi. 2023. InstructBLIP: Towards General-purpose Vision-Language Models with Instruction Tuning. arxiv: 2305.06500 [cs.CV]"},{"key":"e_1_3_2_1_10_1","volume-title":"UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Foundation Model for Urban Indicator Prediction. arXiv preprint arXiv:2403.16831","author":"Hao Xixuan","year":"2024","unstructured":"Xixuan Hao, Wei Chen, Yibo Yan, Siru Zhong, Kun Wang, Qingsong Wen, and Yuxuan Liang. 2024. UrbanVLP: A Multi-Granularity Vision-Language Pre-Trained Foundation Model for Urban Indicator Prediction. arXiv preprint arXiv:2403.16831 (2024)."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.3390\/math11102279"},{"key":"e_1_3_2_1_12_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_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-68787-8_40"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1126\/science.aaf7894"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3610949"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332317"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C. Berg Wan-Yen Lo Piotr Doll\u00e1r and Ross Girshick. 2023. Segment Anything. arxiv: 2304.02643 [cs.CV]","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_18_1","volume-title":"Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond. arXiv preprint arXiv:2402.10805","author":"Li Yongqi","year":"2024","unstructured":"Yongqi Li, Wenjie Wang, Leigang Qu, Liqiang Nie, Wenjie Li, and Tat-Seng Chua. 2024. Generative Cross-Modal Retrieval: Memorizing Images in Multimodal Language Models for Retrieval and Beyond. arXiv preprint arXiv:2402.10805 (2024)."},{"key":"e_1_3_2_1_19_1","first-page":"1","article-title":"Recurrent attention and semantic gate for remote sensing image captioning","volume":"60","author":"Li Yunpeng","year":"2021","unstructured":"Yunpeng Li, Xiangrong Zhang, Jing Gu, Chen Li, Xin Wang, Xu Tang, and Licheng Jiao. 2021. Recurrent attention and semantic gate for remote sensing image captioning. IEEE Transactions on Geoscience and Remote Sensing, Vol. 60 (2021), 1--16.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_20_1","volume-title":"RemoteCLIP: A Vision Language Foundation Model for Remote Sensing. arXiv preprint arXiv:2306.11029","author":"Liu Fan","year":"2023","unstructured":"Fan Liu, Delong Chen, Zhangqingyun Guan, Xiaocong Zhou, Jiale Zhu, and Jun Zhou. 2023. RemoteCLIP: A Vision Language Foundation Model for Remote Sensing. arXiv preprint arXiv:2306.11029 (2023)."},{"key":"e_1_3_2_1_21_1","volume-title":"Visual instruction tuning. arXiv preprint arXiv:2304.08485","author":"Liu Haotian","year":"2023","unstructured":"Haotian Liu, Chunyuan Li, Qingyang Wu, and Yong Jae Lee. 2023. Visual instruction tuning. arXiv preprint arXiv:2304.08485 (2023)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"e_1_3_2_1_23_1","volume-title":"Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation.","author":"Mi Li","year":"2022","unstructured":"Li Mi, Siran Li, Christel Chappuis, and Devis Tuia. 2022. Knowledge-Aware Cross-Modal Text-Image Retrieval for Remote Sensing Images. In Proceedings of the Second Workshop on Complex Data Challenges in Earth Observation."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592236"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2009.191"},{"key":"e_1_3_2_1_27_1","volume-title":"Kosmos-2: Grounding Multimodal Large Language Models to the World. arXiv preprint arXiv:2306.14824","author":"Peng Zhiliang","year":"2023","unstructured":"Zhiliang Peng, Wenhui Wang, Li Dong, Yaru Hao, Shaohan Huang, Shuming Ma, and Furu Wei. 2023. Kosmos-2: Grounding Multimodal Large Language Models to the World. arXiv preprint arXiv:2306.14824 (2023)."},{"key":"e_1_3_2_1_28_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 visual models from natural language supervision. In International conference on machine learning. PMLR, 8748--8763."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.3390\/rs5041704"},{"key":"e_1_3_2_1_30_1","volume-title":"Understanding satellite-imagery-based crop yield predictions. Stanford","author":"Sabini Mark","year":"2017","unstructured":"Mark Sabini, Gili Rusak, and Brad Ross. 2017. Understanding satellite-imagery-based crop yield predictions. Stanford (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"Devis Tuia, and Bruno Martins.","author":"Daniel Silva Jo","year":"2024","unstructured":"Jo ao Daniel Silva, Jo ao Magalh aes, Devis Tuia, and Bruno Martins. 2024. Large Language Models for Captioning and Retrieving Remote Sensing Images. arXiv preprint arXiv:2402.06475 (2024)."},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557294"},{"key":"e_1_3_2_1_33_1","volume-title":"Attention is all you need. Advances in neural information processing systems","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, Vol. 30 (2017)."},{"key":"e_1_3_2_1_34_1","volume-title":"Advancing plain vision transformer toward remote sensing foundation model","author":"Wang Di","year":"2022","unstructured":"Di Wang, Qiming Zhang, Yufei Xu, Jing Zhang, Bo Du, Dacheng Tao, and Liangpei Zhang. 2022. Advancing plain vision transformer toward remote sensing foundation model. IEEE Transactions on Geoscience and Remote Sensing (2022)."},{"key":"e_1_3_2_1_35_1","volume-title":"Cross-city transfer learning for deep spatio-temporal prediction. arXiv preprint arXiv:1802.00386","author":"Wang Leye","year":"2018","unstructured":"Leye Wang, Xu Geng, Xiaojuan Ma, Feng Liu, and Qiang Yang. 2018. Cross-city transfer learning for deep spatio-temporal prediction. arXiv preprint arXiv:1802.00386 (2018)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/MC.2018.2880015"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"e_1_3_2_1_38_1","volume-title":"Skyscript: A large and semantically diverse vision-language dataset for remote sensing. arXiv preprint arXiv:2312.12856","author":"Wang Zhecheng","year":"2023","unstructured":"Zhecheng Wang, Rajanie Prabha, Tianyuan Huang, Jiajun Wu, and Ram Rajagopal. 2023. Skyscript: A large and semantically diverse vision-language dataset for remote sensing. arXiv preprint arXiv:2312.12856 (2023)."},{"key":"e_1_3_2_1_39_1","volume-title":"When urban region profiling meets large language models. arXiv preprint arXiv:2310.18340","author":"Yan Yibo","year":"2023","unstructured":"Yibo Yan, Haomin Wen, Siru Zhong, Wei Chen, Haodong Chen, Qingsong Wen, Roger Zimmermann, and Yuxuan Liang. 2023. When urban region profiling meets large language models. arXiv preprint arXiv:2310.18340 (2023)."},{"key":"e_1_3_2_1_40_1","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:2304.14178 (2023)."},{"key":"e_1_3_2_1_41_1","volume-title":"Exploring a fine-grained multiscale method for cross-modal remote sensing image retrieval. arXiv preprint arXiv:2204.09868","author":"Yuan Zhiqiang","year":"2022","unstructured":"Zhiqiang Yuan, Wenkai Zhang, Kun Fu, Xuan Li, Chubo Deng, Hongqi Wang, and Xian Sun. 2022. Exploring a fine-grained multiscale method for cross-modal remote sensing image retrieval. arXiv preprint arXiv:2204.09868 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"A lightweight multi-scale crossmodal text-image retrieval method in remote sensing","author":"Yuan Zhiqiang","year":"2021","unstructured":"Zhiqiang Yuan, Wenkai Zhang, Xuee Rong, Xuan Li, Jialiang Chen, Hongqi Wang, Kun Fu, and Xian Sun. 2021. A lightweight multi-scale crossmodal text-image retrieval method in remote sensing. IEEE Transactions on Geoscience and Remote Sensing (2021)."},{"key":"e_1_3_2_1_43_1","first-page":"1","article-title":"Remote sensing cross-modal text-image retrieval based on global and local information","volume":"60","author":"Yuan Zhiqiang","year":"2022","unstructured":"Zhiqiang Yuan, Wenkai Zhang, Changyuan Tian, Xuee Rong, Zhengyuan Zhang, Hongqi Wang, Kun Fu, and Xian Sun. 2022. Remote sensing cross-modal text-image retrieval based on global and local information. IEEE Transactions on Geoscience and Remote Sensing, Vol. 60 (2022), 1--16.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_1_44_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_45_1","volume-title":"UV-SAM: Adapting Segment Anything Model for Urban Village Identification. arXiv preprint arXiv:2401.08083","author":"Zhang Xin","year":"2024","unstructured":"Xin Zhang, Yu Liu, Yuming Lin, Qingming Liao, and Yong Li. 2024. UV-SAM: Adapting Segment Anything Model for Urban Village Identification. arXiv preprint arXiv:2401.08083 (2024)."},{"key":"e_1_3_2_1_46_1","volume-title":"Remote Sensing Image Retrieval in the Past Decade: Achievements, Challenges, and Future Directions","author":"Zhou Weixun","year":"2023","unstructured":"Weixun Zhou, Haiyan Guan, Ziyu Li, Zhenfeng Shao, and Mahmoud R Delavar. 2023. Remote Sensing Image Retrieval in the Past Decade: Achievements, Challenges, and Future Directions. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing (2023)."},{"key":"e_1_3_2_1_47_1","volume-title":"Urban Computing: Taxonomy, Advances, and Outlook. arXiv preprint arXiv:2402.19348","author":"Zou Xingchen","year":"2024","unstructured":"Xingchen Zou, Yibo Yan, Xixuan Hao, Yuehong Hu, Haomin Wen, Erdong Liu, Junbo Zhang, Yong Li, Tianrui Li, Yu Zheng, et al. 2024. Deep Learning for Cross-Domain Data Fusion in Urban Computing: Taxonomy, Advances, and Outlook. arXiv preprint arXiv:2402.19348 (2024)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680604","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680604","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:56Z","timestamp":1750295876000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680604"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":47,"alternative-id":["10.1145\/3664647.3680604","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680604","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}