{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T04:39:37Z","timestamp":1784349577636,"version":"3.55.0"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T00:00:00Z","timestamp":1665360000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Jiangsu Province Science Foundation for Youths","award":["BK20210707"],"award-info":[{"award-number":["BK20210707"]}]},{"name":"Shenzhen Science and Technology Program","award":["JCYJ20180507183823045, JCYJ20210324120208022"],"award-info":[{"award-number":["JCYJ20180507183823045, JCYJ20210324120208022"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62101371"],"award-info":[{"award-number":["62101371"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2022,10,10]]},"DOI":"10.1145\/3503161.3548316","type":"proceedings-article","created":{"date-parts":[[2022,10,10]],"date-time":"2022-10-10T15:43:12Z","timestamp":1665416592000},"page":"404-412","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":78,"title":["Visual Grounding in Remote Sensing Images"],"prefix":"10.1145","author":[{"given":"Yuxi","family":"Sun","sequence":"first","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shanshan","family":"Feng","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xutao","family":"Li","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yunming","family":"Ye","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Kang","sequence":"additional","affiliation":[{"name":"Soochow University, Suzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xu","family":"Huang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology, Shenzhen, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2022,10,10]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16188"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01010"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2008.2002695"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.475"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00808"},{"key":"e_1_3_2_2_6_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). 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_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.470"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.493"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01661"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2012.2233469"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00477"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00597"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00431"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.5194\/agile-giss-2-8-2021"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.9"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17602"},{"key":"e_1_3_2_2_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_48"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"e_1_3_2_2_23_1","volume-title":"Manning","author":"Qi Peng","year":"2020","unstructured":"Peng Qi , Yuhao Zhang , Yuhui Zhang , Jason Bolton , and Christopher D . Manning . 2020 . Stanza : A Python Natural Language Processing Toolkit for Many Human Languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics : System Demonstrations. Peng Qi, Yuhao Zhang, Yuhui Zhang, Jason Bolton, and Christopher D. Manning. 2020. Stanza: A Python Natural Language Processing Toolkit for Many Human Languages. In Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics: System Demonstrations."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413850"},{"key":"e_1_3_2_2_25_1","volume-title":"Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767","author":"Redmon Joseph","year":"2018","unstructured":"Joseph Redmon and Ali Farhadi . 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 ( 2018 ). Joseph Redmon and Ali Farhadi. 2018. Yolov3: An incremental improvement. arXiv preprint arXiv:1804.02767 (2018)."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11164"},{"key":"e_1_3_2_2_27_1","volume-title":"Numeracy for language models: Evaluating and improving their ability to predict numbers. arXiv preprint arXiv:1805.08154","author":"Spithourakis Georgios P","year":"2018","unstructured":"Georgios P Spithourakis and Sebastian Riedel . 2018. Numeracy for language models: Evaluating and improving their ability to predict numbers. arXiv preprint arXiv:1805.08154 ( 2018 ). Georgios P Spithourakis and Sebastian Riedel. 2018. Numeracy for language models: Evaluating and improving their ability to predict numbers. arXiv preprint arXiv:1805.08154 (2018)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2022.3231215","article-title":"Multisensor fusion and explicit semantic preserving-based deep hashing for cross-modal remote sensing image retrieval","volume":"60","author":"Sun Yuxi","year":"2022","unstructured":"Yuxi Sun , Shanshan Feng , Yunming Ye , Xutao Li , Jian Kang , Zhichao Huang , and Chuyao Luo . 2022 . Multisensor fusion and explicit semantic preserving-based deep hashing for cross-modal remote sensing image retrieval . IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1 -- 14 . Yuxi Sun, Shanshan Feng, Yunming Ye, Xutao Li, Jian Kang, Zhichao Huang, and Chuyao Luo. 2022. Multisensor fusion and explicit semantic preserving-based deep hashing for cross-modal remote sensing image retrieval. IEEE Transactions on Geoscience and Remote Sensing 60 (2022), 1--14.","journal-title":"IEEE Transactions on Geoscience and Remote Sensing"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413905"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"crossref","unstructured":"Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz etal 2019. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019).  Thomas Wolf Lysandre Debut Victor Sanh Julien Chaumond Clement Delangue Anthony Moi Pierric Cistac Tim Rault R\u00e9mi Louf Morgan Funtowicz et al. 2019. Huggingface's transformers: State-of-the-art natural language processing. arXiv preprint arXiv:1910.03771 (2019).","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00474"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00997"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2973983"},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_23"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00478"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00142"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00437"},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00447"}],"event":{"name":"MM '22: The 30th ACM International Conference on Multimedia","location":"Lisboa Portugal","acronym":"MM '22","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 30th ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548316","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3503161.3548316","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T19:00:43Z","timestamp":1750186843000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3503161.3548316"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,10]]},"references-count":40,"alternative-id":["10.1145\/3503161.3548316","10.1145\/3503161"],"URL":"https:\/\/doi.org\/10.1145\/3503161.3548316","relation":{},"subject":[],"published":{"date-parts":[[2022,10,10]]},"assertion":[{"value":"2022-10-10","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}