{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:05:45Z","timestamp":1778947545354,"version":"3.51.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171332"],"award-info":[{"award-number":["62171332"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3406897","type":"journal-article","created":{"date-parts":[[2024,5,29]],"date-time":"2024-05-29T17:28:18Z","timestamp":1717003698000},"page":"1-15","source":"Crossref","is-referenced-by-count":19,"title":["Masking-Based Cross-Modal Remote Sensing Image\u2013Text Retrieval via Dynamic Contrastive Learning"],"prefix":"10.1109","volume":"62","author":[{"given":"Zuopeng","family":"Zhao","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology and Artificial Intelligence, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6972-9783","authenticated-orcid":false,"given":"Xiaoran","family":"Miao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2023-0244","authenticated-orcid":false,"given":"Chen","family":"He","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingbing","family":"Min","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yumeng","family":"Gao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kanyaphakphachsorn","family":"Pharksuwan","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, China University of Mining and Technology, Xuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/app9102110"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3005403"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCIS48478.2019.8974502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2014.10.029"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2016.2598228"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3021052"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3052254"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2756911"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2013.2268736"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3291708"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3236662"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2979273"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref14","first-page":"2","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. NaacL-HLT","volume":"1","author":"Kenton"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref16","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref18","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref19","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"ref21","article-title":"RemoteCLIP: A vision language foundation model for remote sensing","author":"Liu","year":"2023","journal-title":"arXiv:2306.11029"},{"key":"ref22","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref23","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","author":"Su","year":"2019","journal-title":"arXiv:1908.08530"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.11.020"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3231851"},{"key":"ref41","first-page":"5753","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Yang"},{"key":"ref42","article-title":"BART: Denoising sequence-to-sequence pre-training for natural language generation, translation, and comprehension","author":"Lewis","year":"2019","journal-title":"arXiv:1910.13461"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref44","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00677"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01763"},{"key":"ref48","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","volume":"139","author":"Jia"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/rs14225675"},{"key":"ref51","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Ramesh"},{"key":"ref52","first-page":"646","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Bao"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref56","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref57","first-page":"935","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/app122312221"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3226325"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3318227"},{"key":"ref63","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3339661"},{"key":"ref65","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"key":"ref66","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Houlsby"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref68","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_42"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10540645.pdf?arnumber=10540645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,4]],"date-time":"2024-09-04T05:20:25Z","timestamp":1725427225000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10540645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":71,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3406897","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}