{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T16:55:10Z","timestamp":1781110510901,"version":"3.54.1"},"reference-count":111,"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":["62372155"],"award-info":[{"award-number":["62372155"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32371877"],"award-info":[{"award-number":["32371877"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012130","name":"Chinese Aeronautical Establishment","doi-asserted-by":"publisher","award":["2022Z071108001"],"award-info":[{"award-number":["2022Z071108001"]}],"id":[{"id":"10.13039\/501100012130","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Joint Fund of Ministry of Education for Equipment Pre-Research","award":["8091B022123"],"award-info":[{"award-number":["8091B022123"]}]},{"DOI":"10.13039\/501100018581","name":"Water Science and Technology Project of Jiangsu Province","doi-asserted-by":"publisher","award":["2021063"],"award-info":[{"award-number":["2021063"]}],"id":[{"id":"10.13039\/501100018581","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Technology Winter Olympics Special Project","award":["201001D"],"award-info":[{"award-number":["201001D"]}]},{"name":"Forest Fire Comprehensive System Construction-Unmanned Aerial Patrol Monitoring System of Chongli","award":["DA2-20001"],"award-info":[{"award-number":["DA2-20001"]}]},{"DOI":"10.13039\/501100013088","name":"Qinglan Project of Jiangsu Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013088","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.2024.3390838","type":"journal-article","created":{"date-parts":[[2024,4,18]],"date-time":"2024-04-18T13:29:23Z","timestamp":1713446963000},"page":"1-16","source":"Crossref","is-referenced-by-count":325,"title":["RemoteCLIP: A Vision Language Foundation Model for Remote Sensing"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8746-9845","authenticated-orcid":false,"given":"Fan","family":"Liu","sequence":"first","affiliation":[{"name":"College of Computer Science and Software Engineering, Hohai University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8172-2894","authenticated-orcid":false,"given":"Delong","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Electronic and Computer Engineering, The Hong Kong University of Science and Technology, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhangqingyun","family":"Guan","sequence":"additional","affiliation":[{"name":"College of Computer and Information, Hohai University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaocong","family":"Zhou","sequence":"additional","affiliation":[{"name":"College of Computer and Information, Hohai University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiale","family":"Zhu","sequence":"additional","affiliation":[{"name":"College of Computer and Information, Hohai University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8793-8610","authenticated-orcid":false,"given":"Qiaolin","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Information Science and Technology, Nanjing Forestry University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5794-9458","authenticated-orcid":false,"given":"Liyong","family":"Fu","sequence":"additional","affiliation":[{"name":"Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5822-8233","authenticated-orcid":false,"given":"Jun","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Information and Communication Technology, Griffith University, Nathan, QLD, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref2","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. 37th Int. Conf. Mach. Learn.","volume":"119","author":"Chen"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref5","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. Conf. North Amer. Chapter Assoc. Comput. Linguistics, Hum. Lang. Technol.","volume":"1","author":"Devlin"},{"key":"ref6","first-page":"1","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst., Annu. Conf. Neural Inf. Process. Syst.","author":"Brown"},{"key":"ref7","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref8","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref9","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. NeurIPS","author":"Alayrac"},{"key":"ref10","first-page":"1","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Bao"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref12","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. NeurIPS","author":"Cong"},{"key":"ref13","article-title":"Scale-MAE: A scale-aware masked autoencoder for multiscale geospatial representation learning","author":"Reed","year":"2022","journal-title":"arXiv:2212.14532"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref17","article-title":"GFM: Building geospatial foundation models via continual pretraining","author":"Mendieta","year":"2023","journal-title":"arXiv:2302.04476"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00604"},{"key":"ref19","first-page":"20149","article-title":"Architecture-agnostic masked image modeling\u2014From ViT back to CNN","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","volume":"202","author":"Li"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00765"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01391"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00212"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01392"},{"key":"ref24","article-title":"What do self-supervised vision transformers learn?","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Park"},{"key":"ref25","first-page":"1","article-title":"ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustness","volume-title":"Proc. 7th Int. Conf. Learn. Represent. (ICLR)","author":"Geirhos"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3557915.3561043"},{"key":"ref27","article-title":"On the opportunities and challenges of foundation models for geospatial artificial intelligence","author":"Mai","year":"2023","journal-title":"arXiv:2304.06798"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2022.3198244"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3007029"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3069799"},{"key":"ref34","first-page":"3967","article-title":"Tile2vec: Unsupervised representation learning for spatially distributed data","volume-title":"Proc. AAAI Conf. Artif. Intell.","volume":"33","author":"Jean"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/rs12203276"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115569"},{"key":"ref37","first-page":"1182","article-title":"Self-supervised learning of remote sensing scene representations using contrastive multiview coding","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Stojnic"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.03.021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/773"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref43","article-title":"Vision-language models for vision tasks: A survey","author":"Zhang","year":"2023","journal-title":"arXiv:2304.00685"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/app10248931"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2022.3231851"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2022.3226325"},{"key":"ref50","first-page":"14","article-title":"Knowledge-aware cross-modal text-image retrieval for remote sensing images","volume-title":"Proc. 2nd Workshop Complex Data Challenges Earth Observ. (CDCEO) Co-Located 31st Int. Joint Conf. Artif. Intell. 25th Eur. Conf. Artif. Intell. (IJCAI-ECAI)","volume":"3207","author":"Mi"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3318227"},{"key":"ref52","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref53","article-title":"Reproducible scaling laws for contrastive language-image learning","author":"Cherti","year":"2022","journal-title":"arXiv:2212.07143"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_30"},{"key":"ref55","first-page":"1","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. 10th Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref56","first-page":"1","article-title":"CoCa: Contrastive captioners are image-text foundation models","volume":"2022","author":"Yu","year":"2022","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref57","article-title":"Scaling language-image pre-training via masking","author":"Li","year":"2022","journal-title":"arXiv:2212.00794"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3335859"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref60","volume-title":"Few-shot adaptation of multi-modal foundation models: A survey","volume":"abs\/2401.01736","author":"Liu","year":"2024"},{"key":"ref61","first-page":"2","article-title":"Contrastive learning of medical visual representations from paired images and text","volume-title":"Proc. Mach. Learn. Healthcare Conf.","author":"Zhang"},{"key":"ref62","article-title":"Does CLIP benefit visual question answering in the medical domain as much as it does in the general domain?","author":"Eslami","year":"2021","journal-title":"arXiv:2112.13906"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref64","article-title":"Large-scale domain-specific pretraining for biomedical vision-language processing","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02057"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109519"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3511808.3557067"},{"key":"ref68","article-title":"RS5M: A large scale vision-language dataset for remote sensing vision-language foundation model","author":"Zhang","year":"2023","journal-title":"arXiv:2306.11300"},{"key":"ref69","article-title":"SATIN: A multi-task metadataset for classifying satellite imagery using vision-language models","author":"Roberts","year":"2023","journal-title":"arXiv:2304.11619"},{"key":"ref70","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref71","article-title":"PaLI-X: On scaling up a multilingual vision and language model","author":"Chen","year":"2023","journal-title":"arXiv:2305.18565"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i16.29727"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/0734-189x(85)90016-7"},{"key":"ref74","volume-title":"Implementation and benchmarking of perceptual image hash functions","author":"Zauner","year":"2010"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref76","article-title":"Object detection in optical remote sensing images: A survey and a new benchmark","author":"Li","year":"2019","journal-title":"arXiv:1909.00133"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2900302"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-021-02893-3"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.5220\/0006120603240331"},{"key":"ref81","volume-title":"Vaihingen Dataset","year":"2012"},{"key":"ref82","volume-title":"Potsdam Dataset","year":"2012"},{"key":"ref83","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proc. CVPR Workshops","author":"Zamir"},{"key":"ref84","first-page":"1","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","volume-title":"Proc. Neural Inf. Process. Syst. Track Datasets Benchmarks 1, NeurIPS Datasets and Benchmarks","author":"Wang"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.3390\/app10217622"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.446"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_33"},{"key":"ref88","article-title":"Vision meets drones: A challenge","author":"Zhu","year":"2018","journal-title":"arXiv:1804.07437"},{"key":"ref89","first-page":"1","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3013818"},{"issue":"9","key":"ref93","doi-asserted-by":"crossref","first-page":"3359","DOI":"10.1080\/01431161.2022.2091964","article-title":"A fusion-based contrastive learning model for cross-modal remote sensing retrieval","volume":"43","author":"Li","year":"2022","journal-title":"Int. J. Remote Sens."},{"key":"ref94","article-title":"Direction-oriented visual-semantic embedding model for remote sensing image-text retrieval","author":"Ma","year":"2023","journal-title":"arXiv:2310.08276"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref97","article-title":"PatternNet: A benchmark dataset for performance evaluation of remote sensing image retrieval","author":"Zhou","year":"2017","journal-title":"arXiv:1706.03424"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.10.035004"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.09.020"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.3390\/s20061594"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2496185"},{"key":"ref106","volume-title":"Structural high-resolution satellite image indexing","author":"Xia","year":"2010"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2475299"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273513"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref110","first-page":"1849","article-title":"Improved deep metric learning with multi-class N-pair loss objective","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn"},{"key":"ref111","first-page":"12310","article-title":"Barlow twins: Self-supervised learning via redundancy reduction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zbontar"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10354519\/10504785.pdf?arnumber=10504785","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,18]],"date-time":"2025-09-18T17:46:03Z","timestamp":1758217563000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10504785\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":111,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3390838","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}