{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T14:40:51Z","timestamp":1780670451534,"version":"3.54.1"},"reference-count":58,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":["62306310"],"award-info":[{"award-number":["62306310"]}],"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":[[2025]]},"DOI":"10.1109\/tgrs.2025.3565552","type":"journal-article","created":{"date-parts":[[2025,4,29]],"date-time":"2025-04-29T17:31:45Z","timestamp":1745947905000},"page":"1-17","source":"Crossref","is-referenced-by-count":5,"title":["CLIP-MoA: Visual-Language Models With Mixture of Adapters for Multitask Remote Sensing Image Classification"],"prefix":"10.1109","volume":"63","author":[{"given":"Zhongzheng","family":"Fu","sequence":"first","affiliation":[{"name":"School of Information Engineering, China University of Geosciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4296-2289","authenticated-orcid":false,"given":"Hongping","family":"Yan","sequence":"additional","affiliation":[{"name":"School of Information Engineering, China University of Geosciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kun","family":"Ding","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems (MAIS), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111322"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi9060400"},{"key":"ref3","first-page":"370","article-title":"Support vector machine algorithm in machine learning","volume-title":"11th Int. Conf. Pattern Recognit. Appl. Methods (ICPRAM)","author":"Najafabadi"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1117\/12.2281755"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1142\/S0218301318500076"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/762"},{"issue":"2","key":"ref9","first-page":"1","article-title":"Imagenet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref11","first-page":"1","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Conf. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"},{"key":"ref13","article-title":"RSGPT: A remote sensing vision language model and benchmark","author":"Hu","year":"2023","journal-title":"arXiv:2307.15266"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref15","article-title":"SkySenseGPT: A fine-grained instruction tuning dataset and model for remote sensing vision-language understanding","author":"Luo","year":"2024","journal-title":"arXiv:2406.10100"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref19","article-title":"RS-GPT4 V: A unified multimodal instruction-following dataset for remote sensing image understanding","author":"Xu","year":"2024","journal-title":"arXiv:2406.12479"},{"key":"ref20","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"arXiv:2201.12086"},{"key":"ref21","article-title":"COSMOS: Cross-modality self-distillation for vision language pre-training","author":"Kim","year":"2024","journal-title":"arXiv:2412.01814"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32444"},{"key":"ref25","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020","journal-title":"arXiv:2009.09796"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.11.004"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.3390\/rs13132620"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.04.014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3788\/lop56.101003"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2210901"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01600"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2015.11.032"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-024-57563-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111522"},{"key":"ref36","article-title":"P-tuning V2: Prompt tuning can be comparable to fine-tuning universally across scales and tasks","author":"Liu","year":"2021","journal-title":"arXiv:2110.07602"},{"key":"ref37","first-page":"2790","article-title":"Parameter-efficient transfer learning for NLP","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","volume":"97","author":"Houlsby"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01891-x"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.39"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.388"},{"key":"ref42","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Shazeer"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/s20041226"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2017.2675998"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref48","volume-title":"RS_C11_Database","author":"Zhao","year":"2016"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/lgrs.2015.2475299"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.3390\/s20061594"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2496185"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"issue":"1","key":"ref53","first-page":"63","article-title":"Structural high-resolution satellite image indexing","volume":"38","author":"Xia","year":"2010","journal-title":"Int. Arch. Photogramm., Remote Sens. Spatial Inf. Sci."},{"key":"ref54","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3408154"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.015"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3400959"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3539499"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10980215.pdf?arnumber=10980215","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,14]],"date-time":"2025-05-14T05:09:39Z","timestamp":1747199379000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10980215\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3565552","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}