{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T16:23:03Z","timestamp":1783700583512,"version":"3.55.0"},"reference-count":46,"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":["62376282"],"award-info":[{"award-number":["62376282"]}],"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.2024.3509721","type":"journal-article","created":{"date-parts":[[2024,12,2]],"date-time":"2024-12-02T18:38:50Z","timestamp":1733164730000},"page":"1-10","source":"Crossref","is-referenced-by-count":16,"title":["Efficient Prompt Tuning of Large Vision-Language Model for Fine-Grained Ship Classification"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4238-8985","authenticated-orcid":false,"given":"Long","family":"Lan","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5267-232X","authenticated-orcid":false,"given":"Fengxiang","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8398-6324","authenticated-orcid":false,"given":"Xiangtao","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9326-0316","authenticated-orcid":false,"given":"Zengmao","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9066-1475","authenticated-orcid":false,"given":"Xinwang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, National University of Defense Technology, Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3008993"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/rs14133087"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3161433"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3111117"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3123666"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3109600"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3192256"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3162195"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref11","first-page":"13","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Wang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3066539"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3172223"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3235747"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28343"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref18","article-title":"Vision-language models for vision tasks: A survey","volume-title":"arXiv:2304.00685","author":"Zhang","year":"2023"},{"key":"ref19","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":"ref20","first-page":"1","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":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref22","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"arXiv:2108.10904","author":"Wang","year":"2021"},{"key":"ref23","first-page":"32897","article-title":"VLMo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bao"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref25","article-title":"VL-BERT: Pre-training of generic visual-linguistic representations","volume-title":"arXiv:1908.08530","author":"Su","year":"2019"},{"key":"ref26","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":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref28","article-title":"VisualBERT: A simple and performant baseline for vision and language","volume-title":"arXiv:1908.03557","author":"Harold Li","year":"2019"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref30","article-title":"SOC: Semantic-assisted object cluster for referring video object segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Luo"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096319"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.2981686"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/rs13040747"},{"key":"ref34","article-title":"CLIP-adapter: Better vision-language models with feature adapters","volume-title":"arXiv:2110.04544","author":"Gao","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1561\/0600000105"},{"key":"ref36","article-title":"Tip-adapter: Training-free CLIP-adapter for better vision-language modeling","volume-title":"arXiv:2111.03930","author":"Zhang","year":"2021"},{"key":"ref37","article-title":"SVL-adapter: Self-supervised adapter for vision-language pretrained models","volume-title":"arXiv:2210.03794","author":"Pantazis","year":"2022"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01631"},{"key":"ref39","article-title":"Prompt-aligned gradient for prompt tuning","volume-title":"arXiv:2205.14865","author":"Zhu","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00653"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref42","article-title":"Scaling efficient masked image modeling on large remote sensing dataset","volume-title":"arXiv:2406.11933","author":"Wang","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref45","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"arXiv:2010.11929","author":"Dosovitskiy","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00166"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10772151.pdf?arnumber=10772151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,24]],"date-time":"2024-12-24T06:23:52Z","timestamp":1735021432000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10772151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":46,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3509721","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}