{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,25]],"date-time":"2026-06-25T16:01:51Z","timestamp":1782403311806,"version":"3.54.5"},"reference-count":62,"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":["62371192"],"award-info":[{"award-number":["62371192"]}],"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.2025.3630131","type":"journal-article","created":{"date-parts":[[2025,11,7]],"date-time":"2025-11-07T18:10:13Z","timestamp":1762539013000},"page":"1-11","source":"Crossref","is-referenced-by-count":2,"title":["SARCLIP: The First Vision\u2013Language Foundation Model for SAR Image"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4218-5467","authenticated-orcid":false,"given":"Pengfei","family":"Wang","sequence":"first","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-8687-6793","authenticated-orcid":false,"given":"Zhuhao","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1500-1829","authenticated-orcid":false,"given":"Yajun","family":"Li","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Baogang","family":"Ding","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1346-5090","authenticated-orcid":false,"given":"Ding","family":"Zhang","sequence":"additional","affiliation":[{"name":"Shanghai Key Laboratory of Multidimensional Information Processing, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/0952813X.2021.1964003"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref6","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref7","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref8","article-title":"GPT-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv:2410.21276"},{"key":"ref9","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref10","volume-title":"Improving Image Generation With Better Captions","author":"Betker","year":"2023"},{"key":"ref11","article-title":"Sora: A review on background, technology, limitations, and opportunities of large vision models","author":"Liu","year":"2024","journal-title":"arXiv:2402.17177"},{"key":"ref12","article-title":"DINO: DETR with improved DeNoising anchor boxes for end-to-end object detection","author":"Zhang","year":"2022","journal-title":"arXiv:2203.03605"},{"key":"ref13","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Cong"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00604"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00765"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00212"},{"key":"ref20","first-page":"1","article-title":"What do self-supervised vision transformers learn?","volume-title":"Proc. 11th Int. Conf. Learn. Represent. (ICLR)","author":"Park"},{"key":"ref21","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Radford"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3557915.3561043"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"},{"key":"ref25","first-page":"128430","article-title":"SARDet-100K: Towards open-source benchmark and ToolKit for large-scale SAR object detection","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01519"},{"key":"ref28","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"Xu","year":"2015","journal-title":"arXiv:1502.03044"},{"key":"ref29","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3226325"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3318227"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3231851"},{"key":"ref36","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)","author":"Mi"},{"key":"ref37","first-page":"265","article-title":"Scaling laws for generative mixed-modal language models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Aghajanyan"},{"key":"ref38","article-title":"Scaling laws for neural language models","author":"Kaplan","year":"2020","journal-title":"arXiv:2001.08361"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref40","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","author":"Li","year":"2021","journal-title":"arXiv:2110.05208"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref42","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":"ref43","article-title":"BiomedCLIP: A multimodal biomedical foundation model pretrained from fifteen million scientific image-text pairs","author":"Zhang","year":"2023","journal-title":"arXiv:2303.00915"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2772-5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/rs13245104"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3390\/rs11070765"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183690"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.3390\/rs14061488"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3169339"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3005861"},{"issue":"4","key":"ref52","first-page":"906","article-title":"SAR-AIRcraft-1.0: High-resolution SAR aircraft detection and recognition dataset","volume":"12","author":"Wang","year":"2023","journal-title":"J. Radars"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.12000\/JR19097"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3291356"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/rs15112825"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/s21175769"},{"key":"ref57","article-title":"Implementation and benchmarking of perceptual image hash functions","author":"Zauner","year":"2010"},{"key":"ref58","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref59","article-title":"Neural machine translation of rare words with subword units","author":"Sennrich","year":"2015","journal-title":"arXiv:1508.07909"},{"key":"ref60","first-page":"390","article-title":"LLaVA-UHD: An LMM perceiving any aspect ratio and high-resolution images","volume-title":"Proc. Eur. Conf. Comput. Vis. (ECCV)","author":"Xu"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00294"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3390\/rs14153669"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11231801.pdf?arnumber=11231801","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,20]],"date-time":"2025-11-20T06:07:36Z","timestamp":1763618856000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11231801\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3630131","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}