{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,20]],"date-time":"2026-01-20T07:35:22Z","timestamp":1768894522401,"version":"3.49.0"},"reference-count":86,"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":["62171347"],"award-info":[{"award-number":["62171347"]}],"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":["62371373"],"award-info":[{"award-number":["62371373"]}],"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":["62271377"],"award-info":[{"award-number":["62271377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100017596","name":"Key Technology Research Program in Shaanxi Province of China","doi-asserted-by":"publisher","award":["2024CY2-GJHX-17"],"award-info":[{"award-number":["2024CY2-GJHX-17"]}],"id":[{"id":"10.13039\/501100017596","id-type":"DOI","asserted-by":"publisher"}]},{"name":"\u201cScientists + Engineers\u201d Project of Qin Chuangyuan in Shaanxi Province of China","award":["2024QCY-KXJ-152"],"award-info":[{"award-number":["2024QCY-KXJ-152"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3636596","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:28:48Z","timestamp":1764095328000},"page":"1-18","source":"Crossref","is-referenced-by-count":0,"title":["Adaptive Scale-Aware Semantic Memory Network for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0473-113X","authenticated-orcid":false,"given":"Cheng","family":"Zhang","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5425-6437","authenticated-orcid":false,"given":"Zhongle","family":"Ren","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1996-186X","authenticated-orcid":false,"given":"Biao","family":"Hou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Changhui","family":"Xu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianhua","family":"Meng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0047-8955","authenticated-orcid":false,"given":"Weibin","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding, Ministry of Education of China, and the Joint International Research Laboratory of Intelligent Perception and Computation, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3502805"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3539461"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3216481"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3388989"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2023.3316438"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328181"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2024.3496478"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359316"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/rs16214113"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109893"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103939"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3363491"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3475633"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","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":"ref17","article-title":"Recurrent neural network regularization","author":"Zaremba","year":"2014","journal-title":"arXiv:1409.2329"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.3390\/rs17010162"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2023.2283482"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3426359"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3523305"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3487846"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3360089"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3510414"},{"key":"ref29","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00282"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref35","article-title":"Graph neural networks in vision-language image understanding: A survey","author":"Senior","year":"2023","journal-title":"arXiv:2303.03761"},{"key":"ref36","first-page":"444","article-title":"Corpus-guided sentence generation of natural images","volume-title":"Proc. Conf. Empirical Methods Natural Lang. Process.","author":"Yang"},{"key":"ref37","first-page":"1143","article-title":"Im2Text: Describing images using 1 million captioned photographs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"24","author":"Ord\u00f3\u00f1ez"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1406.1078"},{"key":"ref39","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014","journal-title":"arXiv:1409.0473"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.667"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2929141"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2941820"},{"key":"ref44","first-page":"595","article-title":"Multimodal neural language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kiros"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref47","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref49","first-page":"11135","article-title":"Image captioning: Transforming objects into words","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Herdade"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16328"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20059-5_10"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9955644"},{"key":"ref53","article-title":"Generating more pertinent captions by leveraging semantics and style on multi-source datasets","author":"Cornia","year":"2021","journal-title":"arXiv:2111.12727"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00278"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3549555.3549585"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00179"},{"key":"ref58","article-title":"Generalization through memorization: Nearest neighbor language models","author":"Khandelwal","year":"2019","journal-title":"arXiv:1911.00172"},{"key":"ref59","article-title":"Memorizing transformers","author":"Wu","year":"2022","journal-title":"arXiv:2203.08913"},{"key":"ref60","article-title":"SAM 2: Segment anything in images and videos","author":"Ravi","year":"2024","journal-title":"arXiv:2408.00714"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01890"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548022"},{"key":"ref63","first-page":"1","article-title":"Memorization precedes generation: Learning unsupervised gans with memory networks","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kim"},{"key":"ref64","first-page":"1177","article-title":"Learning to generate with memory","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Li"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2980933"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3135711"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3390\/rs14122939"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3198234"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09294-7"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3305889"},{"key":"ref76","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"key":"ref77","first-page":"3621","article-title":"Scaling memory augmented neural networks with sparse reads and writes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rae"},{"key":"ref78","article-title":"Neural Turing machines","author":"Graves","year":"2014","journal-title":"arXiv:1410.5401"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref80","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Worksh. Text Summar. Branches Out","author":"Lin"},{"key":"ref81","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrins. Extrins. Eval. Meas. Mach. Transl. Summar.","author":"Banerjee"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3580686"},{"key":"ref85","first-page":"1","article-title":"Supervision exists everywhere: A data efficient contrastive language-image pre-training paradigm","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Li"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2025.3598283"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11268351.pdf?arnumber=11268351","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T06:18:43Z","timestamp":1764915523000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11268351\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":86,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3636596","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}