{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T00:05:10Z","timestamp":1780445110287,"version":"3.54.1"},"reference-count":80,"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":["62101405"],"award-info":[{"award-number":["62101405"]}],"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"}]},{"name":"Key Technology Research Program in Shaanxi Province of China","award":["2024CY2-GJHX-17"],"award-info":[{"award-number":["2024CY2-GJHX-17"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2024.3523305","type":"journal-article","created":{"date-parts":[[2024,12,27]],"date-time":"2024-12-27T14:18:42Z","timestamp":1735309122000},"page":"1-16","source":"Crossref","is-referenced-by-count":6,"title":["Interactive Concept Network Enhanced Transformer 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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]},{"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":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3296757"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3344195"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3310619"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2021.3088865"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2024.3401696"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3190504"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00185"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3348093"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3334294"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2023.3316438"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3366984"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3192062"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3198234"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref22","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3328181"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102741"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3222606"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883199"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00813"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15561-1_2"},{"key":"ref33","first-page":"2121","article-title":"DeViSE: A deep visual-semantic embedding model","volume-title":"Proc. 26th Int. Conf. Neural Inf. Process. Syst.","volume":"26","author":"Frome"},{"key":"ref34","first-page":"1","article-title":"Unifying visual semantic embeddings with multimodal neural language models","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst., Workshops","author":"Kiros"},{"key":"ref35","first-page":"1889","article-title":"Deep fragment embeddings for bidirectional image sentence mapping","volume-title":"Proc. 27th Int. Conf. Neural Inf. Process. Syst.","author":"Karpathy"},{"key":"ref36","first-page":"220","article-title":"Composing simple image descriptions using web-scale N-grams","volume-title":"Proc. 15th Conf. Comput. Natural Lang. Learn.","author":"Li"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v26i1.8205"},{"key":"ref38","first-page":"747","article-title":"Midge: Generating image descriptions from computer vision detections","volume-title":"Proc. 13th Conf. Eur. Chapter Assoc. Comput. Linguistics","author":"Mitchell"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00188"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref45","first-page":"1","article-title":"Deep captioning with multimodal recurrent neural networks (mRNN)","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Mao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref47","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Simonyan"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.131"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20160"},{"key":"ref50","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_18"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02249"},{"key":"ref54","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"arXiv:2103.00020"},{"key":"ref55","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","author":"Wang","year":"2021","journal-title":"arXiv:2108.10904"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2017.8128075"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2942154"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3010106"},{"key":"ref64","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref65","first-page":"13042","article-title":"Unified language model pre-training for natural language understanding and generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dong"},{"key":"ref66","article-title":"Pretrained language models for text generation: A survey","author":"Li","year":"2022","journal-title":"arXiv:2201.05273"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref71","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Worksh. Intrins. Extrins. Eval. Meas. Mach. Transl. Summar.","author":"Banerjee"},{"key":"ref72","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Proc. Worksh. Text Summar. Branches Out","author":"Lin"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09294-7"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1080\/17538947.2023.2283482"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3305889"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3359316"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109893"},{"key":"ref80","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10816624.pdf?arnumber=10816624","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,10]],"date-time":"2025-01-10T00:44:02Z","timestamp":1736469842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816624\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3523305","relation":{"has-review":[{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v1\/review1","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v2\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v2\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v1\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v3\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v3\/response1","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v2\/review2","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v1\/decision1","asserted-by":"object"},{"id-type":"doi","id":"10.1109\/TGRS.2024.3523305\/v2\/review1","asserted-by":"object"}]},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}