{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T15:14:37Z","timestamp":1788621277571,"version":"build-2803163510"},"reference-count":66,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,9,1]],"date-time":"2026-09-01T00:00:00Z","timestamp":1788220800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1016\/j.jvcir.2026.104906","type":"journal-article","created":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T15:29:10Z","timestamp":1784820550000},"page":"104906","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["ONIR: Object-Noted Tagging for Aerial Image Captioning generation"],"prefix":"10.1016","volume":"120","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4265-2205","authenticated-orcid":false,"given":"Xing","family":"Zi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-7001-3039","authenticated-orcid":false,"given":"Tengjun","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianjing","family":"Fan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xian","family":"Tao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinyi","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ali","family":"Braytee","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mukesh","family":"Prasad","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2026.104906_b1","doi-asserted-by":"crossref","first-page":"154086","DOI":"10.1109\/ACCESS.2021.3128140","article-title":"A systematic survey of remote sensing image captioning","volume":"9","author":"Zhao","year":"2021","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104906_b2","article-title":"Understanding remote sensing imagery like reading a text document: What can remote sensing image captioning offer?","volume":"131","author":"Huang","year":"2024","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"issue":"6","key":"10.1016\/j.jvcir.2026.104906_b3","doi-asserted-by":"crossref","first-page":"3623","DOI":"10.1109\/TGRS.2017.2677464","article-title":"Can a machine generate humanlike language descriptions for a remote sensing image?","volume":"55","author":"Shi","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b4","article-title":"Transforming remote sensing images to textual descriptions","volume":"108","author":"Zia","year":"2022","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.jvcir.2026.104906_b5","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3156","article-title":"Show and tell: A neural image caption generator","author":"Vinyals","year":"2015"},{"issue":"4","key":"10.1016\/j.jvcir.2026.104906_b6","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","article-title":"Exploring models and data for remote sensing image caption generation","volume":"56","author":"Lu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.jvcir.2026.104906_b7","doi-asserted-by":"crossref","first-page":"612","DOI":"10.3390\/rs11060612","article-title":"Description generation for remote sensing images using attribute attention mechanism","volume":"11","author":"Zhang","year":"2019","journal-title":"Remote. Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b8","series-title":"Meshed-memory transformer for image captioning","author":"Cornia","year":"2020"},{"issue":"35","key":"10.1016\/j.jvcir.2026.104906_b9","doi-asserted-by":"crossref","first-page":"26661","DOI":"10.1007\/s11042-020-09294-7","article-title":"Remote sensing image caption generation via transformer and reinforcement learning","volume":"79","author":"Shen","year":"2020","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.jvcir.2026.104906_b10","series-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104906_b11","series-title":"Visual instruction tuning","author":"Liu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b12","series-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b13","series-title":"Flamingo: a visual language model for few-shot learning","author":"Alayrac","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104906_b14","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b15","series-title":"Minigpt-v2: large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b16","series-title":"Tag2text: Guiding vision-language model via image tagging","author":"Huang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b17","series-title":"Lora: low-rank adaptation of large language models","author":"Hu","year":"2021"},{"key":"10.1016\/j.jvcir.2026.104906_b18","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3156","article-title":"Show and tell: A neural image caption generator","author":"Vinyals","year":"2015"},{"key":"10.1016\/j.jvcir.2026.104906_b19","series-title":"International Conference on Machine Learning","first-page":"2048","article-title":"Show attend and tell: Neural image caption generation with visual attention.","author":"Xu","year":"2015"},{"issue":"4","key":"10.1016\/j.jvcir.2026.104906_b20","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","article-title":"Exploring models and data for remote sensing image caption generation","volume":"56","author":"Lu","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens.","ISSN":"https:\/\/id.crossref.org\/issn\/1558-0644","issn-type":"print"},{"key":"10.1016\/j.jvcir.2026.104906_b21","series-title":"Proceedings of the 32nd International Conference on Machine Learning","first-page":"2048","article-title":"Attend and tell: Neural image caption generation with visual attention","volume":"vol.37","author":"Xu","year":"2015"},{"issue":"6","key":"10.1016\/j.jvcir.2026.104906_b22","doi-asserted-by":"crossref","first-page":"3623","DOI":"10.1109\/TGRS.2017.2677464","volume":"55","author":"Shi","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"4","key":"10.1016\/j.jvcir.2026.104906_b23","doi-asserted-by":"crossref","first-page":"2183","DOI":"10.1109\/TGRS.2017.2776321","article-title":"Exploring models and data for remote sensing image caption generation","volume":"56","author":"Lu","year":"2017","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b24","first-page":"1","article-title":"A novel svm-based decoder for remote sensing image captioning","volume":"60","author":"Hoxha","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b25","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104906_b26","doi-asserted-by":"crossref","unstructured":"Peter Anderson, Xiaodong He, Chris Buehler, Damien Teney, Mark Johnson, Stephen Gould, Lei Zhang, Bottom-up and top-down attention for image captioning and visual question answering, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 6077\u20136086.","DOI":"10.1109\/CVPR.2018.00636"},{"key":"10.1016\/j.jvcir.2026.104906_b27","doi-asserted-by":"crossref","unstructured":"Xuying Zhang, Xiaoshuai Sun, Yunpeng Luo, Jiayi Ji, Yiyi Zhou, Yongjian Wu, Feiyue Huang, Rongrong Ji, Rstnet: Captioning with adaptive attention on visual and non-visual words., in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 15465\u201315474.","DOI":"10.1109\/CVPR46437.2021.01521"},{"key":"10.1016\/j.jvcir.2026.104906_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.engappai.2022.105076","article-title":"Generating the captions for remote sensing images: A spatial-channel attention based memory-guided transformer approach","volume":"114","author":"Gajbhiye","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"10.1016\/j.jvcir.2026.104906_b29","doi-asserted-by":"crossref","first-page":"904","DOI":"10.1109\/ACCESS.2024.3522585","article-title":"Enhanced clip-gpt framework for cross-lingual remote sensing image captioning","volume":"13","author":"Song","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104906_b30","doi-asserted-by":"crossref","first-page":"584","DOI":"10.1016\/j.isprsjprs.2026.03.029","article-title":"Material proportion guided hyperspectral image super-resolution via unmixing","volume":"235","author":"Xu","year":"2026","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b31","series-title":"Captext: large language model-based caption generation from image context and description","author":"Ghosh","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b32","unstructured":"Zihao Ni, Yinghao Xu, Weibo Zhang, Zhaoyun Zong, Peng Ren, A size-aware graph embedding approach to remote sensing image captioning with object relative size information, IEEE Trans. Geosci. Remote Sens. 2026."},{"key":"10.1016\/j.jvcir.2026.104906_b33","series-title":"Benchmarking and improving detail image caption","author":"Dong","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b34","series-title":"Hallucination of multimodal large language models: a survey","author":"Bai","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b35","doi-asserted-by":"crossref","first-page":"23716","DOI":"10.52202\/068431-1723","article-title":"Flamingo: a visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.jvcir.2026.104906_b36","series-title":"Instructblip: towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b37","series-title":"Large language models for captioning and retrieving remote sensing images","author":"Daniel Silva","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b38","doi-asserted-by":"crossref","first-page":"64","DOI":"10.1016\/j.isprsjprs.2025.01.020","article-title":"Skyeyegpt: Unifying remote sensing vision-language tasks via instruction tuning with large language model","volume":"221","author":"Zhan","year":"2025","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b39","series-title":"Rsgpt: a remote sensing vision language model and benchmark","author":"Hu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b40","series-title":"Evaluating object hallucination in large vision-language models","author":"Li","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b41","series-title":"A review of multimodal explainable artificial intelligence: past, present and future","author":"Sun","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b42","series-title":"Cross-modal retrieval: a systematic review of methods and future directions","author":"Wang","year":"2024"},{"issue":"11","key":"10.1016\/j.jvcir.2026.104906_b43","doi-asserted-by":"crossref","first-page":"2321","DOI":"10.1109\/LGRS.2015.2475299","article-title":"Deep learning based feature selection for remote sensing scene classification","volume":"12","author":"Zou","year":"2015","journal-title":"IEEE Geosci. Remote. Sens. Lett."},{"key":"10.1016\/j.jvcir.2026.104906_b44","first-page":"1","article-title":"Msanet: Multiscale self-attention aggregation network for few-shot aerial imagery segmentation","volume":"62","author":"Li","year":"2023","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b45","unstructured":"Syed Waqas Zamir, Aditya Arora, Akshita Gupta, Salman Khan, Guolei Sun, Fahad Shahbaz Khan, Fan Zhu, Ling Shao, Gui-Song Xia, Xiang Bai, isaid: A large-scale dataset for instance segmentation in aerial images., in: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops, 2019, pp. 28\u201337."},{"key":"10.1016\/j.jvcir.2026.104906_b46","series-title":"Loveda: a remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"Wang","year":"2021"},{"issue":"1","key":"10.1016\/j.jvcir.2026.104906_b47","doi-asserted-by":"crossref","first-page":"574","DOI":"10.1109\/TGRS.2018.2858817","article-title":"Fully convolutional networks for multisource building extraction from an open aerial and satellite imagery data set","volume":"57","author":"Ji","year":"2018","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.jvcir.2026.104906_b48","series-title":"Vrsbench: a versatile vision-language benchmark dataset for remote sensing image understanding","author":"Li","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b49","series-title":"Deep Learning","first-page":"1","author":"Afandy","year":"2022"},{"key":"10.1016\/j.jvcir.2026.104906_b50","series-title":"Proceedings of the 3rd International Conference on Computer, Artificial Intelligence and Control Engineering","first-page":"405","article-title":"A survey of multimodel large language models","author":"Liang","year":"2024"},{"key":"10.1016\/j.jvcir.2026.104906_b51","unstructured":"Xizhang Yao, Guanghui Yue, Jeremiah D Deng, Hanhe Lin, Wei Zhou, Amlpf-clip: adaptive prompting and distilled learning for imbalanced histopathological image classification, IEEE J. Biomed. Health Informatics 2025."},{"key":"10.1016\/j.jvcir.2026.104906_b52","series-title":"2025 IEEE International Symposium on Circuits and Systems","first-page":"1","article-title":"Clip-dqa: Blindly evaluating dehazed images from global and local perspectives using clip","author":"Zeng","year":"2025"},{"key":"10.1016\/j.jvcir.2026.104906_b53","doi-asserted-by":"crossref","DOI":"10.1109\/LSP.2025.3615082","article-title":"Clip-dqa v2: exploring clip for dehazed image quality assessment from a fragment-level perspective","author":"Zeng","year":"2025","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.jvcir.2026.104906_b54","doi-asserted-by":"crossref","first-page":"1820","DOI":"10.1109\/LSP.2024.3420083","article-title":"Vision-language consistency guided multi-modal prompt learning for blind ai generated image quality assessment","volume":"31","author":"Fu","year":"2024","journal-title":"IEEE Signal Process. Lett."},{"issue":"3","key":"10.1016\/j.jvcir.2026.104906_b55","doi-asserted-by":"crossref","first-page":"833","DOI":"10.1109\/TBC.2024.3391060","article-title":"Adaptive mixed-scale feature fusion network for blind ai-generated image quality assessment","volume":"70","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Broadcast."},{"key":"10.1016\/j.jvcir.2026.104906_b56","doi-asserted-by":"crossref","unstructured":"Li Yu, Situo Wang, Wei Zhou, Moncef Gabbouj, Dvlta-vqa: Decoupled vision-language modeling with text-guided adaptation for blind video quality assessment, IEEE Trans. Circuits Syst. Video Technol. 2026.","DOI":"10.1109\/TCSVT.2026.3657415"},{"key":"10.1016\/j.jvcir.2026.104906_b57","doi-asserted-by":"crossref","unstructured":"Fan Liu, Delong Chen, Zhangqingyun Guan, Xiaocong Zhou, Jiale Zhu, Qiaolin Ye, Liyong Fu, Jun Zhou, Remoteclip: A vision language foundation model for remote sensing, IEEE Trans. Geosci. Remote Sens. 2024.","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"10.1016\/j.jvcir.2026.104906_b58","article-title":"Rs-clip: Zero shot remote sensing scene classification via contrastive vision-language supervision","volume":"124","author":"Li","year":"2023","journal-title":"Int. J. Appl. Earth Obs. Geoinf."},{"key":"10.1016\/j.jvcir.2026.104906_b59","series-title":"Minigpt-4: enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b60","series-title":"Btlm-3b-8k: 7b parameter performance in a 3b parameter model","author":"Dey","year":"2023"},{"key":"10.1016\/j.jvcir.2026.104906_b61","doi-asserted-by":"crossref","first-page":"91150","DOI":"10.1109\/ACCESS.2022.3202193","article-title":"Exploring data and models in sar ship image captioning","volume":"10","author":"Zhao","year":"2022","journal-title":"IEEE Access"},{"key":"10.1016\/j.jvcir.2026.104906_b62","series-title":"Proceedings of the 18th SIGSPATIAL International Conference on Advances in Geographic Information Systems","isbn-type":"print","doi-asserted-by":"crossref","first-page":"270","DOI":"10.1145\/1869790.1869829","article-title":"Bag-of-visual-words and spatial extensions for land-use classification","author":"Yang","year":"2010","ISBN":"https:\/\/id.crossref.org\/isbn\/9781450304283"},{"key":"10.1016\/j.jvcir.2026.104906_b63","doi-asserted-by":"crossref","unstructured":"Kishore Papineni, Salim Roukos, Todd Ward, Wei-Jing Zhu, Bleu: a method for automatic evaluation of machine translation, in: Proceedings of the 40th Annual Meeting of the Association for Computational Linguistics, 2002, pp. 311\u2013318.","DOI":"10.3115\/1073083.1073135"},{"key":"10.1016\/j.jvcir.2026.104906_b64","unstructured":"Satanjeev Banerjee, Alon Lavie, Meteor: An automatic metric for mt evaluation with improved correlation with human judgments., in: Proceedings of the Acl Workshop on Intrinsic and Extrinsic Evaluation Measures for Machine Translation and\/Or Summarization, 2005, pp. 65\u201372."},{"key":"10.1016\/j.jvcir.2026.104906_b65","series-title":"Text Summarization Branches Out","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries.","author":"Lin","year":"2004"},{"key":"10.1016\/j.jvcir.2026.104906_b66","unstructured":"Jiawei Gu, Xuhui Jiang, Zhichao Shi, Hexiang Tan, Xuehao Zhai, Chengjin Xu, Wei Li, Yinghan Shen, Shengjie Ma, Honghao Liu, et al., A survey on llm-as-a-judge, Innov. 2024."}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326002014?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320326002014?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,9,5]],"date-time":"2026-09-05T14:55:37Z","timestamp":1788620137000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320326002014"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9]]},"references-count":66,"alternative-id":["S1047320326002014"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104906","relation":{},"ISSN":["1047-3203"],"issn-type":[{"value":"1047-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,9]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"ONIR: Object-Noted Tagging for Aerial Image Captioning generation","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2026.104906","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 The Authors. Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"104906"}}