{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T11:04:28Z","timestamp":1781780668606,"version":"3.54.5"},"reference-count":54,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62471394"],"award-info":[{"award-number":["62471394"]}],"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":["U21B2041"],"award-info":[{"award-number":["U21B2041"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.patcog.2026.113399","type":"journal-article","created":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T00:27:14Z","timestamp":1772497634000},"page":"113399","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"C","title":["A benchmark For multi-lingual vision-language learning in remote sensing image captioning"],"prefix":"10.1016","volume":"178","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7028-4956","authenticated-orcid":false,"given":"Qi","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-3300-0805","authenticated-orcid":false,"given":"Qing","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-0587-9832","authenticated-orcid":false,"given":"Tao","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6000-8168","authenticated-orcid":false,"given":"Junyu","family":"Gao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0640-3922","authenticated-orcid":false,"given":"Weiping","family":"Ni","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1825-8988","authenticated-orcid":false,"given":"Junzheng","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"6","key":"10.1016\/j.patcog.2026.113399_bib0001","doi-asserted-by":"crossref","first-page":"1641","DOI":"10.1109\/TGRS.2007.894928","article-title":"Dynamics monitoring and disaster assessment for watershed management using time-Series satellite images","volume":"45","author":"Rau","year":"2007","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113399_bib0002","first-page":"1","article-title":"Single-stream extractor network with contrastive pre-training for remote-sensing change captioning","volume":"62","author":"Zhou","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.patcog.2026.113399_bib0003","doi-asserted-by":"crossref","first-page":"2549","DOI":"10.1109\/36.885202","article-title":"The use of multisource satellite and geospatial data to study the effect of urbanization on primary productivity in the United States","volume":"38","author":"Imhoff","year":"2000","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"12","key":"10.1016\/j.patcog.2026.113399_bib0004","doi-asserted-by":"crossref","first-page":"10532","DOI":"10.1109\/TGRS.2020.3044054","article-title":"Word- sentence framework for remote sensing image captioning","volume":"59","author":"Wang","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.patcog.2026.113399_bib0005","doi-asserted-by":"crossref","first-page":"5246","DOI":"10.1109\/TGRS.2020.3010106","article-title":"Truncation cross entropy loss for remote sensing image captioning","volume":"59","author":"Li","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113399_bib0006","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Learning to guide decoding for image captioning","volume":"32","author":"Jiang","year":"2018"},{"key":"10.1016\/j.patcog.2026.113399_bib0007","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"4894","article-title":"Boosting image captioning with attributes","author":"Yao","year":"2017"},{"key":"10.1016\/j.patcog.2026.113399_bib0008","series-title":"2016 International Conference on Computer, Information and Telecommunication Systems (Cits)","first-page":"1","article-title":"Deep semantic understanding of high resolution remote sensing image","author":"Qu","year":"2016"},{"key":"10.1016\/j.patcog.2026.113399_bib0009","first-page":"1","article-title":"Remote-sensing image captioning based on multilayer aggregated transformer","volume":"19","author":"Liu","year":"2022","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.patcog.2026.113399_bib0010","first-page":"1","article-title":"A multiscale grouping transformer with CLIP latents for remote sensing image captioning","volume":"62","author":"Meng","year":"2024","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113399_bib0011","unstructured":"D.C. Bui, N.H. Nguyen, K. Nguyen, UIT-OpenViIC: a novel benchmark for evaluating image captioning in Vietnamese, (2023), arXiv preprint arXiv: 2305.04166."},{"key":"10.1016\/j.patcog.2026.113399_bib0012","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"4634","article-title":"Attention on attention for image captioning","author":"Huang","year":"2019"},{"issue":"3","key":"10.1016\/j.patcog.2026.113399_bib0013","doi-asserted-by":"crossref","first-page":"1985","DOI":"10.1109\/TGRS.2019.2951636","article-title":"Sound active attention framework for remote sensing image captioning","volume":"58","author":"Lu","year":"2019","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.patcog.2026.113399_bib0014","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.patcog.2026.113399_bib0015","first-page":"1","article-title":"RSCaMa: remote sensing image change captioning with state space model","volume":"21","author":"Liu","year":"2024","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"10.1016\/j.patcog.2026.113399_bib0016","unstructured":"A. Gu, T. Dao, Mamba: linear-time sequence modeling with selective state spaces, (2023), arXiv preprint arXiv: 2312.00752."},{"key":"10.1016\/j.patcog.2026.113399_bib0017","unstructured":"J. Bai, S. Bai, Y. Chu, Z. Cui, K. Dang, X. Deng, Y. Fan, W. Ge, Y. Han, F. Huang, et al., Qwen technical report, (2023), arXiv preprint arXiv: 2309.16609."},{"key":"10.1016\/j.patcog.2026.113399_bib0018","unstructured":"Z. Cai, M. Cao, H. Chen, K. Chen, K. Chen, X. Chen, X. Chen, Z. Chen, Z. Chen, P. Chu, et al., Internlm2 technical report, (2024), arXiv preprint arXiv: 2403.17297."},{"key":"10.1016\/j.patcog.2026.113399_bib0019","unstructured":"H. Touvron, L. Martin, K. Stone, P. Albert, A. Almahairi, Y. Babaei, N. Bashlykov, S. Batra, P. Bhargava, S. Bhosale, et al., Llama 2: open foundation and fine-tuned chat models, (2023), arXiv preprint arXiv: 2307.09288."},{"key":"10.1016\/j.patcog.2026.113399_bib0020","unstructured":"P. Wang, S. Bai, S. Tan, S. Wang, Z. Fan, J. Bai, K. Chen, X. Liu, J. Wang, W. Ge, et al., Qwen2-vl: enhancing vision-language model\u2019s perception of the world at any resolution, (2024), arXiv preprint arXiv: 2409.12191."},{"key":"10.1016\/j.patcog.2026.113399_bib0021","doi-asserted-by":"crossref","unstructured":"Z. Chen, W. Wang, H. Tian, S. Ye, Z. Gao, E. Cui, W. Tong, K. Hu, J. Luo, Z. Ma, et al., How far are we to gpt-4v? closing the gap to commercial multimodal models with open-source suites, (2024), arXiv preprint arXiv: 2404.16821.","DOI":"10.1007\/s11432-024-4231-5"},{"key":"10.1016\/j.patcog.2026.113399_bib0022","unstructured":"H. Lu, W. Liu, B. Zhang, B. Wang, K. Dong, B. Liu, J. Sun, T. Ren, Z. Li, H. Yang, et al., Deepseek-vl: towards real-world vision-language understanding, (2024), arXiv preprint arXiv: 2403.05525."},{"key":"10.1016\/j.patcog.2026.113399_bib0023","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"26296","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2024"},{"issue":"4","key":"10.1016\/j.patcog.2026.113399_bib0024","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.patcog.2026.113399_bib0025","first-page":"1","article-title":"NWPU-captions dataset and MLCA-Net for remote sensing image captioning","volume":"60","author":"Cheng","year":"2022","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"6","key":"10.1016\/j.patcog.2026.113399_bib0026","doi-asserted-by":"crossref","first-page":"939","DOI":"10.3390\/rs12060939","article-title":"A multi-level attention model for remote sensing image captions","volume":"12","author":"Li","year":"2020","journal-title":"Remote Sens."},{"issue":"9","key":"10.1016\/j.patcog.2026.113399_bib0027","doi-asserted-by":"crossref","first-page":"2347","DOI":"10.1109\/TMM.2019.2896494","article-title":"COCO-CN for cross-lingual image tagging, captioning, and retrieval","volume":"21","author":"Li","year":"2019","journal-title":"IEEE Trans. Multimedia"},{"key":"10.1016\/j.patcog.2026.113399_bib0028","unstructured":"A.-C. Pham, V.-Q. Nguyen, T.-H. Vuong, Q.-T. Ha, KTVIC: a Vietnamese image captioning dataset on the life domain, (2024), arXiv preprint arXiv: 2401.08100."},{"key":"10.1016\/j.patcog.2026.113399_bib0029","series-title":"IEEE Conference on Computer Vision and Pattern Recognition, CVPR 2021, Virtual, June 19\u201325, 2021","first-page":"4155","article-title":"UC2: universal cross-lingual cross-modal vision-and-language pre-training","author":"Zhou","year":"2021"},{"key":"10.1016\/j.patcog.2026.113399_bib0030","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.patcog.2026.113399_bib0031","doi-asserted-by":"crossref","unstructured":"Y. Yoshikawa, Y. Shigeto, A. Takeuchi, STAIR captions: constructing a large-scale Japanese image caption dataset, (2017), arXiv preprint arXiv: 1705.00823.","DOI":"10.18653\/v1\/P17-2066"},{"key":"10.1016\/j.patcog.2026.113399_bib0032","series-title":"5th Workshop on Vision and Language","first-page":"70","article-title":"Multi30K: multilingual english-German image descriptions","author":"Elliott","year":"2016"},{"key":"10.1016\/j.patcog.2026.113399_bib0033","series-title":"Proceedings of the 54th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","first-page":"1780","article-title":"Cross-lingual image caption generation","author":"Miyazaki","year":"2016"},{"key":"10.1016\/j.patcog.2026.113399_bib0034","doi-asserted-by":"crossref","unstructured":"J. Hitschler, S. Schamoni, S. Riezler, Multimodal pivots for image caption translation, (2016), arXiv preprint arXiv: 1601.03916.","DOI":"10.18653\/v1\/P16-1227"},{"key":"10.1016\/j.patcog.2026.113399_bib0035","series-title":"Proceedings of the 25th ACM International Conference on Multimedia","first-page":"1549","article-title":"Fluency-guided cross-lingual image captioning","author":"Lan","year":"2017"},{"issue":"10","key":"10.1016\/j.patcog.2026.113399_bib0036","doi-asserted-by":"crossref","first-page":"1865","DOI":"10.1109\/JPROC.2017.2675998","article-title":"Remote sensing image scene classification: benchmark and state of the art","volume":"105","author":"Cheng","year":"2017","journal-title":"Proc. IEEE"},{"issue":"63","key":"10.1016\/j.patcog.2026.113399_bib0037","first-page":"1","article-title":"Generalized few-shot semantic segmentation for remote sensing images","author":"Jia","year":"2025","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113399_bib0038","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1109\/TGRS.2020.3042202","article-title":"High-resolution remote sensing image captioning based on structured attention","volume":"60","author":"Zhao","year":"2021","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"12","key":"10.1016\/j.patcog.2026.113399_bib0039","doi-asserted-by":"crossref","first-page":"10532","DOI":"10.1109\/TGRS.2020.3044054","article-title":"Word\u2013sentence framework for remote sensing image captioning","volume":"59","author":"Wang","year":"2020","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"key":"10.1016\/j.patcog.2026.113399_bib0040","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2020.105920","article-title":"Remote sensing image captioning via variational autoencoder and reinforcement learning","volume":"203","author":"Shen","year":"2020","journal-title":"Knowl. Based Syst."},{"key":"10.1016\/j.patcog.2026.113399_bib0041","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109893","article-title":"Learning consensus-aware semantic knowledge for remote sensing image captioning","volume":"145","author":"Li","year":"2024","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113399_bib0042","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"17449","article-title":"Enhance vision-language alignment with noise","volume":"39","author":"Huang","year":"2025"},{"key":"10.1016\/j.patcog.2026.113399_bib0043","unstructured":"R. Zhu, S. Huang, Z. Jiao, H. Zhang, Explore how to inject beneficial noise in mllms, (2025), arXiv preprint arXiv: 2511.12917."},{"key":"10.1016\/j.patcog.2026.113399_bib0044","unstructured":"Z. Chen, W. Wang, Y. Cao, Y. Liu, Z. Gao, E. Cui, J. Zhu, S. Ye, H. Tian, Z. Liu, et al., Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling, (2024), arXiv preprint arXiv: 2412.05271."},{"key":"10.1016\/j.patcog.2026.113399_bib0045","series-title":"International Conference on Machine Learning","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021"},{"key":"10.1016\/j.patcog.2026.113399_bib0046","unstructured":"Z. Yang, L. Li, K. Lin, J. Wang, C.-C. Lin, Z. Liu, L. Wang, The dawn of lmms: preliminary explorations with gpt-4v (ision), arXiv preprint arXiv: 2309.17421 9 (1) (2023) 1."},{"key":"10.1016\/j.patcog.2026.113399_bib0047","unstructured":"Y. Hu, J. Yuan, C. Wen, X. Lu, X. Li, Rsgpt: a remote sensing vision language model and benchmark, (2023), arXiv preprint arXiv: 2307.15266."},{"key":"10.1016\/j.patcog.2026.113399_bib0048","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"27831","article-title":"Geochat: grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2024"},{"key":"10.1016\/j.patcog.2026.113399_bib0049","first-page":"311","article-title":"Bleu: a method for automatic evaluation of machine translation","author":"Papineni","year":"2002","journal-title":"Proc. Assoc. Comput. Linguist."},{"key":"10.1016\/j.patcog.2026.113399_bib0050","first-page":"376","article-title":"Meteor universal: language specific translation evaluation for any target language","author":"Denkowski","year":"2014","journal-title":"Proc. Workshop Stat. Mach. Transl."},{"key":"10.1016\/j.patcog.2026.113399_bib0051","first-page":"138","article-title":"Automatic evaluation of machine translation quality using n-gram co-occurrence statistics","author":"Doddington","year":"2002","journal-title":"Proc. Int. Conf. Human Lang. Technol. Res."},{"key":"10.1016\/j.patcog.2026.113399_bib0052","first-page":"4566","article-title":"Cider: consensus-based image description evaluation","author":"Vedantam","year":"2015","journal-title":"Proc. IEEE Conf. Comput. Vis. Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.113399_bib0053","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and visual question answering","author":"Anderson","year":"2018"},{"key":"10.1016\/j.patcog.2026.113399_bib0054","series-title":"International Conference on Learning Representations","article-title":"LoRA: low-rank adaptation of large language models","author":"Hu","year":"2022"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600364X?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S003132032600364X?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,5,21]],"date-time":"2026-05-21T16:57:02Z","timestamp":1779382622000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S003132032600364X"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":54,"alternative-id":["S003132032600364X"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113399","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A benchmark For multi-lingual vision-language learning in remote sensing image captioning","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.113399","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"113399"}}