{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T14:17:06Z","timestamp":1788185826838,"version":"build-2803163510"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T00:00:00Z","timestamp":1784851200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"},{"start":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T00:00:00Z","timestamp":1788134400000},"content-version":"vor","delay-in-days":38,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0"}],"funder":[{"name":"Major Project of Yunnan Science and Technology","award":["Grant No.: 202302AE09002003"],"award-info":[{"award-number":["Grant No.: 202302AE09002003"]}]},{"name":"Yunnan Provincial Science and Technology Talent and Platform Program","award":["202405AF140013"],"award-info":[{"award-number":["202405AF140013"]}]},{"name":"Major Project of Yunnan Provincial Science and Technology","award":["202502AE090019"],"award-info":[{"award-number":["202502AE090019"]}]},{"name":"Scientific Research Fund Project of Yunnan Provincial Department of Education","award":["Grant No.: 2023J0461"],"award-info":[{"award-number":["Grant No.: 2023J0461"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Sci Rep"],"DOI":"10.1038\/s41598-026-60482-1","type":"journal-article","created":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T19:24:20Z","timestamp":1784921060000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Robust and accurate multimodal information extraction from tobacco box labels using MLDP"],"prefix":"10.1038","volume":"16","author":[{"given":"Songling","family":"Huang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minghua","family":"Han","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianping","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuyan","family":"Bai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,7,24]]},"reference":[{"issue":"5","key":"60482_CR1","doi-asserted-by":"publisher","first-page":"90","DOI":"10.16472\/j.chinatobacco.2020.289","volume":"27","author":"W Ge","year":"2021","unstructured":"Ge, W. et al. Current situation and prospects of the quality traceability system construction in China\u2019s tobacco industry. Chinese Tobacco Sci. 27(5), 90\u201399. https:\/\/doi.org\/10.16472\/j.chinatobacco.2020.289 (2021).","journal-title":"Chinese Tobacco Sci."},{"key":"60482_CR2","doi-asserted-by":"publisher","unstructured":"LiZhonhua, Liu Yalong, Du Yu, Zhou Jiaxian, Guo Liang, Pu Xuesong. Research on Data Collection and Integration Methods for the Whole Industrial Chain of the Tobacco Industry under the New Retail Model. Modern Market. 2022, 12(4): 81\u201388. https:\/\/doi.org\/10.12677\/mom.2022.124010.","DOI":"10.12677\/mom.2022.124010"},{"issue":"10","key":"60482_CR3","first-page":"35","volume":"9","author":"L Wenhua","year":"2010","unstructured":"Wenhua, L. & Gailong, L. OCR Post-processing Method Based on NLP. Software Guide 9(10), 35\u201336 (2010).","journal-title":"Software Guide"},{"key":"60482_CR4","first-page":"133","volume":"41","author":"Z Yngchun","year":"2022","unstructured":"Yngchun, Z. The Zhixue intelligent correction system based on OCR-NLP graphic-text processing and its application in senior high school english writing continuation. English Campus 41, 133\u2013135 (2022).","journal-title":"English Campus"},{"key":"60482_CR5","first-page":"46","volume":"6","author":"M Tianlong","year":"2023","unstructured":"Tianlong, M., Yanan, H. & Ying, Z. Application scenario research of the treasury system based on the integration of RPA\/OCR\/NLP technologies. Informat. Forum 6, 46\u201352 (2023).","journal-title":"Informat. Forum"},{"key":"60482_CR6","doi-asserted-by":"publisher","first-page":"50050","DOI":"10.1109\/ACCESS.2021.3068728","volume":"9","author":"SK Liu","year":"2021","unstructured":"Liu, S. K. et al. Metaknowledge extraction based on multi-modal documents. IEEE Access 9, 50050\u201350060. https:\/\/doi.org\/10.1109\/ACCESS.2021.3068728 (2021).","journal-title":"IEEE Access"},{"key":"60482_CR7","doi-asserted-by":"publisher","first-page":"112","DOI":"10.1038\/s41598-023-50179-0.10.1038\/s41598","volume":"14","author":"A Takano","year":"2024","unstructured":"Takano, A., Cole, T. C. H. & Konagai, H. A novel automated label data extraction and database generation system from herbarium specimen images using OCR and NER. Sci Rep 14, 112. https:\/\/doi.org\/10.1038\/s41598-023-50179-0.10.1038\/s41598 (2024).","journal-title":"Sci Rep"},{"key":"60482_CR8","doi-asserted-by":"publisher","DOI":"10.3389\/frai.2024.1428716","volume":"7","author":"A Salvi","year":"2025","unstructured":"Salvi, A. et al. Ocular biometry OCR: A machine learning algorithm leveraging optical character recognition to extract intraocular lens biometry measurements. Front. Artif. Intell. 7, 1428716. https:\/\/doi.org\/10.3389\/frai.2024.1428716 (2025).","journal-title":"Front. Artif. Intell."},{"key":"60482_CR9","unstructured":"Lu J, Batra D, Parikh D, Lee S. ViLBERT: Pretraining Task-Agnostic Visiolinguistic Representations for Vision-and-Language Tasks. arXiv preprint arXiv:1908.02265, 2019."},{"key":"60482_CR10","doi-asserted-by":"publisher","unstructured":"Xu Y, Li M, Cui L, Huang S, Wei F, Zhou M. LayoutLM: Pre-training of Text and Layout for Document Image Understanding. In: Proc 26th ACM SIGKDD Int. Confer. Knowledge Disc. Data Min. ACM; 2020:1192\u20131200. https:\/\/doi.org\/10.1145\/3394486.3403172.","DOI":"10.1145\/3394486.3403172"},{"key":"60482_CR11","first-page":"1050","volume":"9","author":"E Bugliarello","year":"2021","unstructured":"Bugliarello, E., Cotterell, R., Okazaki, N. & Elliott, D. Multimodal pretraining unmasked: A meta-analysis and a unified framework of vision-and-language BERTs. Trans. Assoc. Comput. Linguist. 9, 1050\u20131067 (2021).","journal-title":"Trans. Assoc. Comput. Linguist."},{"key":"60482_CR12","unstructured":"He P, Gao J, Chen W. DeBERTaV3: Improving DeBERTa using ELECTRA-style pre-training with gradient-disentangled embedding sharing. In: Int. Conf. Learn. Represent. (ICLR). 2023."},{"key":"60482_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.compbiomed.2024.107921","volume":"170","author":"BS Al-Smadi","year":"2024","unstructured":"Al-Smadi, B. S. DeBERTa-BiLSTM: A multi-label classification model of Arabic medical questions using pre-trained models and deep learning. Comput. Biol. Med. 170, 107921. https:\/\/doi.org\/10.1016\/j.compbiomed.2024.107921 (2024).","journal-title":"Comput. Biol. Med."},{"key":"60482_CR14","unstructured":"Aziz A, Hossain MA, Chy AN. Enhancing the DeBERTa transformers model for classifying sentences from biomedical abstracts. arXiv preprint arXiv:2406.03001 2024."},{"key":"60482_CR15","unstructured":"Hinton G, Vinyals O, Dean J. Distilling the knowledge in a neural network. arXiv preprint arXiv:1503.02531 2015.."},{"key":"60482_CR16","unstructured":"Li C, Liu W, Guo R, Yin X, Jiang K, Du Y, Du Y, Zhu L, Lai B, Hu X, Yu D, Ma Y. PP-OCRv3: More attempts for the improvement of ultra-lightweight OCR system. arXiv preprint arXiv:2206.03001 2022."},{"key":"60482_CR17","doi-asserted-by":"crossref","unstructured":"Li M, Xu Y, Cui L, Huang S, Wei F, Li Z, Zhou M. DocBank: A Benchmark Dataset for Document Layout Analysis. arXiv preprint arXiv:2006.01038, 2020.","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"60482_CR18","unstructured":"Inoue, Hiroshi. \u201cMulti-Sample Dropout for Accelerated Training and Better Generalization.\u201d arXiv preprint arXiv:1905.09788 (2020)."},{"key":"60482_CR19","doi-asserted-by":"crossref","unstructured":"Liao, Minghui, Zhaoyi Wan, Cong Yao, Kai Chen, and Xiang Bai. \u201cReal-time Scene Text Detection with Differentiable Binarization.\u201d arXiv preprint arXiv:1911.08947 (2019).","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"60482_CR20","unstructured":"Bourne, Jonathan. \u201cCLOCR-C: Context Leveraging OCR Correction with Pre-trained Language Models.\u201d arXiv preprint arXiv:2408.17428 (2024)."},{"issue":"1","key":"60482_CR21","doi-asserted-by":"publisher","first-page":"107","DOI":"10.56028\/aetr.6.1.107.2023","volume":"6","author":"B Long","year":"2023","unstructured":"Long, B., Tan, F. & Newman, M. Ensemble DeBERTa models on USMLE patient notes automatic scoring using note-based and character-based approaches. Adv. Eng. Techn. Res. 6(1), 107\u2013120 (2023).","journal-title":"Adv. Eng. Techn. Res."},{"key":"60482_CR22","unstructured":"Townsend, Benjamin, Madison May, and Christopher Wells. \u201cRealKIE: Five Novel Datasets for Enterprise Key Information Extraction.\u201d arXiv preprint arXiv:2403.20101 (2024)."},{"key":"60482_CR23","doi-asserted-by":"crossref","unstructured":"Aziz, Abdul, Md. Akram Hossain, and Abu Nowshed Chy. \u201cCSECU-DSG at SemEval-2023 Task 4: Fine-tuning DeBERTa Transformer Model with Cross-fold Training and Multi-sample Dropout for Human Values Identification.\u201d In The 17th Int. Workshop Semant. Eval. (SemEval-2023), 1988\u20131994. July 13\u201314, 2023.","DOI":"10.18653\/v1\/2023.semeval-1.274"},{"key":"60482_CR24","doi-asserted-by":"publisher","first-page":"7399","DOI":"10.1007\/s12652-022-04447-y","volume":"14","author":"D Tom\u00e1s","year":"2023","unstructured":"Tom\u00e1s, D., Ortega-Bueno, R., Zhang, G., Rosso, P. & Schifanella, R. Transformer-based models for multimodal irony detection. J. Ambient Intell. Humaniz. Comput. 14, 7399\u20137410 (2023).","journal-title":"J. Ambient Intell. Humaniz. Comput."},{"key":"60482_CR25","unstructured":"Li, J., et al. \"UDOP: Unified Vision-Language Pre-training for Document Understanding.\"\u00a0arXiv preprint\u00a0arXiv:2212.02623\u00a0(2022)."},{"key":"60482_CR26","unstructured":"Kim, G., et al. \"Donut: Document Understanding Transformer without OCR.\"\u00a0Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition\u00a0(2022)."},{"key":"60482_CR27","unstructured":"Sensen Gao, Shanshan Zhao, Xu Jiang, Lunhao Duan, Yong Xien Chng, Qing-Guo Chen, Weihua Luo, Kaifu Zhang, Jia-Wang Bian, Mingming Gong. Scaling Beyond Context: A Survey of Multimodal Retrieval-Augmented Generation for Document Understanding. arXiv preprint, 2025. https:\/\/arxiv.org\/abs\/2510.15253"},{"key":"60482_CR28","unstructured":"Dong Nguyen Tien, Dung D. Le. Robustness Evaluation of OCR-based Visual Document Understanding under Multi-Modal Adversarial Attacks. arXiv preprint, 2025. https:\/\/arxiv.org\/abs\/2506.16407"},{"key":"60482_CR29","unstructured":"Jiarui Zhang, Yuliang Liu, Zijun Wu, Guosheng Pang, Zhili Ye, Yupei Zhong, et al. MonkeyOCR v1.5 Technical Report: Unlocking Robust Document Parsing for Complex Patterns. arXiv preprint, 2025. https:\/\/arxiv.org\/abs\/2511.10390"},{"key":"60482_CR30","unstructured":"Zilong Wang, Xiaoyu Shen. Hybrid OCR-LLM Framework for Enterprise-Scale Document Information Extraction Under Copy-heavy Task. arXiv preprint, 2025. https:\/\/arxiv.org\/abs\/2510.10138"},{"key":"60482_CR31","unstructured":"Proceedings of the 19th International Conference on Document Analysis and Recognition (ICDAR 2025). https:\/\/www.icdar2025.com\/program\/list-of-workshops"},{"key":"60482_CR32","unstructured":"Niu J, Liu Z, Gu Z, Wang B, Ouyang L, Zhao Z, et al. MinerU2.5: A Decoupled Vision-Language Model for Efficient High-Resolution Document Parsing. arXiv preprint arXiv:2509.22186, 2025. Available: https:\/\/arxiv.org\/abs\/2509.22186."},{"key":"60482_CR33","unstructured":"Cui C, Sun T, Liang S, Gao T, Zhang Z, Liu J, et al. PaddleOCR-VL: Boosting Multilingual Document Parsing via a 0.9B Ultra-Compact Vision-Language Model. arXiv preprint arXiv:2510.14528, 2025. Available: https:\/\/arxiv.org\/abs\/2510.14528."},{"key":"60482_CR34","unstructured":"Bai S, Chen K, Liu X, Wang J, Ge W, Song S, et al. Qwen2.5-VL Technical Report. arXiv preprint arXiv:2502.13923, 2025. Available: https:\/\/arxiv.org\/abs\/2502.13923."}],"container-title":["Scientific Reports"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60482-1","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60482-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60482-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,31]],"date-time":"2026-08-31T13:51:17Z","timestamp":1788184277000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41598-026-60482-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,7,24]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2026,12]]}},"alternative-id":["60482"],"URL":"https:\/\/doi.org\/10.1038\/s41598-026-60482-1","relation":{"has-preprint":[{"id-type":"doi","id":"10.21203\/rs.3.rs-7596494\/v1","asserted-by":"object"}]},"ISSN":["2045-2322"],"issn-type":[{"value":"2045-2322","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,7,24]]},"assertion":[{"value":"12 September 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 June 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 July 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"On behalf of all authors, the corresponding author states that there are no competing financial or non-financial interests related to this work. The authors declare that they have no known financial or personal relationships that could inappropriately influence the work reported in this study. The authors declare no competing interests.","order":1,"name":"Ethics","label":"Competing interests","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"This study follows the ethical guidelines for industrial data research in the context of smart agriculture and does not involve human or animal subjects. Since this research only uses anonymous cigarette package label images and related metadata provided by Xiamen Haisheng Rongchuang Information Technology Co., Ltd., formal approval from an Institutional Review Board (IRB) was not required. All data was processed under strict confidentiality agreements to ensure compliance with the company\u2019s data protection policies and industry regulations.","order":2,"name":"Ethics","label":"Institutional Review Board Statement","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"27244"}}