{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T07:50:29Z","timestamp":1781941829834,"version":"3.54.5"},"reference-count":30,"publisher":"Springer Science and Business Media LLC","issue":"2","license":[{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T00:00:00Z","timestamp":1758499200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["IJDAR"],"published-print":{"date-parts":[[2026,6]]},"DOI":"10.1007\/s10032-025-00556-4","type":"journal-article","created":{"date-parts":[[2025,9,22]],"date-time":"2025-09-22T08:00:25Z","timestamp":1758528025000},"page":"365-380","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Devanagari character encoded mix-merge vision transformer for robust document layout analysis"],"prefix":"10.1007","volume":"29","author":[{"given":"Shweta","family":"Singh","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sudeep","family":"Varshney","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ankur","family":"Choudhary","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,9,22]]},"reference":[{"key":"556_CR1","doi-asserted-by":"crossref","unstructured":"Vidyarthi, A., Mittal, N., Kansal, A.: Text and non-text region identification using texture and connected components. In: 2014 International Conference on Signal Propagation and Computer Technology (ICSPCT 2014), pp. 604\u2013609. (2014)","DOI":"10.1109\/ICSPCT.2014.6884904"},{"key":"556_CR2","doi-asserted-by":"crossref","unstructured":"Namboodiri, A.M., Jain, A.K.: Document structure and layout analysis. In: Digital Document Processing: Major Directions and Recent Advances, pp. 29\u201348. Springer, (2007)","DOI":"10.1007\/978-1-84628-726-8_2"},{"key":"556_CR3","doi-asserted-by":"crossref","unstructured":"Javed, M., Nagabhushan, P., Chaudhuri, B.B.: Automatic extraction of correlation-entropy features for text document analysis directly in run-length compressed domain. In: 2015 13th International Conference on Document Analysis and Recognition (ICDAR), pp. 1\u20135. IEEE, (2015)","DOI":"10.1109\/ICDAR.2015.7333714"},{"issue":"6","key":"556_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3355610","volume":"52","author":"GM Binmakhashen","year":"2019","unstructured":"Binmakhashen, G.M., Mahmoud, S.A.: Document layout analysis: a comprehensive survey. ACM Comput. Surveys (CSUR) 52(6), 1\u201336 (2019)","journal-title":"ACM Comput. Surveys (CSUR)"},{"key":"556_CR5","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s12530-020-09343-4","volume":"12","author":"L Lenc","year":"2021","unstructured":"Lenc, L., Mart\u00b4\u0131nek, Ji.\u02c7r\u00b4\u0131, Kr\u00b4al, P., Nicolao, A., Christlein, V.: Hdpa: historical document processing and analysis framework. Evol. Syst. 12, 177\u2013190 (2021)","journal-title":"Evol. Syst."},{"key":"556_CR6","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2023.116986","volume":"116","author":"P Mishra","year":"2023","unstructured":"Mishra, P.: Domain adaptive learning for document layout analysis and object detection using classifier alignment mechanism. Signal Process. Image Commun. 116, 116986 (2023)","journal-title":"Signal Process. Image Commun."},{"issue":"6","key":"556_CR7","doi-asserted-by":"publisher","DOI":"10.1007\/s12046-019-1126-9","volume":"44","author":"S Narang","year":"2019","unstructured":"Narang, S., Jindal, M.K., Kumar, M.: Devanagari ancient documents recognition using statistical feature extraction techniques. S\u0101dhan\u0101 44(6), 141 (2019)","journal-title":"S\u0101dhan\u0101"},{"key":"556_CR8","doi-asserted-by":"crossref","unstructured":"Gorai, M., Nene, M.J.: Layout and text extraction from document images using neural networks. In: 2020 5th International Conference on Communication and Electronics Systems (ICCES), pp 1107\u20131112. IEEE, (2020)","DOI":"10.1109\/ICCES48766.2020.9137859"},{"issue":"1","key":"556_CR9","first-page":"47","volume":"9","author":"A Fateh","year":"2022","unstructured":"Fateh, A., Rezvani, M., Tajary, A., Fateh, M.: Providing a voting-based method for combining deep neural network outputs to layout analysis of printed documents. J. Mach. Vis. Image Process. 9(1), 47\u201364 (2022)","journal-title":"J. Mach. Vis. Image Process."},{"issue":"3","key":"556_CR10","doi-asserted-by":"publisher","first-page":"65","DOI":"10.3390\/jimaging10030065","volume":"10","author":"FC Fizaine","year":"2024","unstructured":"Fizaine, F.C., Bard, P., Paindavoine, M., Robin, C., Bouye, E., Lefevre, R., Vinter, A.: Historical text line segmentation using deep learning algorithms: Mask-rcnn against u-net networks. J. Imag. 10(3), 65 (2024)","journal-title":"J. Imag."},{"key":"556_CR11","unstructured":"Datta, S., Mollah, M.A., Fairooz, R., Fahim, T.I.: Performance enhancement leveraging mask-rcnn on bengali document layout analysis. arXiv preprint arXiv:2308.10511, (2023)"},{"key":"556_CR12","doi-asserted-by":"crossref","unstructured":"Aljiffry, L., Al-Barhamtoshy, H., Jamal, A., Abukhodair, F.: Arabic documents layout analysis (adla) using fine-tuned faster rcn. In: 2022 20th International Conference on Language Engineering (ESOLEC), vol. 20, pp. 66\u201371. IEEE, (2022)","DOI":"10.1109\/ESOLEC54569.2022.10009375"},{"key":"556_CR13","doi-asserted-by":"crossref","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: Proceedings of the 26th ACM SIGKDD international conference on knowledge discovery & data mining, pp 1192\u20131200, (2020)","DOI":"10.1145\/3394486.3403172"},{"key":"556_CR14","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":"556_CR15","doi-asserted-by":"crossref","unstructured":"Zhu, W., Sokhandan, N., Yang, G., Martin, S., Sathyanarayana, S.: Docbed: a multi-stage ocr solution for documents with complex layouts. In Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 12643\u201312649, (2022)","DOI":"10.1609\/aaai.v36i11.21539"},{"key":"556_CR16","doi-asserted-by":"crossref","unstructured":"Huang, Y., Lv, T., Cui, L., Lu, Y., Wei, F.: Layoutlmv3: Pre-training for document AI with unified text and image masking. In: Proceedings of the 30th ACM International Conference on Multimedia, pp 4083\u20134091, (2022)","DOI":"10.1145\/3503161.3548112"},{"key":"556_CR17","doi-asserted-by":"crossref","unstructured":"Li, J., Xu, Y., Lv, T., Cui, L., Zhang, C., Wei, F.: Dit: self-supervised pre-training for document image transformer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 3530\u20133539, (2022)","DOI":"10.1145\/3503161.3547911"},{"issue":"3","key":"556_CR18","doi-asserted-by":"publisher","first-page":"269","DOI":"10.1007\/s10032-021-00380-6","volume":"24","author":"S Biswas","year":"2021","unstructured":"Biswas, S., Riba, P., Llad\u00b4os, J., Pal, U.: Beyond document object detection: instance-level segmentation of complex layouts. Int. J. Doc. Anal. Recognit. (IJDAR) 24(3), 269\u2013281 (2021)","journal-title":"Int. J. Doc. Anal. Recognit. (IJDAR)"},{"key":"556_CR19","unstructured":"Suh, S., Kim, J., Lukowicz, P., Lee, Y.O.: Two-stage generative adversarial networks for document image binarization with color noise and background removal. arXiv preprint arXiv:2010.10103, (2020)"},{"key":"556_CR20","unstructured":"Kastanas, S., Tan, S., He, Y.: Document AI: a comparative study of transformer-based, graph-based models, and convolutional neural networks for document layout analysis. arXiv preprint arXiv:2308.15517, (2023)"},{"key":"556_CR21","doi-asserted-by":"crossref","unstructured":"Da, C., Luo, C., Zheng, Q., Yao, C.: Vision grid transformer for document layout analysis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp 19462\u201319472, (2023)","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"556_CR22","doi-asserted-by":"crossref","unstructured":"Shehzadi, T., Stricker, D., Afzal, M.Z.: A hybrid approach for document layout analysis in document images. In: International Conference on Document Analysis and Recognition, pp. 21\u201339. Springer, (2024)","DOI":"10.1007\/978-3-031-70546-5_2"},{"issue":"2","key":"556_CR23","doi-asserted-by":"publisher","first-page":"276","DOI":"10.1080\/02564602.2020.1843553","volume":"39","author":"VK Sharma","year":"2022","unstructured":"Sharma, V.K., Mittal, N., Vidyarthi, A.: Context-based translation for the out of vocabulary words applied to Hindi-English cross-lingual information retrieval. IETE Tech. Rev. 39(2), 276\u2013285 (2022)","journal-title":"IETE Tech. Rev."},{"issue":"6","key":"556_CR24","doi-asserted-by":"publisher","first-page":"8197","DOI":"10.1007\/s11042-021-11074-w","volume":"82","author":"VK Sharma","year":"2023","unstructured":"Sharma, V.K., Mittal, N., Vidyarthi, A.: Semantic morphological variant selection and translation disambiguation for cross- lingual information retrieval. Multimed. Tools Appl. 82(6), 8197\u20138212 (2023)","journal-title":"Multimed. Tools Appl."},{"issue":"1","key":"556_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3569010","volume":"23","author":"V Sharma","year":"2024","unstructured":"Sharma, V., Mittal, N., Vidyarthi, A., Gupta, D.: Exploring web-based translation resources applied to Hindi-English cross- lingual information retrieval. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 23(1), 1\u201319 (2024)","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"key":"556_CR26","doi-asserted-by":"crossref","unstructured":"Kaur, R.P., Kumar, M., Jindal, M.K.: Segmentation of unstructured scanned Devanagari newspaper documents. In: International Conference on Computer Vision and Image Processing, pages 107\u2013117. Springer, (2021)","DOI":"10.1007\/978-3-031-11346-8_10"},{"issue":"1","key":"556_CR27","doi-asserted-by":"publisher","first-page":"50","DOI":"10.51983\/ajeat-2019.8.1.1060","volume":"8","author":"AK Bathla","year":"2019","unstructured":"Bathla, A.K., Gupta, S.K., Jindal, M.K.: Character segmentation and skew correction for handwritten Devanagari scripts: a friends technique. Asian J. Eng. Appl. Technol. 8(1), 50\u201354 (2019)","journal-title":"Asian J. Eng. Appl. Technol."},{"issue":"08","key":"556_CR28","doi-asserted-by":"publisher","first-page":"41","DOI":"10.47392\/irjash.2020.91","volume":"2","author":"M Kohli","year":"2020","unstructured":"Kohli, M., Kumar, S.: Comparative analysis of segmentation and recognition techniques for offline handwritten words. Int. Res. J. Adv. Sci. Hub 2(08), 41\u201348 (2020)","journal-title":"Int. Res. J. Adv. Sci. Hub"},{"key":"556_CR29","doi-asserted-by":"publisher","first-page":"49530","DOI":"10.1109\/ACCESS.2023.3277392","volume":"11","author":"D Rajpal","year":"2023","unstructured":"Rajpal, D., Garg, A.R.: Deep learning model for recognition of handwritten devanagari numerals with low computational complexity and space requirements. IEEE Access 11, 49530\u201349539 (2023)","journal-title":"IEEE Access"},{"issue":"1","key":"556_CR30","doi-asserted-by":"publisher","first-page":"0055","DOI":"10.5565\/rev\/elcvia.1344","volume":"20","author":"SS Shiravale","year":"2021","unstructured":"Shiravale, S.S., Jayadevan, R., Sannakki, S.S.: Recognition of devanagari scene text using autoencoder cnn. ELCVIA: Electron. Lett. Comput. Vis. Image Anal. 20(1), 0055\u20130069 (2021)","journal-title":"ELCVIA: Electron. Lett. Comput. Vis. Image Anal."}],"container-title":["International Journal on Document Analysis and Recognition (IJDAR)"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00556-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10032-025-00556-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10032-025-00556-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,20]],"date-time":"2026-06-20T07:08:13Z","timestamp":1781939293000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10032-025-00556-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,22]]},"references-count":30,"journal-issue":{"issue":"2","published-print":{"date-parts":[[2026,6]]}},"alternative-id":["556"],"URL":"https:\/\/doi.org\/10.1007\/s10032-025-00556-4","relation":{},"ISSN":["1433-2833","1433-2825"],"issn-type":[{"value":"1433-2833","type":"print"},{"value":"1433-2825","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,22]]},"assertion":[{"value":"3 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 September 2025","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors of this manuscript declare that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"The author of this manuscript confirms that: (i) Informed, written consent has been obtained from the relevant sources wherever is required; (ii) All procedures followed were in accordance with the ethical standards of the responsible committee on human experimentation (institutional and national) and with the Helsinki Declaration of 1964 and its later amendments. (iii) Approval and\/or informed consent were not required for the study as the dataset is collected from the Kaggle website, a well-known data repository for worldwide data analytics problems and live challenges.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethics approval"}}]}}