{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T05:28:06Z","timestamp":1781587686367,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":34,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,12,16]],"date-time":"2024-12-16T00:00:00Z","timestamp":1734307200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Young Scientists Fund of the National Natural Science Foundation of China","award":["72304215"],"award-info":[{"award-number":["72304215"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,12,16]]},"DOI":"10.1145\/3677389.3702534","type":"proceedings-article","created":{"date-parts":[[2025,3,13]],"date-time":"2025-03-13T12:53:52Z","timestamp":1741870432000},"page":"1-11","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Fine-Grained, Accurate Data Generation and Multimodal Layout Analysis for Academic Papers"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2180-4184","authenticated-orcid":false,"given":"Dehao","family":"Ying","sequence":"first","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6503-4688","authenticated-orcid":false,"given":"Fengchang","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan University, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7088-9752","authenticated-orcid":false,"given":"Haihua","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Information Science, University of North Texas, Denton, Texas, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0929-7416","authenticated-orcid":false,"given":"Wei","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Information Management, Wuhan university, Wuhan, Hubei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,3,13]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.271"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"e_1_3_2_2_3_1","volume-title":"Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Li Dong, Songhao Piao, and Furu Wei. 2021. Beit: Bert pre-training of image transformers. arXiv preprint arXiv:2106.08254 (2021)."},{"key":"e_1_3_2_2_4_1","volume-title":"SciBERT: A pretrained language model for scientific text. arXiv preprint arXiv:1903.10676","author":"Beltagy Iz","year":"2019","unstructured":"Iz Beltagy, Kyle Lo, and Arman Cohan. 2019. SciBERT: A pretrained language model for scientific text. arXiv preprint arXiv:1903.10676 (2019)."},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"e_1_3_2_2_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01783"},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_8_1","volume-title":"International Conference on Machine Learning. PMLR, 980--989","author":"Deng Yuntian","year":"2017","unstructured":"Yuntian Deng, Anssi Kanervisto, Jeffrey Ling, and Alexander M Rush. 2017. Image-to-markup generation with coarse-to-fine attention. In International Conference on Machine Learning. PMLR, 980--989."},{"key":"e_1_3_2_2_9_1","unstructured":"Alexey Dosovitskiy Lucas Beyer Alexander Kolesnikov Dirk Weissenborn Xiaohua Zhai Thomas Unterthiner Mostafa Dehghani Matthias Minderer Georg Heigold Sylvain Gelly et al. 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00332-1"},{"key":"e_1_3_2_2_11_1","first-page":"39","article-title":"Unidoc: Unified pretraining framework for document understanding","volume":"34","author":"Gu Jiuxiang","year":"2021","unstructured":"Jiuxiang Gu, Jason Kuen, Vlad I Morariu, Handong Zhao, Rajiv Jain, Nikolaos Barmpalios, Ani Nenkova, and Tong Sun. 2021. Unidoc: Unified pretraining framework for document understanding. Advances in Neural Information Processing Systems 34 (2021), 39--50.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.50"},{"key":"e_1_3_2_2_14_1","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 16000--16009","author":"Chen Xinlei","year":"2022","unstructured":"KaimingHe, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 16000--16009."},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1_40"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547911"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings, Part V 13","author":"Lin Tsung-Yi","year":"2014","unstructured":"Tsung-Yi Lin, Michael Maire, Serge Belongie, James Hays, Pietro Perona, Deva Ramanan, Piotr Doll\u00e1r, and C Lawrence Zitnick. 2014. Microsoft coco: Common objects in context. In Computer Vision-ECCV 2014: 13th European Conference, Zurich, Switzerland, September 6--12, 2014, Proceedings, Part V 13. Springer, 740--755."},{"key":"e_1_3_2_2_22_1","volume-title":"Thuy Dung Nguyen, and Min-Yen Kan","author":"Luong Minh-Thang","year":"2012","unstructured":"Minh-Thang Luong, Thuy Dung Nguyen, and Min-Yen Kan. 2012. Logical structure recovery in scholarly articles with rich document features. In Multimedia Storage and Retrieval Innovations for Digital Library Systems. IGI Global, 270--292."},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.244677"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"e_1_3_2_2_25_1","volume-title":"Doclaynet: A large humanannotated dataset for document-layout analysis. URL: https:\/\/arxiv.org\/abs\/2206 1062","author":"Pfitzmann B","year":"2022","unstructured":"B Pfitzmann, C Auer, M Dolfi, AS Nassar, and PWJ Staar. 2022. Doclaynet: A large humanannotated dataset for document-layout analysis. URL: https:\/\/arxiv.org\/abs\/2206 1062 (2022)."},{"key":"e_1_3_2_2_26_1","volume-title":"Towards a multi-modal, multi-task learning based pre-training framework for document representation learning. arXiv preprint arXiv:2009.14457","author":"Pramanik Subhojeet","year":"2020","unstructured":"Subhojeet Pramanik, Shashank Mujumdar, and Hima Patel. 2020. Towards a multi-modal, multi-task learning based pre-training framework for document representation learning. arXiv preprint arXiv:2009.14457 (2020)."},{"key":"e_1_3_2_2_27_1","volume-title":"Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross Girshick, and Jian Sun. 2015. Faster r-cnn: Towards real-time object detection with region proposal networks. Advances in neural information processing systems 28 (2015)."},{"key":"e_1_3_2_2_28_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.39"},{"key":"e_1_3_2_2_30_1","volume-title":"Layoutxlm: Multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint arXiv:2104.08836","author":"Xu Yiheng","year":"2021","unstructured":"Yiheng Xu, Tengchao Lv, Lei Cui, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, and Furu Wei. 2021. Layoutxlm: Multimodal pre-training for multilingual visually-rich document understanding. arXiv preprint arXiv:2104.08836 (2021)."},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.462"},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_8"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"}],"event":{"name":"JCDL '24: 24th ACM\/IEEE Joint Conference on Digital Libraries","location":"Hong Kong China","acronym":"JCDL '24","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval","SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web","IEEE TCDL"]},"container-title":["Proceedings of the 24th ACM\/IEEE Joint Conference on Digital Libraries"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702534","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3677389.3702534","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,15]],"date-time":"2025-07-15T20:19:50Z","timestamp":1752610790000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3677389.3702534"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,16]]},"references-count":34,"alternative-id":["10.1145\/3677389.3702534","10.1145\/3677389"],"URL":"https:\/\/doi.org\/10.1145\/3677389.3702534","relation":{},"subject":[],"published":{"date-parts":[[2024,12,16]]},"assertion":[{"value":"2025-03-13","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}