{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T09:48:31Z","timestamp":1774000111654,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":22,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,12]]},"DOI":"10.1145\/3788149.3788244","type":"proceedings-article","created":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:35:19Z","timestamp":1773988519000},"page":"445-450","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Domain-Specific Datasets with Abundant Layout Categories for Accident Investigation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-4882-0585","authenticated-orcid":false,"given":"Lingyu","family":"Pan","sequence":"first","affiliation":[{"name":"North China Institute of Science and Technolog, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8272-4422","authenticated-orcid":false,"given":"Zixiang","family":"Zhou","sequence":"additional","affiliation":[{"name":"North China Institute of Science and Technolog, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-1962-4588","authenticated-orcid":false,"given":"Yunlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"Hebei Internet of Things Monitoring Technology Innovation Center, North China Institute of Science and Technology, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-2861","authenticated-orcid":false,"given":"Wenxing","family":"Wu","sequence":"additional","affiliation":[{"name":"College of Computer Science, Qinghai Normal University, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-9217-8233","authenticated-orcid":false,"given":"Ziye","family":"Shi","sequence":"additional","affiliation":[{"name":"North China Institute of Science and Technolog, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-8646-7532","authenticated-orcid":false,"given":"Mingyu","family":"Qin","sequence":"additional","affiliation":[{"name":"North China Institute of Science and Technolog, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8109-4112","authenticated-orcid":false,"given":"Zeyu","family":"Fan","sequence":"additional","affiliation":[{"name":"North China Institute of Science and Technolog, Langfang, Hebei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2026,3,19]]},"reference":[{"key":"e_1_3_3_1_2_2","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3429"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"crossref","unstructured":"Hiromichi Fujisawa. 2008. Forty Years of Research in Character and Document Recognition\u2014an Industrial Perspective. Pattern recognition 41 8 (2008).","DOI":"10.1016\/j.patcog.2008.03.015"},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"crossref","unstructured":"Max G\u00f6bel Tamir Hassan Ermelinda Oro and Giorgio Orsi. 2013. ICDAR 2013 table competition. (2013) 1449\u20131453.","DOI":"10.1109\/ICDAR.2013.292"},{"key":"e_1_3_3_1_5_2","unstructured":"Mohsen\u00a0Asghari Ilani and Yaser\u00a0Mike Banad. 2025. LabelImg: CNN-Based Surface Defect Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.05813 (2025)."},{"key":"e_1_3_3_1_6_2","unstructured":"Wenjun Ke Yifan Zheng Yining Li Hengyuan Xu Dong Nie Peng Wang and Yao He. 2025. Large language models in document intelligence: A comprehensive survey recent advances challenges and future trends. ACM Transactions on Information Systems (2025)."},{"key":"e_1_3_3_1_7_2","unstructured":"Minghao Li Lei Cui Shaohan Huang Furu Wei Ming Zhou and Zhoujun Li. 2019. Tablebank: A benchmark dataset for table detection and recognition. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1903.01949 (2019)."},{"key":"e_1_3_3_1_8_2","unstructured":"Minghao Li Yiheng Xu Lei Cui Shaohan Huang Furu Wei Zhoujun Li and Ming Zhou. 2020. DocBank: A Benchmark Dataset for Document Layout Analysis. Computing Research Repository abs\/2006.01038 (2020)."},{"key":"e_1_3_3_1_9_2","unstructured":"Chenglong Liu Haoran Wei Jinyue Chen Lingyu Kong Zheng Ge Zining Zhu Liang Zhao Jianjian Sun Chunrui Han and Xiangyu Zhang. 2024. Focus anywhere for fine-grained multi-page document understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.14295 (2024)."},{"key":"e_1_3_3_1_10_2","unstructured":"Nikolaos Livathinos Christoph Auer Ahmed Nassar Rafael\u00a0Teixeira de Lima Maksym Lysak Brown Ebouky Cesar Berrospi Michele Dolfi Panagiotis Vagenas Matteo Omenetti et\u00a0al. 2025. Advanced Layout Analysis Models for Docling. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2509.11720 (2025)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00046"},{"key":"e_1_3_3_1_12_2","unstructured":"Tengchao Lv Yupan Huang Jingye Chen Yuzhong Zhao Yilin Jia Lei Cui Shuming Ma Yaoyao Chang Shaohan Huang Wenhui Wang et\u00a0al. 2023. Kosmos-2.5: A multimodal literate model. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2309.11419 (2023)."},{"key":"e_1_3_3_1_13_2","unstructured":"Xiaochun Mai Hong Zhang Xiao Jia and Max Q-H Meng. 2020. Faster R-CNN with classifier fusion for automatic detection of small fruits. IEEE Transactions on Automation Science and Engineering 17 3 (2020) 1555\u20131569."},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Nobuto Moriguchi Lisa Ito and Akihiro Tokai. 2024. Risk Assessment of Chemical Release Accident Triggered by Landslide Using Bayesian Network. Science of the Total Environment 916 (2024).","DOI":"10.1016\/j.scitotenv.2024.170426"},{"key":"e_1_3_3_1_15_2","doi-asserted-by":"crossref","unstructured":"Alejandro Pe\u00f1a Aythami Morales Julian Fierrez Javier Ortega-Garcia I\u00f1igo Puente Jorge Cordova and Gonzalo Cordova. 2024. Continuous document layout analysis: Human-in-the-loop AI-based data curation database and evaluation in the domain of public affairs. Information Fusion 108 (2024) 102398.","DOI":"10.1016\/j.inffus.2024.102398"},{"key":"e_1_3_3_1_16_2","doi-asserted-by":"publisher","DOI":"10.1145\/3534678.3539043"},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","unstructured":"Nahian Siddique Sidike Paheding Colin\u00a0P Elkin and Vijay Devabhaktuni. 2021. U-Net and Its Variants for Medical Image Segmentation: A Review of Theory and Applications. IEEE Access 9 (2021) 82031\u201382057.","DOI":"10.1109\/ACCESS.2021.3086020"},{"key":"e_1_3_3_1_18_2","unstructured":"Bin Wang Chao Xu Xiaomeng Zhao Linke Ouyang Fan Wu Zhiyuan Zhao Rui Xu Kaiwen Liu Yuan Qu Fukai Shang et\u00a0al. 2024. MinerU: An Open-Source Solution for Precise Document Content Extraction. arXiv e-prints (2024) arXiv\u20132409."},{"key":"e_1_3_3_1_19_2","unstructured":"Jiabo Ye Anwen Hu Haiyang Xu Qinghao Ye Ming Yan Yuhao Dan Chenlin Zhao Guohai Xu Chenliang Li Junfeng Tian et\u00a0al. 2023. mplug-docowl: Modularized multimodal large language model for document understanding. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2307.02499 (2023)."},{"key":"e_1_3_3_1_20_2","unstructured":"Qinghao Ye Haiyang Xu Guohai Xu Jiabo Ye Ming Yan Yiyang Zhou Junyang Wang Anwen Hu Pengcheng Shi Yaya Shi et\u00a0al. 2023. mplug-owl: Modularization empowers large language models with multimodality. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2304.14178 (2023)."},{"key":"e_1_3_3_1_21_2","unstructured":"Zhiyuan Zhao Hengrui Kang Bin Wang and Conghui He. 2024. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.12628 (2024)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"crossref","unstructured":"Xu Zhong Jianbin Tang and Antonio\u00a0Jimeno Yepes. 2019. Publaynet: largest dataset ever for document layout analysis. (2019) 1015\u20131022.","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"e_1_3_3_1_23_2","doi-asserted-by":"crossref","unstructured":"Silvia Zottin Axel\u00a0De Nardin Emanuela Colombi Claudio Piciarelli Filippo Pavan and Gian\u00a0Luca Foresti. 2024. U-DIADS-Bib: a Full and Few-Shot Pixel-Precise Dataset for Document Layout Analysis of Ancient Manuscripts. Neural Computing and Applications (2024) 1\u201313.","DOI":"10.1007\/s00521-023-09356-5"}],"event":{"name":"CSAI 2025: 2025 The 9th International Conference on Computer Science and Artificial Intelligence","location":"Beijing China","acronym":"CSAI 2025"},"container-title":["Proceedings of the 2025 9th International Conference on Computer Science and Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3788149.3788244","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T06:37:54Z","timestamp":1773988674000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3788149.3788244"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,12]]},"references-count":22,"alternative-id":["10.1145\/3788149.3788244","10.1145\/3788149"],"URL":"https:\/\/doi.org\/10.1145\/3788149.3788244","relation":{},"subject":[],"published":{"date-parts":[[2025,12,12]]},"assertion":[{"value":"2026-03-19","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}