{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:43:16Z","timestamp":1775068996902,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":30,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,8,25]],"date-time":"2023-08-25T00:00:00Z","timestamp":1692921600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"BKM","award":["2522DIG002"],"award-info":[{"award-number":["2522DIG002"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,8,25]]},"DOI":"10.1145\/3604951.3605513","type":"proceedings-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T17:20:33Z","timestamp":1690910433000},"page":"73-78","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":4,"title":["Document Layout Analysis with Deep Learning and Heuristics"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-8041-6506","authenticated-orcid":false,"given":"Vahid","family":"Rezanezhad","sequence":"first","affiliation":[{"name":"Berlin State Library, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2397-242X","authenticated-orcid":false,"given":"Konstantin","family":"Baierer","sequence":"additional","affiliation":[{"name":"Berlin State Library, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2167-4322","authenticated-orcid":false,"given":"Mike","family":"Gerber","sequence":"additional","affiliation":[{"name":"Berlin State Library, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7275-5483","authenticated-orcid":false,"given":"Kai","family":"Labusch","sequence":"additional","affiliation":[{"name":"Berlin State Library, Germany"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5293-8322","authenticated-orcid":false,"given":"Clemens","family":"Neudecker","sequence":"additional","affiliation":[{"name":"Berlin State Library, Germany"}]}],"member":"320","published-online":{"date-parts":[[2023,8,25]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2009.271"},{"key":"e_1_3_2_1_2_1","unstructured":"Alessandra\u00a0Bel\u00e9zia Ara\u00fajo. 2019. An\u00e1lise de layout de p\u00e1gina em jornais hist\u00f3ricos germano-brasileiros.  Alessandra\u00a0Bel\u00e9zia Ara\u00fajo. 2019. An\u00e1lise de layout de p\u00e1gina em jornais hist\u00f3ricos germano-brasileiros."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3322905.3322916"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.125"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333898"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.282"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_1_8_1","volume-title":"Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805","author":"Devlin Jacob","year":"2018","unstructured":"Jacob Devlin , Ming-Wei Chang , Kenton Lee , and Kristina Toutanova . 2018 . Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018). Jacob Devlin, Ming-Wei Chang, Kenton Lee, and Kristina Toutanova. 2018. Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)."},{"key":"e_1_3_2_1_9_1","volume-title":"LAMBERT: Layout-Aware Language Modeling for Information Extraction. In International Conference on Document Analysis and Recognition","author":"Garncarek \u0141ukasz","year":"2021","unstructured":"\u0141ukasz Garncarek , Rafa\u0142 Powalski , Tomasz Stanis\u0142awek , Bartosz Topolski , Piotr Halama , Micha\u0142 Turski , and Filip Grali\u0144ski . 2021 . LAMBERT: Layout-Aware Language Modeling for Information Extraction. In International Conference on Document Analysis and Recognition . Springer, New York, 532\u2013547. \u0141ukasz Garncarek, Rafa\u0142 Powalski, Tomasz Stanis\u0142awek, Bartosz Topolski, Piotr Halama, Micha\u0142 Turski, and Filip Grali\u0144ski. 2021. LAMBERT: Layout-Aware Language Modeling for Information Extraction. In International Conference on Document Analysis and Recognition. Springer, New York, 532\u2013547."},{"key":"e_1_3_2_1_10_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arxiv:1512.03385\u00a0[cs.CV]  Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arxiv:1512.03385\u00a0[cs.CV]"},{"key":"e_1_3_2_1_11_1","volume-title":"Combining visual and textual features for semantic segmentation of historical newspapers. Journal of Data Mining & Digital Humanities","author":"Kaplan Fr\u00e9d\u00e9ric","year":"2021","unstructured":"Fr\u00e9d\u00e9ric Kaplan , Sofia\u00a0Ares Oliveira , Simon Clematide , Maud Ehrmann , and Rapha\u00ebl Barman . 2021. Combining visual and textual features for semantic segmentation of historical newspapers. Journal of Data Mining & Digital Humanities ( 2021 ). Fr\u00e9d\u00e9ric Kaplan, Sofia\u00a0Ares Oliveira, Simon Clematide, Maud Ehrmann, and Rapha\u00ebl Barman. 2021. Combining visual and textual features for semantic segmentation of historical newspapers. Journal of Data Mining & Digital Humanities (2021)."},{"key":"e_1_3_2_1_12_1","volume-title":"Kingma and Jimmy Ba","author":"P.","year":"2017","unstructured":"Diederik\u00a0 P. Kingma and Jimmy Ba . 2017 . Adam : A Method for Stochastic Optimization . arxiv:1412.6980\u00a0[cs.LG] Diederik\u00a0P. Kingma and Jimmy Ba. 2017. Adam: A Method for Stochastic Optimization. arxiv:1412.6980\u00a0[cs.LG]"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2104.13037"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2102.11838"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2103.05489"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58595-2_6"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"e_1_3_2_1_18_1","volume-title":"Machine learning in document analysis and recognition","author":"Malerba Donato","unstructured":"Donato Malerba , Michelangelo Ceci , and Margherita Berardi . 2008. Machine learning for reading order detection in document image understanding . In Machine learning in document analysis and recognition . Springer , New York , 45\u201369. Donato Malerba, Michelangelo Ceci, and Margherita Berardi. 2008. Machine learning for reading order detection in document image understanding. In Machine learning in document analysis and recognition. Springer, New York, 45\u201369."},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3322905.3322917"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICFHR-2018.2018.00011"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/2501115.2501130"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.72"},{"key":"e_1_3_2_1_23_1","volume-title":"Munich","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger , Philipp Fischer , and Thomas Brox . 2015 . U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference , Munich , Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, New York, 234\u2013241. Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In Medical Image Computing and Computer-Assisted Intervention\u2013MICCAI 2015: 18th International Conference, Munich, Germany, October 5-9, 2015, Proceedings, Part III 18. Springer, New York, 234\u2013241."},{"key":"e_1_3_2_1_24_1","volume-title":"Jacob Carlson, and Weining Li.","author":"Shen Zejiang","year":"2021","unstructured":"Zejiang Shen , Ruochen Zhang , Melissa Dell , Benjamin Charles\u00a0Germain Lee , Jacob Carlson, and Weining Li. 2021 . Layoutparser : A unified toolkit for deep learning based document image analysis. In Document Analysis and Recognition\u2013ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part I 16. Springer , New York, 131\u2013146. Zejiang Shen, Ruochen Zhang, Melissa Dell, Benjamin Charles\u00a0Germain Lee, Jacob Carlson, and Weining Li. 2021. Layoutparser: A unified toolkit for deep learning based document image analysis. In Document Analysis and Recognition\u2013ICDAR 2021: 16th International Conference, Lausanne, Switzerland, September 5\u201310, 2021, Proceedings, Part I 16. Springer, New York, 131\u2013146."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.5555\/1304596.1304846"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-67558-9_28"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"crossref","unstructured":"Chris Tensmeyer Brian Davis Curtis Wigington Iain Lee and Bill Barrett. 2017. PageNet: Page Boundary Extraction in Historical Handwritten Documents. arxiv:1709.01618\u00a0[cs.CV]  Chris Tensmeyer Brian Davis Curtis Wigington Iain Lee and Bill Barrett. 2017. PageNet: Page Boundary Extraction in Historical Handwritten Documents. arxiv:1709.01618\u00a0[cs.CV]","DOI":"10.1145\/3151509.3151522"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2108.11591"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/DAS.2018.39"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"}],"event":{"name":"HIP '23: 7th International Workshop on Historical Document Imaging and Processing","location":"San Jose CA USA","acronym":"HIP '23"},"container-title":["Proceedings of the 7th International Workshop on Historical Document Imaging and Processing"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604951.3605513","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3604951.3605513","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:46:37Z","timestamp":1750178797000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3604951.3605513"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,25]]},"references-count":30,"alternative-id":["10.1145\/3604951.3605513","10.1145\/3604951"],"URL":"https:\/\/doi.org\/10.1145\/3604951.3605513","relation":{},"subject":[],"published":{"date-parts":[[2023,8,25]]},"assertion":[{"value":"2023-08-25","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}