{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:43:42Z","timestamp":1775069022355,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":23,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,4,30]],"date-time":"2023-04-30T00:00:00Z","timestamp":1682812800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc\/4.0\/"}],"funder":[{"DOI":"10.13039\/100000208","name":"Institute of Museum and Library Services","doi-asserted-by":"publisher","award":["LG-37-19-0078-19"],"award-info":[{"award-number":["LG-37-19-0078-19"]}],"id":[{"id":"10.13039\/100000208","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,4,30]]},"DOI":"10.1145\/3543873.3587609","type":"proceedings-article","created":{"date-parts":[[2023,4,28]],"date-time":"2023-04-28T11:36:14Z","timestamp":1682681774000},"page":"834-842","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["A New Annotation Method and Dataset for Layout Analysis of Long Documents"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-8491-0193","authenticated-orcid":false,"given":"Aman","family":"Ahuja","sequence":"first","affiliation":[{"name":"Department of Computer Science, Virginia Tech, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0307-5532","authenticated-orcid":false,"given":"Kevin","family":"Dinh","sequence":"additional","affiliation":[{"name":"Virginia Tech, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3552-2067","authenticated-orcid":false,"given":"Brian","family":"Dinh","sequence":"additional","affiliation":[{"name":"Virginia Tech, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8307-8844","authenticated-orcid":false,"given":"William A.","family":"Ingram","sequence":"additional","affiliation":[{"name":"Virginia Tech, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1447-6870","authenticated-orcid":false,"given":"Edward","family":"Fox","sequence":"additional","affiliation":[{"name":"Virginia Tech, USA"}]}],"member":"320","published-online":{"date-parts":[[2023,4,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.wiesp-1.14"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.1992.201771"},{"key":"e_1_3_2_1_3_1","unstructured":"Kevin Dinh Brian Dinh Andrew Leavitt and Annie Tran. 2022. Object Detection. http:\/\/hdl.handle.net\/10919\/114082 Virginia Tech CS4624 team term project."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/JCDL52503.2021.00030"},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020","author":"Li Minghao","year":"2020","unstructured":"Minghao Li, Lei Cui, Shaohan Huang, Furu Wei, Ming Zhou, and Zhoujun Li. 2020. TableBank: Table Benchmark for Image-based Table Detection and Recognition. In Proceedings of The 12th Language Resources and Evaluation Conference, LREC 2020, Marseille, France, May 11-16, 2020. European Language Resources Association, 1918\u20131925. https:\/\/aclanthology.org\/2020.lrec-1.236\/"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.82"},{"key":"e_1_3_2_1_11_1","unstructured":"Patrice Lopez and et al.2008\u20132022. GROBID. https:\/\/github.com\/kermitt2\/grobid."},{"key":"e_1_3_2_1_12_1","volume-title":"CORD: A Consolidated Receipt Dataset for Post-OCR Parsing. In Workshop on Document Intelligence at NeurIPS","author":"Park Seunghyun","year":"2019","unstructured":"Seunghyun Park, Seung Shin, Bado Lee, Junyeop Lee, Jaeheung Surh, Minjoon Seo, and Hwalsuk Lee. 2019. CORD: A Consolidated Receipt Dataset for Post-OCR Parsing. In Workshop on Document Intelligence at NeurIPS 2019. https:\/\/openreview.net\/forum?id=SJl3z659UH"},{"key":"e_1_3_2_1_13_1","volume-title":"Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015","author":"Ren Shaoqing","year":"2015","unstructured":"Shaoqing Ren, Kaiming He, Ross\u00a0B. Girshick, and Jian Sun. 2015. Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks. In Advances in Neural Information Processing Systems 28: Annual Conference on Neural Information Processing Systems 2015, December 7-12, 2015, Montreal, Quebec, Canada. 91\u201399. https:\/\/proceedings.neurips.cc\/paper\/2015\/hash\/14bfa6bb14875e45bba028a21ed38046-Abstract.html"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_9"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/BigData52589.2021.9672058"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2207.02696"},{"key":"e_1_3_2_1_18_1","unstructured":"Papers with Code. 2022. Real-Time Object Detection on COCO. https:\/\/paperswithcode.com\/sota\/real-time-object-detection-on-coco"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2210.16391"},{"key":"e_1_3_2_1_23_1","unstructured":"Kecheng Zhu Zachary Gager Shelby Neal Jiangyue Li and You Peng. 2022. Object Detection. http:\/\/hdl.handle.net\/10919\/109979 Virginia Tech CS4624 team term project."}],"event":{"name":"WWW '23: The ACM Web Conference 2023","location":"Austin TX USA","acronym":"WWW '23","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2023"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587609","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3543873.3587609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T23:48:38Z","timestamp":1755820118000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3543873.3587609"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,4,30]]},"references-count":23,"alternative-id":["10.1145\/3543873.3587609","10.1145\/3543873"],"URL":"https:\/\/doi.org\/10.1145\/3543873.3587609","relation":{},"subject":[],"published":{"date-parts":[[2023,4,30]]},"assertion":[{"value":"2023-04-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}