{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T11:19:22Z","timestamp":1777634362208,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":27,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,7,18]],"date-time":"2023-07-18T00:00:00Z","timestamp":1689638400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,7,19]]},"DOI":"10.1145\/3539618.3591839","type":"proceedings-article","created":{"date-parts":[[2023,7,19]],"date-time":"2023-07-19T00:22:59Z","timestamp":1689726179000},"page":"3285-3289","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Context-Aware Classification of Legal Document Pages"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-0456-2743","authenticated-orcid":false,"given":"Pavlos","family":"Fragkogiannis","sequence":"first","affiliation":[{"name":"Thomson Reuters Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-5521-091X","authenticated-orcid":false,"given":"Martina","family":"Forster","sequence":"additional","affiliation":[{"name":"Thomson Reuters Labs, Zug, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7458-414X","authenticated-orcid":false,"given":"Grace E.","family":"Lee","sequence":"additional","affiliation":[{"name":"Thomson Reuters Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8774-3725","authenticated-orcid":false,"given":"Dell","family":"Zhang","sequence":"additional","affiliation":[{"name":"Thomson Reuters Labs, London, United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,7,18]]},"reference":[{"key":"e_1_3_2_2_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/EnT50460.2021.9681776"},{"key":"e_1_3_2_2_2_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2106.11539"},{"key":"e_1_3_2_2_3_1","doi-asserted-by":"crossref","unstructured":"Souhail Bakkali Zuheng Ming Mickael Coustaty and Marcal Rusinol. 2020. Visual and Textual Deep Feature Fusion for Document Image Classification. 562--563. https:\/\/openaccess.thecvf.com\/content_CVPRW_2020\/html\/w34\/Bakkali_Visual_and_Textual_Deep_Feature_Fusion_for_Document_Image_Classification_CVPRW_2020_paper.html","DOI":"10.1109\/CVPRW50498.2020.00289"},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"crossref","unstructured":"Ali Furkan Biten Rub\u00e8n Tito Lluis Gomez Ernest Valveny and Dimosthenis Karatzas. 2022. OCR-IDL: OCR Annotations for Industry Document Library Dataset. http:\/\/arxiv.org\/abs\/2202.12985 arXiv:2202.12985 [cs].","DOI":"10.1007\/978-3-031-25069-9_16"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.2307\/2280710"},{"key":"e_1_3_2_2_6_1","volume-title":"Sapunov","author":"Burtsev Mikhail S.","year":"2021","unstructured":"Mikhail S. Burtsev, Yuri Kuratov, Anton Peganov, and Grigory V. Sapunov. 2021. Memory Transformer. http:\/\/arxiv.org\/abs\/2006.11527 arXiv:2006.11527 [cs]."},{"key":"e_1_3_2_2_7_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-5821"},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1285"},{"key":"e_1_3_2_2_9_1","volume-title":"Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks. arXiv:1801.09321 [cs] (Aug","author":"Das Arindam","year":"2018","unstructured":"Arindam Das, Saikat Roy, Ujjwal Bhattacharya, and Swapan Kumar Parui. 2018. Document Image Classification with Intra-Domain Transfer Learning and Stacked Generalization of Deep Convolutional Neural Networks. arXiv:1801.09321 [cs] (Aug. 2018). http:\/\/arxiv.org\/abs\/1801.09321 arXiv: 1801.09321."},{"key":"e_1_3_2_2_10_1","volume-title":"Modular Multimodal Architecture for Document Classification. arXiv:1912.04376 [cs] (Dec","author":"Dauphinee Tyler","year":"2019","unstructured":"Tyler Dauphinee, Nikunj Patel, and Mohammad Rashidi. 2019. Modular Multimodal Architecture for Document Classification. arXiv:1912.04376 [cs] (Dec. 2019). http:\/\/arxiv.org\/abs\/1912.04376 arXiv: 1912.04376 version: 1."},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1502.07058"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","unstructured":"Yupan Huang Tengchao Lv Lei Cui Yutong Lu and Furu Wei. 2022. LayoutLMv3: Pre-training for Document AI with Unified Text and Image Masking. https:\/\/doi.org\/10.48550\/arXiv.2204.08387 arXiv:2204.08387 [cs].","DOI":"10.48550\/arXiv.2204.08387"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","unstructured":"Zhiheng Huang Wei Xu and Kai Yu. 2015. Bidirectional LS\u2122-CRF Models for Sequence Tagging. https:\/\/doi.org\/10.48550\/arXiv.1508.01991 arXiv:1508.01991 [cs].","DOI":"10.48550\/arXiv.1508.01991"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAC.1980.1102314"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2013.10.030"},{"key":"e_1_3_2_2_18_1","volume-title":"Proceedings of the Eighteenth International Conference on Machine Learning (ICML '01)","author":"Lafferty John D.","unstructured":"John D. Lafferty, Andrew McCallum, and Fernando C. N. Pereira. 2001. Conditional Random Fields: Probabilistic Models for Segmenting and Labeling Sequence Data. In Proceedings of the Eighteenth International Conference on Machine Learning (ICML '01). Morgan Kaufmann Publishers Inc., San Francisco, CA, USA, 282--289."},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","unstructured":"Ilya Loshchilov and Frank Hutter. 2019. Decoupled Weight Decay Regularization. https:\/\/doi.org\/10.48550\/arXiv.1711.05101 arXiv:1711.05101 [cs math].","DOI":"10.48550\/arXiv.1711.05101"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-022-00406-7"},{"key":"e_1_3_2_2_21_1","volume-title":"Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association","author":"Luz de Araujo Pedro Henrique","year":"2020","unstructured":"Pedro Henrique Luz de Araujo, Te\u00f3filo Em\u00eddio de Campos, Fabricio Ataides Braz, and Nilton Correia da Silva. 2020. VICTOR: a Dataset for Brazilian Legal Documents Classification. In Proceedings of the Twelfth Language Resources and Evaluation Conference. European Language Resources Association, Marseille, France, 1449--1458. https:\/\/aclanthology.org\/2020.lrec-1.181"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","unstructured":"Xuezhe Ma and Eduard Hovy. 2016. End-to-end Sequence Labeling via Bi-directional LS\u2122-CNNs-CRF. https:\/\/doi.org\/10.48550\/arXiv.1603.01354 arXiv:1603.01354 [cs stat].","DOI":"10.48550\/arXiv.1603.01354"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1007\/BF02295996"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","unstructured":"F\u00e1bio Souza Rodrigo Nogueira and Roberto Lotufo. 2020a. BERTimbau: Pretrained BERT Models for Brazilian Portuguese. 403--417. https:\/\/doi.org\/10.1007\/978-3-030-61377-8_28","DOI":"10.1007\/978-3-030-61377-8_28"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","unstructured":"F\u00e1bio Souza Rodrigo Nogueira and Roberto Lotufo. 2020b. Portuguese Named Entity Recognition using BERT-CRF. https:\/\/doi.org\/10.48550\/arXiv.1909.10649 arXiv:1909.10649 [cs].","DOI":"10.48550\/arXiv.1909.10649"},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1989.1.2.270"},{"key":"e_1_3_2_2_27_1","doi-asserted-by":"publisher","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. https:\/\/doi.org\/10.48550\/arXiv.2104.08836 arXiv:2104.08836 [cs].","DOI":"10.48550\/arXiv.2104.08836"}],"event":{"name":"SIGIR '23: The 46th International ACM SIGIR Conference on Research and Development in Information Retrieval","location":"Taipei Taiwan","acronym":"SIGIR '23","sponsor":["SIGIR ACM Special Interest Group on Information Retrieval"]},"container-title":["Proceedings of the 46th International ACM SIGIR Conference on Research and Development in Information Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591839","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3539618.3591839","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T16:37:59Z","timestamp":1750178279000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3539618.3591839"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,7,18]]},"references-count":27,"alternative-id":["10.1145\/3539618.3591839","10.1145\/3539618"],"URL":"https:\/\/doi.org\/10.1145\/3539618.3591839","relation":{},"subject":[],"published":{"date-parts":[[2023,7,18]]},"assertion":[{"value":"2023-07-18","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}