{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,2]],"date-time":"2026-01-02T07:29:26Z","timestamp":1767338966045,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":28,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,12,6]],"date-time":"2023-12-06T00:00:00Z","timestamp":1701820800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100006374","name":"National Science Fund for Distinguished Young Scholars","doi-asserted-by":"publisher","award":["No.62225113"],"award-info":[{"award-number":["No.62225113"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100006374","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["No.2042023kf1033"],"award-info":[{"award-number":["No.2042023kf1033"]}],"id":[{"id":"10.13039\/501100006374","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,12,6]]},"DOI":"10.1145\/3611380.3628554","type":"proceedings-article","created":{"date-parts":[[2023,12,30]],"date-time":"2023-12-30T12:03:31Z","timestamp":1703937811000},"page":"1-10","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Enhancing Visually-Rich Document Understanding via Layout Structure Modeling"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-2531-6537","authenticated-orcid":false,"given":"Qiwei","family":"Li","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0436-8446","authenticated-orcid":false,"given":"Zuchao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0764-5085","authenticated-orcid":false,"given":"Xiantao","family":"Cai","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8104-3448","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7290-0487","authenticated-orcid":false,"given":"Hai","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,12,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413511"},{"key":"e_1_3_2_1_3_1","volume-title":"Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116","author":"Conneau Alexis","year":"2019","unstructured":"Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzm\u00e1n, Edouard Grave, Myle Ott, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Unsupervised cross-lingual representation learning at scale. arXiv preprint arXiv:1911.02116 (2019)."},{"key":"e_1_3_2_1_4_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)."},{"key":"e_1_3_2_1_5_1","unstructured":"M. Ding Z. Yang W. Hong W. Zheng C. Zhou D. Yin J. Lin X. Zou Z. Shao and H. Yang. 2021. CogView: Mastering Text-to-Image Generation via Transformers. (2021)."},{"key":"e_1_3_2_1_6_1","volume-title":"An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929","author":"Dosovitskiy Alexey","year":"2020","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, 2020. An image is worth 16x16 words: Transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"e_1_3_2_1_12_1","volume-title":"Chargrid: Towards understanding 2d documents. arXiv preprint arXiv:1809.08799","author":"Katti Anoop\u00a0Raveendra","year":"2018","unstructured":"Anoop\u00a0Raveendra Katti, Christian Reisswig, Cordula Guder, Sebastian Brarda, Steffen Bickel, Johannes H\u00f6hne, and Jean\u00a0Baptiste Faddoul. 2018. Chargrid: Towards understanding 2d documents. arXiv preprint arXiv:1809.08799 (2018)."},{"key":"e_1_3_2_1_13_1","volume-title":"Formnet: Structural encoding beyond sequential modeling in form document information extraction. arXiv preprint arXiv:2203.08411","author":"Lee Chen-Yu","year":"2022","unstructured":"Chen-Yu Lee, Chun-Liang Li, Timothy Dozat, Vincent Perot, Guolong Su, Nan Hua, Joshua Ainslie, Renshen Wang, Yasuhisa Fujii, and Tomas Pfister. 2022. Formnet: Structural encoding beyond sequential modeling in form document information extraction. arXiv preprint arXiv:2203.08411 (2022)."},{"key":"e_1_3_2_1_14_1","volume-title":"Rope: reading order equivariant positional encoding for graph-based document information extraction. arXiv preprint arXiv:2106.10786","author":"Lee Chen-Yu","year":"2021","unstructured":"Chen-Yu Lee, Chun-Liang Li, Chu Wang, Renshen Wang, Yasuhisa Fujii, Siyang Qin, Ashok Popat, and Tomas Pfister. 2021. Rope: reading order equivariant positional encoding for graph-based document information extraction. arXiv preprint arXiv:2106.10786 (2021)."},{"key":"e_1_3_2_1_15_1","volume-title":"Structurallm: Structural pre-training for form understanding. arXiv preprint arXiv:2105.11210","author":"Li Chenliang","year":"2021","unstructured":"Chenliang Li, Bin Bi, Ming Yan, Wei Wang, Songfang Huang, Fei Huang, and Luo Si. 2021. Structurallm: Structural pre-training for form understanding. arXiv preprint arXiv:2105.11210 (2021)."},{"key":"e_1_3_2_1_16_1","volume-title":"Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint arXiv:1903.11279","author":"Liu Xiaojing","year":"2019","unstructured":"Xiaojing Liu, Feiyu Gao, Qiong Zhang, and Huasha Zhao. 2019. Graph convolution for multimodal information extraction from visually rich documents. arXiv preprint arXiv:1903.11279 (2019)."},{"key":"e_1_3_2_1_17_1","volume-title":"Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692","author":"Liu Yinhan","year":"2019","unstructured":"Yinhan Liu, Myle Ott, Naman Goyal, Jingfei Du, Mandar Joshi, Danqi Chen, Omer Levy, Mike Lewis, Luke Zettlemoyer, and Veselin Stoyanov. 2019. Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"e_1_3_2_1_19_1","volume-title":"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."},{"key":"e_1_3_2_1_20_1","volume-title":"ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding. arXiv preprint arXiv:2210.06155","author":"Peng Qiming","year":"2022","unstructured":"Qiming Peng, Yinxu Pan, Wenjin Wang, Bin Luo, Zhenyu Zhang, Zhengjie Huang, Teng Hu, Weichong Yin, Yongfeng Chen, Yin Zhang, 2022. ERNIE-Layout: Layout Knowledge Enhanced Pre-training for Visually-rich Document Understanding. arXiv preprint arXiv:2210.06155 (2022)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.5555\/3367471.3367508"},{"key":"e_1_3_2_1_22_1","volume-title":"Graph attention networks. arXiv preprint arXiv:1710.10903","author":"Veli\u010dkovi\u0107 Petar","year":"2017","unstructured":"Petar Veli\u010dkovi\u0107, Guillem Cucurull, Arantxa Casanova, Adriana Romero, Pietro Lio, and Yoshua Bengio. 2017. Graph attention networks. arXiv preprint arXiv:1710.10903 (2017)."},{"key":"e_1_3_2_1_23_1","volume-title":"ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding. arXiv preprint arXiv:2209.08569","author":"Wang Wenjin","year":"2022","unstructured":"Wenjin Wang, Zhengjie Huang, Bin Luo, Qianglong Chen, Qiming Peng, Yinxu Pan, Weichong Yin, Shikun Feng, Yu Sun, Dianhai Yu, 2022. ERNIE-mmLayout: Multi-grained MultiModal Transformer for Document Understanding. arXiv preprint arXiv:2209.08569 (2022)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"e_1_3_2_1_25_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_1_26_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.253"},{"key":"e_1_3_2_1_27_1","volume-title":"Layoutlmv2: Multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740","author":"Xu Yang","year":"2020","unstructured":"Yang Xu, Yiheng Xu, Tengchao Lv, Lei Cui, Furu Wei, Guoxin Wang, Yijuan Lu, Dinei Florencio, Cha Zhang, Wanxiang Che, 2020. Layoutlmv2: Multi-modal pre-training for visually-rich document understanding. arXiv preprint arXiv:2012.14740 (2020)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N16-1174"}],"event":{"name":"MMAsia '23: ACM Multimedia Asia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Tainan Taiwan","acronym":"MMAsia '23"},"container-title":["ACM Multimedia Asia Workshops"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611380.3628554","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3611380.3628554","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,26]],"date-time":"2025-08-26T19:09:37Z","timestamp":1756235377000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3611380.3628554"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,6]]},"references-count":28,"alternative-id":["10.1145\/3611380.3628554","10.1145\/3611380"],"URL":"https:\/\/doi.org\/10.1145\/3611380.3628554","relation":{},"subject":[],"published":{"date-parts":[[2023,12,6]]},"assertion":[{"value":"2023-12-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}