{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,24]],"date-time":"2026-04-24T06:14:31Z","timestamp":1777011271593,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1109\/wincom59760.2023.10322990","type":"proceedings-article","created":{"date-parts":[[2023,11,22]],"date-time":"2023-11-22T19:07:27Z","timestamp":1700680047000},"page":"1-7","source":"Crossref","is-referenced-by-count":7,"title":["Visually-Rich Document Understanding: Concepts, Taxonomy and Challenges"],"prefix":"10.1109","author":[{"given":"Abdellatif","family":"Sassioui","sequence":"first","affiliation":[{"name":"LEYTON,Casablanca,Morocco"}]},{"given":"Rachid","family":"Benouini","sequence":"additional","affiliation":[{"name":"LEYTON,Casablanca,Morocco"}]},{"given":"Yasser","family":"El Ouargui","sequence":"additional","affiliation":[{"name":"LEYTON,Casablanca,Morocco"}]},{"given":"Mohamed","family":"El Kamili","sequence":"additional","affiliation":[{"name":"C3S Laboratory, Hassan II University\nCasablanca, Morocco"}]},{"given":"Meriyem","family":"Chergui","sequence":"additional","affiliation":[{"name":"LEYTON,Casablanca,Morocco"}]},{"given":"Mohammed","family":"Ouzzif","sequence":"additional","affiliation":[{"name":"LEYTON,Casablanca,Morocco"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.1995.602059"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/34.244677"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1476"},{"key":"ref9","volume-title":"Textract ocr","year":"2023"},{"key":"ref10","volume-title":"Google document ai","year":"2023"},{"key":"ref11","volume-title":"Azure document ai","year":"2023"},{"key":"ref12","article-title":"A survey of deep learning approaches for ocr and document understanding","author":"Subramani","year":"2020","journal-title":"arXiv preprint"},{"key":"ref13","article-title":"Document ai: Benchmarks, models and applications","author":"Cui","year":"2021","journal-title":"arXiv preprint"},{"key":"ref14","article-title":"DUE: End-to-end document understanding benchmark","volume-title":"Thirty-fifth Conference on Neural Information Processing Systems Datasets and Benchmarks Track (Round 2)","author":"Borchmann"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12269"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_2"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2825107"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.368"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00917"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.74"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.149"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333933"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41734-4_10"},{"key":"ref24","article-title":"Pix2struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"International Conference on Machine Learning","author":"Lee"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109419"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_34"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547751"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475345"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"ref35","article-title":"{BERT}grid: Contextualized embedding for 2d document representation and understanding","volume-title":"Workshop on Document Intelligence at NeurIPS","author":"Denk"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_35"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-2005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_22"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214102"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref41","volume-title":"Tesseract: An open-source optical character recognition engine","author":"Kay","year":"2007"},{"key":"ref42","volume-title":"Easyocr"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.265"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413900"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.703"},{"key":"ref48","article-title":"BERT: Pretraining of deep bidirectional transformers for language understanding","volume-title":"Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers)","author":"Devlin"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01605"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109834"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333910"},{"key":"ref53","article-title":"Funsd: A dataset for form understanding in noisy scanned documents","author":"Guillaume Jaume","year":"2019","journal-title":"Accepted to ICDAR-OST"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref55","volume-title":"Cord: A consolidated receipt dataset for post-ocr parsing","author":"Park","year":"2019"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.82"}],"event":{"name":"2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM)","location":"Istanbul, Turkiye","start":{"date-parts":[[2023,10,26]]},"end":{"date-parts":[[2023,10,28]]}},"container-title":["2023 10th International Conference on Wireless Networks and Mobile Communications (WINCOM)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10322877\/10322879\/10322990.pdf?arnumber=10322990","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,14]],"date-time":"2024-03-14T01:46:04Z","timestamp":1710380764000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10322990\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/wincom59760.2023.10322990","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]}}}