{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T04:44:06Z","timestamp":1775277846354,"version":"3.50.1"},"reference-count":78,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20A20183"],"award-info":[{"award-number":["U20A20183"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62021001"],"award-info":[{"award-number":["62021001"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"GPU"},{"name":"MCC Lab of Information Science and Technology Institution and the Supercomputing Center of the USTC"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2023.3347094","type":"journal-article","created":{"date-parts":[[2023,12,26]],"date-time":"2023-12-26T19:27:53Z","timestamp":1703618873000},"page":"6142-6154","source":"Crossref","is-referenced-by-count":20,"title":["Deep Unrestricted Document Image Rectification"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8127-6639","authenticated-orcid":false,"given":"Hao","family":"Feng","sequence":"first","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6095-6132","authenticated-orcid":false,"given":"Shaokai","family":"Liu","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9624-7451","authenticated-orcid":false,"given":"Jiajun","family":"Deng","sequence":"additional","affiliation":[{"name":"Australian Institute for Machine Learning, University of Adelaide, Adelaide, SA, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1690-9836","authenticated-orcid":false,"given":"Wengang","family":"Zhou","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"CAS Key Laboratory of Technology in Geo-spatial Information Processing and Application System, Department of Electronic Engineering and Information Science, University of Science and Technology of China, Hefei, China"}]}],"member":"263","reference":[{"key":"ref1","first-page":"739","article-title":"An experimental system for office document handling and text recognition","volume-title":"Proc. Int. Conf. Pattern Recognit.","author":"Ciardiello","year":"1988"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8545609"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3146771"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33015717"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214102"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1126\/science.253.5023.974"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2008.917359"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110136"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2229971"},{"key":"ref13","article-title":"UniDoc: A universal large multimodal model for simultaneous text detection, recognition, spotting and understanding","author":"Feng","year":"2023"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6812"},{"key":"ref15","article-title":"Cnstd","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.87"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2001.937649"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.497"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70831"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2019301"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2004.1334171"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315038"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2675980"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.40"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1023\/A:1007906904009"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.88"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2003.1227630"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2001.958227"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-70659-3_36"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.151"},{"key":"ref32","article-title":"Geometric rectification of creased document images based on isometric mapping","author":"Luo","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70724"},{"key":"ref34","article-title":"Intrinsic decomposition of document images in-the-wild","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Das","year":"2020"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00022"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00423"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475388"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00450"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107576"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00494"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_30"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-57058-3_10"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00453"},{"key":"ref44","article-title":"DocScanner: Robust document image rectification with progressive learning","author":"Feng","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_27"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_13"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530756"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548214"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356563"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.191"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1023\/b:visi.0000029664.99615.94"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01270-0_11"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/5.993400"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618174"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3470970"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-019-2757-1"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2988148"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2017.2788206"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TBC.2018.2816783"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2735192"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref69","first-page":"707","article-title":"Binary codes capable of correcting deletions, insertions, and reversals","volume":"10","author":"Levenshtein","year":"1966","journal-title":"Sov. Phys. Doklady"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.147"},{"key":"ref72","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1117\/12.2520589"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2007.4376991"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref76","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref78","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"Neural Inf. Process. Syst."}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10384483\/10374269.pdf?arnumber=10374269","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:55:59Z","timestamp":1725904559000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10374269\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":78,"URL":"https:\/\/doi.org\/10.1109\/tmm.2023.3347094","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}