{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:10:49Z","timestamp":1766139049908,"version":"3.40.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,5,1]],"date-time":"2025-05-01T00:00:00Z","timestamp":1746057600000},"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":["62336008","62106265"],"award-info":[{"award-number":["62336008","62106265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2025,5]]},"DOI":"10.1109\/tpami.2025.3530998","type":"journal-article","created":{"date-parts":[[2025,1,17]],"date-time":"2025-01-17T18:36:14Z","timestamp":1737138974000},"page":"3358-3376","source":"Crossref","is-referenced-by-count":4,"title":["Understand Layout and Translate Text: Unified Feature-Conductive End-to-End Document Image Translation"],"prefix":"10.1109","volume":"47","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-4057-7098","authenticated-orcid":false,"given":"Zhiyang","family":"Zhang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6892-905X","authenticated-orcid":false,"given":"Yaping","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yupu","family":"Liang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9787-6273","authenticated-orcid":false,"given":"Cong","family":"Ma","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Xiang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-3406","authenticated-orcid":false,"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4911-4717","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9864-3818","authenticated-orcid":false,"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","first-page":"109","article-title":"Integrating optical character recognition and machine translation of historical documents","volume-title":"Proc. Workshop Lang. Technol. Resour. Tools Digit. Humanities","author":"Afli"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-4543-0_30"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17537"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ESCI56872.2023.10099625"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpbt-1.8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412281"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3183386"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956695"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41731-3_5"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41676-7_28"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3324540"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.751"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.1004"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.673"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i5.16558"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25277"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-demos.10"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-long.392"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.naacl-short.41"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4770"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1162\/coli.2006.32.4.485"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref29","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.534"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"article-title":"LayoutXLM: Multimodal pre-training for multilingual visually-rich document understanding","year":"2021","author":"Xu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"ref37","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-1030"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d16-1163"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2061"},{"article-title":"Sparks of artificial general intelligence: Early experiments with GPT-4","year":"2023","author":"Bubeck","key":"ref42"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1036\/1097-8542.284200"},{"article-title":"Is chatGPT a good translator? Yes with GPT-4 as the engine","year":"2023","author":"Jiao","key":"ref44"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01785"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","year":"2024","author":"Wang","key":"ref47"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2876404"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2954406"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3021361"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3233226"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3333949"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3232389"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3181116"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01654-0"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i11.26538"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1017\/cbo9781316584989.004"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5040\/9781635577068-1238"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3235826"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.192"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547911"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3214102"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.14778\/2824032.2824058"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/3183713.3183729"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10958761\/10844563.pdf?arnumber=10844563","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T17:13:54Z","timestamp":1744305234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10844563\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,5]]},"references-count":71,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3530998","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"type":"print","value":"0162-8828"},{"type":"electronic","value":"2160-9292"},{"type":"electronic","value":"1939-3539"}],"subject":[],"published":{"date-parts":[[2025,5]]}}}