{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T15:57:26Z","timestamp":1783439846820,"version":"3.54.6"},"reference-count":69,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62225603"],"award-info":[{"award-number":["62225603"]}],"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":["62576147"],"award-info":[{"award-number":["62576147"]}],"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":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3653415","type":"journal-article","created":{"date-parts":[[2026,1,27]],"date-time":"2026-01-27T05:48:07Z","timestamp":1769492887000},"page":"6008-6019","source":"Crossref","is-referenced-by-count":24,"title":["TextMonkey: An OCR-Free Large Multimodal Model for Understanding Document"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3037-173X","authenticated-orcid":false,"given":"Yuliang","family":"Liu","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2621-2020","authenticated-orcid":false,"given":"Biao","family":"Yang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-3786-6476","authenticated-orcid":false,"given":"Qiang","family":"Liu","sequence":"additional","affiliation":[{"name":"Kingsoft, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-7266-3950","authenticated-orcid":false,"given":"Zhang","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyin","family":"Ma","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-4491-2568","authenticated-orcid":false,"given":"Shuo","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3449-5940","authenticated-orcid":false,"given":"Xiang","family":"Bai","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and Automation, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref4","first-page":"18893","article-title":"Pix2Struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2023"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref6","first-page":"2024","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref7","article-title":"LLaVAR: Enhanced visual instruction tuning for text-rich image understanding","author":"Zhang","year":"2023"},{"key":"ref8","article-title":"UniDoc: A universal large multimodal model for simultaneous text detection, recognition, spotting and understanding","author":"Feng","year":"2023"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4250-y"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475345"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.748"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27828"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"ref22","first-page":"1","article-title":"StrucTexTv2: Masked visual-textual prediction for document image pre-training","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Yu","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_23"},{"key":"ref24","article-title":"Towards improving document understanding: An exploration on text-grounding via mllms","author":"Wang","year":"2023"},{"key":"ref25","article-title":"Qwen2.5-VL technical report","author":"Bai","year":"2025"},{"key":"ref26","article-title":"Qwen3-VL technical report","author":"Bai","year":"2025"},{"key":"ref27","article-title":"dots.ocr: Multilingual document layout parsing in a single vision-language model","author":"Li","year":"2025"},{"key":"ref28","article-title":"MinerU2.5: A decoupled vision-language model for efficient high-resolution document parsing","author":"Niu","year":"2025"},{"key":"ref29","article-title":"DeepSeek-OCR: Contexts optical compression","author":"Wei","year":"2025"},{"key":"ref30","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Hu","year":"2022"},{"key":"ref31","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023"},{"key":"ref32","first-page":"1","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Bolya","year":"2023"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1723"},{"key":"ref34","article-title":"COCO-Text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1148170.1148307"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref42","first-page":"1697","article-title":"InfographicVQA","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Mathew","year":"2022"},{"key":"ref43","article-title":"DeepForm: Understand structured documents at scale","author":"Svetlichnaya","year":"2020","journal-title":"Weights & Biases report"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref46","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2142"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.27999"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01239"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref52","article-title":"InternLM-XComposer2: Mastering free-form text-image composition and comprehension in vision-language large model","author":"Dong","year":"2024"},{"key":"ref53","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/icdar.2019.00244"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41731-3_3"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547787"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2021.3107437"},{"key":"ref66","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02313"},{"key":"ref69","article-title":"MonkeyOCR: Document parsing with a structure-recognition-relation triplet paradigm","author":"Li","year":"2025"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11364328.pdf?arnumber=11364328","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:27Z","timestamp":1775505387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11364328\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":69,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3653415","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}