{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:50Z","timestamp":1783455470183,"version":"3.55.0"},"reference-count":158,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["62206104"],"award-info":[{"award-number":["62206104"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program","doi-asserted-by":"crossref","award":["2022YFC2305102"],"award-info":[{"award-number":["2022YFC2305102"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Alibaba Innovative Research"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3677075","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T19:48:04Z","timestamp":1774381684000},"page":"9210-9227","source":"Crossref","is-referenced-by-count":3,"title":["OmniParser V2: Structured-Points-of-Thought for Unified Visual Text Parsing and Its Generality to Multimodal Large Language Models"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4666-3646","authenticated-orcid":false,"given":"Wenwen","family":"Yu","sequence":"first","affiliation":[{"name":"School of Information Science and Engineering, East China University of Science and Technology, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2343-7750","authenticated-orcid":false,"given":"Zhibo","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Wan","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0516-167X","authenticated-orcid":false,"given":"Sibo","family":"Song","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Tang","sequence":"additional","affiliation":[{"name":"Alibaba Group, Hangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6277-2959","authenticated-orcid":false,"given":"Wenqing","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Communications, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3037-173X","authenticated-orcid":false,"given":"Yuliang","family":"Liu","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 Software Engineering, Huazhong University of Science and Technology, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ChatGPT","year":"2023"},{"key":"ref2","article-title":"GPT-4","year":"2023"},{"key":"ref3","article-title":"GPT-4V(ision) system card","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01368"},{"key":"ref5","first-page":"1","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":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547751"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00098"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref13","first-page":"1","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2384"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.02019"},{"key":"ref17","first-page":"1","article-title":"OCRBench V2: An improved benchmark for evaluating large multimodal models on visual text localization and reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fu","year":"2024"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21322"},{"key":"ref19","article-title":"UniDoc: A universal large multimodal model for simultaneous text detection, recognition, spotting and understanding","author":"Feng","year":"2023"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01788"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.560"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3095916"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.242"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00527"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00595"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_5"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2937086"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00480"},{"key":"ref31","first-page":"9076","article-title":"TextDragon: An end-to-end framework for arbitrary shaped text spotting","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Wei","year":"2019"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6896"},{"key":"ref33","first-page":"9126","article-title":"Convolutional character networks","volume-title":"Proc. IEEE Int. Conf. Comput. Vis.","author":"Linjie","year":"2019"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3223908"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00455"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref38","first-page":"1","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00930"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547942"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3312285"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01786"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_17"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00674"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379828"},{"key":"ref47","first-page":"1","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01478"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680981"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72751-1_17"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32286"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155612"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02653-7"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394486.3403172"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.201"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548112"},{"key":"ref58","article-title":"LayoutXLM: Multimodal pre-training for multilingual visually-rich document understanding","author":"Xu","year":"2021"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.493"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00103"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00560"},{"key":"ref62","first-page":"39","article-title":"Unidoc: Unified pretraining framework for document understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Gu","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00454"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.260"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-emnlp.274"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00685"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412927"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.389"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.846"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-acl.28"},{"key":"ref71","first-page":"1","article-title":"StrucTexTv2: Masked visual-textual prediction for document image pre-training","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu","year":"2022"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01474"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.552"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_32"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.979"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547877"},{"key":"ref78","first-page":"1","article-title":"Pix2Struct: Screenshot parsing as pretraining for visual language understanding","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Lee","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01401"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25069-9_19"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41734-4_10"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/144"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413900"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41731-3_3"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219834"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00166"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.292"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00243"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86337-1_50"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58604-1_5"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3481534"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00074"},{"key":"ref93","article-title":"Pingan-VCGroup\u2019s solution for ICDAR 2021 competition on scientific literature parsing task B: Table recognition to HTML","author":"Ye","year":"2021"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00457"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548038"},{"key":"ref96","article-title":"Trust: An accurate and end-to-end table structure recognizer using splitting-based transformers","author":"Guo","year":"2022"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611961"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01071"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_2"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00095"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.192"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01792"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01482"},{"key":"ref105","first-page":"1","article-title":"Upocr: Towards unified pixel-level ocr interface","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Peng","year":"2024"},{"key":"ref106","article-title":"StrucTexTv3: An efficient vision-language model for text-rich image perception, comprehension, and beyond","author":"Lyu","year":"2024"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref108","first-page":"1","article-title":"Nougat: Neural optical understanding for academic documents","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Blecher","year":"2024"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00382"},{"key":"ref110","article-title":"Kosmos-2.5: A multimodal literate model","author":"Lv","year":"2023"},{"key":"ref111","article-title":"General OCR theory: Towards OCR-2.0 via a unified end-to-end model","author":"Wei","year":"2024"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/JSAC.2025.3574612"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TMC.2024.3357874"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2023.3239189"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01481"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref117","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01523"},{"key":"ref119","first-page":"10524","article-title":"On layer normalization in the transformer architecture","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Xiong","year":"2020"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01461"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref122","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72761-0_10"},{"key":"ref123","article-title":"Qwen-vl: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2026.3653415"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6864"},{"key":"ref126","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_30"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16383"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16348"},{"key":"ref129","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3077555"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547882"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_15"},{"key":"ref132","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00456"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref134","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-019-00334-z"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.234"},{"key":"ref139","first-page":"379","article-title":"Open images v5 text annotation and yet another mask text spotter","volume-title":"Proc. Asian Conf. Mach. Learn.","author":"Krylov","year":"2021"},{"key":"ref140","first-page":"1","article-title":"Pix2Seq: A language modeling framework for object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2022"},{"key":"ref141","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov","year":"2019"},{"key":"ref142","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.02.002"},{"key":"ref143","first-page":"1","article-title":"Cord: A consolidated receipt dataset for post-OCR parsing","volume-title":"Proc. Document Intell. Workshop at Neural Inf. Process. Syst.","author":"Park","year":"2019"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref145","first-page":"980","article-title":"Image-to-markup generation with coarse-to-fine attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Deng","year":"2017"},{"key":"ref146","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3495831"},{"key":"ref147","first-page":"9396","article-title":"Panoptic segmentation","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit.","author":"Kirillov","year":"2018"},{"key":"ref148","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00060"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547787"},{"key":"ref150","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref152","first-page":"1","article-title":"Mini-monkey: Multi-scale adaptive cropping for multimodal large language models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Huang","year":"2025"},{"key":"ref153","article-title":"Qwen2-Vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"ref154","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024"},{"key":"ref155","article-title":"Qwen2.5-vl Technical report","author":"Bai","year":"2025"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01363"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.108"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-025-09422-z"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11455330.pdf?arnumber=11455330","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:45:03Z","timestamp":1783453503000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11455330\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":158,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3677075","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":[[2026,8]]}}}