{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:41Z","timestamp":1777888961353,"version":"3.51.4"},"reference-count":66,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001839","name":"University Grants Committee (UGC)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001839","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00343","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"3596-3606","source":"Crossref","is-referenced-by-count":0,"title":["DOGR: Towards Versatile Visual Document Grounding and Referring"],"prefix":"10.1109","author":[{"given":"Yinan","family":"Zhou","sequence":"first","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuxin","family":"Chen","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haokun","family":"Lin","sequence":"additional","affiliation":[{"name":"ARC Lab, Tencent PCG"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yichen","family":"Wu","sequence":"additional","affiliation":[{"name":"City University of Hongkong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuyu","family":"Yang","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongang","family":"Qi","sequence":"additional","affiliation":[{"name":"vivo Mobile Communication Co."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chen","family":"Ma","sequence":"additional","affiliation":[{"name":"City University of Hongkong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Zhu","sequence":"additional","affiliation":[{"name":"Xi'an Jiaotong University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Qwen2.5-vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00439"},{"key":"ref3","volume-title":"Textocr-gpt4v","author":"Carter","year":"2024"},{"key":"ref4","article-title":"Shikra: Unleashing multimodal 1lm\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Tabfact: A large-scale dataset for table-based fact verification","volume-title":"International Conference on Learning Representations (ICLR)","author":"Chen"},{"key":"ref6","article-title":"Internvl: Scaling up vision foundation models and aligning for generic visual-linguistic tasks","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and testtime scaling","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4231-5"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.78"},{"key":"ref10","article-title":"Gemini 2.5: Pushing the frontier with advanced reasoning, multimodality, long context, and next generation agentic capabilities","author":"Comanici","year":"2025","journal-title":"arXiv preprint"},{"key":"ref11","volume-title":"Pymupdf: Python bindings for mupdf.","year":"2024"},{"key":"ref12","article-title":"Internlm-xcomposer2\u20134khd: A pioneering large vision-language model handling resolutions from 336 pixels to 4 k hd","author":"Dong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.acl-long.291"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00592"},{"key":"ref18","volume-title":"Figureqa: An annotated figure dataset for visual reasoning","author":"Ebrahimi Kahou","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_15"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.571"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref22","article-title":"Toklip: Marry visual tokens to clip for multimodal comprehension and generation","author":"Lin","year":"2025","journal-title":"arXiv preprint"},{"key":"ref23","volume-title":"Draw-and-understand: Leveraging visual prompts to enable mllms to comprehend what you want","author":"Lin","year":"2024"},{"key":"ref24","article-title":"Focus anywhere for finegrained multi-page document understanding","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Focus anywhere for finegrained multi-page document understanding","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref26","article-title":"Aligning large multi-modal model with robust instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Mmc: Advancing multimodal chart understanding with large-scale instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref30","article-title":"Kosmos-2.5: A multimodal literate model","author":"Lv","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s100320200071"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.inlg-1.20"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref39","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"ArXiv, abs\/2306"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_44"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"ref44","volume-title":"Deepform: Understand structured documents at scale","author":"Svetlichnaya","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.401"},{"key":"ref47","article-title":"Gemini 1.5: Unlocking multimodal understanding across millions of tokens of context","author":"Team","year":"2024","journal-title":"arXiv preprint"},{"key":"ref48","volume-title":"Cc-main-2021\u201331-pdfuntruncated","author":"Allison","year":"2024"},{"key":"ref49","article-title":"Cambrian1: A fully open, vision-centric exploration of multimodal 1 lms","author":"Tong","year":"2024","journal-title":"arXiv preprint"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3472749.3474765"},{"key":"ref52","volume-title":"Mineru: An open-source solution for precise document content extraction","author":"Wang","year":"2024"},{"key":"ref53","article-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref54","article-title":"Vary: Scaling up the vision vocabulary for large vision-language models","author":"Wei","year":"2023","journal-title":"arXiv preprint"},{"key":"ref55","volume-title":"wendlerc\/renderedtext","author":"Wendler","year":"2023"},{"key":"ref56","article-title":"Magpie: Alignment data synthesis from scratch by prompting aligned 11 ms with nothing","volume-title":"ArXiv, abs\/2406.08464","author":"Xu","year":"2024"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00543"},{"key":"ref58","article-title":"Qwen2 technical report","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.187"},{"key":"ref60","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00451"},{"key":"ref62","article-title":"Mm1. 5: Methods, analysis & insights from multimodal 11 m fine-tuning","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72775-7_2"},{"key":"ref64","article-title":"Internlm-xcomposer-2.5: A versatile large vision language model supporting long-contextual input and output","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.334"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2025.3599088"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11446010.pdf?arnumber=11446010","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:47Z","timestamp":1777611827000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446010\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00343","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}