{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,13]],"date-time":"2026-07-13T18:52:43Z","timestamp":1783968763499,"version":"3.55.0"},"reference-count":53,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.02019","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"21744-21754","source":"Crossref","is-referenced-by-count":4,"title":["CC-OCR: A Comprehensive and Challenging OCR Benchmark for Evaluating Large Multimodal Models in Literacy"],"prefix":"10.1109","author":[{"given":"Zhibo","family":"Yang","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jun","family":"Tang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhaohai","family":"Li","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengfei","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jianqiang","family":"Wan","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Humen","family":"Zhong","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuejing","family":"Liu","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingkun","family":"Yang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peng","family":"Wang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuai","family":"Bai","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lianwen","family":"Jin","sequence":"additional","affiliation":[{"name":"South China University of Technology"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junyang","family":"Lin","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"The claude 3 model family: Opus","volume-title":"sonnet, haiku"},{"key":"ref2","author":"Abdin","year":"2024","journal-title":"Phi-4 technical report"},{"key":"ref3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Qwen-vl: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","article-title":"Qwen2.5vl technical report","author":"Bai","year":"2025","journal-title":"arXiv preprint"},{"key":"ref6","article-title":"Nougat: Neural optical understanding for academic documents","author":"Blecher","year":"2023","journal-title":"arXiv preprint"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681167"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2018.8546143"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-emnlp.175"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00244"},{"key":"ref13","article-title":"Post-ocr parsing: building simple and robust parser via bio tagging","volume-title":"Workshop on Document Intelligence at NeurIPS 2019","author":"Hwang","year":"2019"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICDARW.2019.10029"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_29"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41731-3_3"},{"key":"ref18","article-title":"Binary coors capable or \u2019correcting deletions, insertions, and reversals","author":"Lcvenshtcin","year":"1966","journal-title":"Soviet Physics-Doklady"},{"key":"ref19","first-page":"1918","article-title":"TableBank: Table benchmark for image-based table detection and recognition","volume-title":"Proceedings of the 12th Language Resources and Evaluation Conference","author":"Li","year":"2020"},{"key":"ref20","article-title":"Focus anywhere for finegrained multi-page document understanding","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4235-6"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2026.3653415"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00098"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01480"},{"key":"ref26","article-title":"Kosmos-2.5: A multimodal literate model","author":"Lv","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00247"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s100320200071"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.5244\/C.26.127"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref32","article-title":"Cord: a consolidated receipt dataset for post-ocr parsing","volume-title":"Workshop on Document Intelligence at NeurIPS 2019","author":"Park","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00851"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2019.06.020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.404"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01845"},{"key":"ref39","article-title":"Gemini: a family of highly capable multimodal models","author":"Team","year":"2023","journal-title":"arXiv preprint"},{"key":"ref40","author":"Tong","year":"2024","journal-title":"Cambrian-1: A fully open, vision-centric exploration of multimodal 11 ms"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16378"},{"key":"ref42","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":"ref43","article-title":"General ocr theory: Towards ocr-2.0 via a unified end-to-end model","author":"Wei","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00461"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01474"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25430"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-41679-8_32"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00451"},{"key":"ref49","article-title":"Detecting curve text in the wild: New dataset and new solution","author":"Yuliang","year":"2017","journal-title":"arXiv preprint"},{"key":"ref50","article-title":"Tabpedia: Towards comprehensive visual table understanding with concept synergy","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref51","article-title":"Doclayout-yolo: Enhancing document layout analysis through diverse synthetic data and global-to-local adaptive perception","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_34"},{"key":"ref53","author":"Zhu","year":"2025","journal-title":"Internvl3: Exploring advanced training and test-time recipes for open-source multimodal models"}],"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\/11445117.pdf?arnumber=11445117","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:19:56Z","timestamp":1777529996000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445117\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.02019","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}