{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T10:39:04Z","timestamp":1774435144626,"version":"3.50.1"},"reference-count":24,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["62503015"],"award-info":[{"award-number":["62503015"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Signal Process. Lett."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/lsp.2025.3636988","type":"journal-article","created":{"date-parts":[[2025,11,25]],"date-time":"2025-11-25T18:31:45Z","timestamp":1764095505000},"page":"106-110","source":"Crossref","is-referenced-by-count":1,"title":["TIMTQE: Benchmarking Machine Translation Quality Estimation for Text Images"],"prefix":"10.1109","volume":"33","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3488-6028","authenticated-orcid":false,"given":"Shuo","family":"Li","sequence":"first","affiliation":[{"name":"College of Information and Communication Engineering, Harbin Engineering University, Harbin, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-1000","authenticated-orcid":false,"given":"Xiaojun","family":"Bi","sequence":"additional","affiliation":[{"name":"Key Laboratory of Ethnic Language Intelligent Analysis and Security Governance of MOE, Minzu University of China, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1014-4545","authenticated-orcid":false,"given":"Yiwen","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute for Artificial Intelligence, Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3530998"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.325"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/coli_a_00481"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-emnlp.51"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2871250"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1017\/S1351324922000110"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.445"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.121"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3380996"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3178899"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref12","first-page":"22721","article-title":"Large multilingual models pivot zero-shot multimodal learning across languages","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Hu","year":"2024"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2020.3010163"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.45"},{"key":"ref15","first-page":"7748","article-title":"MTVQA: Benchmarking multilingual text-centric visual question answering","volume-title":"Proc. Findings Assoc. Comput. Linguistics","author":"Tang","year":"2025"},{"key":"ref16","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref17","article-title":"Gemini: A family of highly capable multimodal models","author":"Team","year":"2023"},{"key":"ref18","first-page":"4963","article-title":"MLQE-PE: A multilingual quality estimation and post-editing dataset","volume-title":"Proc. 13th Lang. Resour. Eval. Conf.","author":"Fomicheva","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657891"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333898"},{"key":"ref21","article-title":"mPLUG-Owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02527"},{"key":"ref23","article-title":"Qwen2. 5-vl technical report","author":"Bai","year":"2025"},{"key":"ref24","article-title":"Llava-next: Improved reasoning, OCR, and world knowledge","author":"Liu","year":"2024"}],"container-title":["IEEE Signal Processing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/97\/11304147\/11267222.pdf?arnumber=11267222","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:03:52Z","timestamp":1766171032000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11267222\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":24,"URL":"https:\/\/doi.org\/10.1109\/lsp.2025.3636988","relation":{},"ISSN":["1070-9908","1558-2361"],"issn-type":[{"value":"1070-9908","type":"print"},{"value":"1558-2361","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}