{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,23]],"date-time":"2026-10-23T20:20:00Z","timestamp":1792786800885,"version":"4.5.0"},"reference-count":56,"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":[{"name":"NSFC","award":["62322604"],"award-info":[{"award-number":["62322604"]}],"id":[{"id":"https:\/\/ror.org\/01h0zpd94","id-type":"ROR","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3729471","type":"journal-article","created":{"date-parts":[[2026,9,7]],"date-time":"2026-09-07T19:04:33Z","timestamp":1788807873000},"page":"9661-9674","source":"Crossref","is-referenced-by-count":0,"title":["BPE-Level Visual-Textual Alignment for Multi-Scene Text Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3346-8315","authenticated-orcid":false,"given":"Tongkun","family":"Guan","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-8477-7021","authenticated-orcid":false,"given":"Yutong","family":"Cai","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8449-1834","authenticated-orcid":false,"given":"Haocheng","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zijian","family":"Hu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1235-598X","authenticated-orcid":false,"given":"Wei","family":"Shen","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4029-3322","authenticated-orcid":false,"given":"Xiaokang","family":"Yang","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University","place":["Shanghai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.378"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0823-z"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107656"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3348297"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01348"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02155"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2011.6126402"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.157"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3496576"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00983"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3609196"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3294822"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_24"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3156390"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3539597.3570428"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680877"},{"key":"ref17","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref18","article-title":"COCO-text: Dataset and benchmark for text detection and recognition in natural images","author":"Veit","year":"2016","journal-title":"arXiv:1601.07140"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00453"},{"key":"ref20","article-title":"Beyond cropped regions: New benchmark and corresponding baseline for Chinese scene text retrieval in diverse layouts","author":"Li","year":"2025","journal-title":"arXiv:2506.04999"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2013.221"},{"key":"ref22","article-title":"Detecting curve text in the wild: New dataset and new solution","author":"Yuliang","year":"2017","journal-title":"arXiv:1712.02170"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00112"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2015.7333942"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00869"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.237"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00156"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00252"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107559"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2017.233"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00918"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00253"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00225"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00264"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86549-8_36"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17635"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.177"},{"key":"ref38","article-title":"FigureQA: An annotated figure dataset for visual reasoning","author":"Kahou","year":"2017","journal-title":"arXiv:1710.07300"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093523"},{"key":"ref40","article-title":"Dynamic prompt learning via policy gradient for semi-structured mathematical reasoning","author":"Lu","year":"2022","journal-title":"arXiv:2209.14610"},{"key":"ref41","article-title":"DUE: End-to-end document understanding benchmark","volume-title":"Proc. NeurIPS Datasets and Benchmarks","volume":"1","author":"Borchmann","year":"2021"},{"key":"ref42","article-title":"TabFact: A large-scale dataset for table-based fact verification","author":"Chen","year":"2019","journal-title":"arXiv:1909.02164"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P15-1142"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73113-6_10"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00254"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2019.00250"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3107437"},{"key":"ref49","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01100"},{"key":"ref51","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"},{"key":"ref52","article-title":"SigLIP 2: Multilingual vision-language encoders with improved semantic understanding, localization, and dense features","author":"Tschannen","year":"2025","journal-title":"arXiv:2502.14786"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_43"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_41"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01854"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01478"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11683336.pdf?arnumber=11683336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,24]],"date-time":"2026-09-24T15:55:19Z","timestamp":1790265319000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11683336\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3729471","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}