{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T06:36:37Z","timestamp":1774938997209,"version":"3.50.1"},"reference-count":54,"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\/501100013059","name":"Jiangsu Funding Program for Excellent Postdoctoral Talent","doi-asserted-by":"publisher","award":["2025ZB557"],"award-info":[{"award-number":["2025ZB557"]}],"id":[{"id":"10.13039\/501100013059","id-type":"DOI","asserted-by":"publisher"}]},{"name":"18th Special Funding of the China Postdoctoral Science Foundation","award":["2025T181131"],"award-info":[{"award-number":["2025T181131"]}]},{"DOI":"10.13039\/100012493","name":"Jiangsu Provincial Natural Science Foundation for Youth","doi-asserted-by":"publisher","award":["BK20251442"],"award-info":[{"award-number":["BK20251442"]}],"id":[{"id":"10.13039\/100012493","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3675497","type":"journal-article","created":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T19:50:48Z","timestamp":1774381848000},"page":"3299-3310","source":"Crossref","is-referenced-by-count":0,"title":["Pseudo-Text Guided Robust Learning for Noisy Correspondence in Cross-Modal Retrieval"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2773-9924","authenticated-orcid":false,"given":"Dan","family":"Shi","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5341-5985","authenticated-orcid":false,"given":"Zechao","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2993-7142","authenticated-orcid":false,"given":"Lei","family":"Zhu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9008-222X","authenticated-orcid":false,"given":"Jinhui","family":"Tang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2421443"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2963957"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2024.3525147"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3467130"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591758"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374111"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3330975"},{"key":"ref8","first-page":"29406","article-title":"Learning with noisy correspondence for cross-modal matching","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Huang"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01904"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02519"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3318002"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448059"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01676"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.4135\/9781071810118"},{"key":"ref15","first-page":"7164","article-title":"How does disagreement help generalization against label corruption?","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yu"},{"key":"ref16","first-page":"312","article-title":"Unsupervised label noise modeling and loss correction","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Arazo"},{"key":"ref17","article-title":"Robust early-learning: Hindering the memorization of noisy labels","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Xia"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3446776"},{"key":"ref19","first-page":"12","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547922"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680860"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2419074"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878970"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2863040"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038354"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3637442"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00591"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3038365"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2024\/69"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657756"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.541"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00750"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref38","first-page":"4514","article-title":"Probing inter-modality: Visual parsing with self-attention for vision-and-language pre-training","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Xue"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374221"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02585"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3559457"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00726"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref44","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref45","article-title":"Enhancing zero-shot facial expression recognition by LLM knowledge transfer","author":"Zhao","year":"2024","journal-title":"arXiv:2405.19100"},{"key":"ref46","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":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00041"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2016.2577031"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"ref53","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Kingma"},{"key":"ref54","article-title":"GIT: A generative image-to-text transformer for vision and language","author":"Wang","year":"2022","journal-title":"Trans. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11455609.pdf?arnumber=11455609","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,31]],"date-time":"2026-03-31T05:08:58Z","timestamp":1774933738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11455609\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3675497","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}