{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,10]],"date-time":"2026-01-10T19:40:18Z","timestamp":1768074018455,"version":"3.49.0"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LZ23F020004"],"award-info":[{"award-number":["LZ23F020004"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004731","name":"Natural Science Foundation of Zhejiang Province","doi-asserted-by":"publisher","award":["LQ23F020008"],"award-info":[{"award-number":["LQ23F020008"]}],"id":[{"id":"10.13039\/501100004731","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U22A2094"],"award-info":[{"award-number":["U22A2094"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306278"],"award-info":[{"award-number":["62306278"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Public Welfare Technology Research Project of Zhejiang Province under ","award":["LGF21F020010"],"award-info":[{"award-number":["LGF21F020010"]}]},{"name":"Young Elite Scientists Sponsorship Program"},{"name":"CAST","award":["2022QNRC001"],"award-info":[{"award-number":["2022QNRC001"]}]},{"name":"Zhejiang Gongshang University Digital + Discipline Construction","award":["SZJ2022A002"],"award-info":[{"award-number":["SZJ2022A002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2024,11]]},"DOI":"10.1109\/tkde.2024.3400060","type":"journal-article","created":{"date-parts":[[2024,5,13]],"date-time":"2024-05-13T17:39:07Z","timestamp":1715621947000},"page":"5860-5873","source":"Crossref","is-referenced-by-count":5,"title":["Cross-Lingual Cross-Modal Retrieval With Noise-Robust Fine-Tuning"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-2823-3051","authenticated-orcid":false,"given":"Rui","family":"Cai","sequence":"first","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5244-3274","authenticated-orcid":false,"given":"Jianfeng","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-6794-9381","authenticated-orcid":false,"given":"Tianxiang","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5600-3583","authenticated-orcid":false,"given":"Yonghui","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7231-1260","authenticated-orcid":false,"given":"Yabing","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0201-1638","authenticated-orcid":false,"given":"Xun","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering and Information Science, School of Information Science and Technology, University of Science and Technology of China, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5566-4689","authenticated-orcid":false,"given":"Xun","family":"Wang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang Gongshang University, Hangzhou, Zhejiang, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3094-7735","authenticated-orcid":false,"given":"Meng","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Information Engineering, Hefei University of Technology, Hefei, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2765836"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16406"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3102119"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3144352"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611949"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475621"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00217"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3140611"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3149716"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401151"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00397"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00414"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.315"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3634917"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28376"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.195"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.findings-emnlp.293"},{"key":"ref18","first-page":"79","article-title":"Europarl: A parallel corpus for statistical machine translation","volume-title":"Proc. Mach. Transl. Summit x: Papers","volume":"5","author":"Koehn","year":"2005"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.507"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548003"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475380"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3463031"},{"key":"ref25","first-page":"6616","article-title":"Large-scale adversarial training for vision-and-language representation learning","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Gan","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462838"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6795"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref29","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/2505515.2507880"},{"key":"ref31","first-page":"2234","article-title":"Semantic concept discovery for large-scale zero-shot event detection","volume-title":"Proc. 24th Int. Joint Conf. Artif. Intell.","author":"Chang","year":"2015"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3078971.3079041"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2627563"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00208"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_13"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475241"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462823"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3168424"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.767"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00877"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00725"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.07.028"},{"key":"ref44","article-title":"Clip2video: Mastering video-text retrieval via image clip","author":"Fang","year":"2021"},{"key":"ref45","article-title":"Image search using multilingual texts: A cross-modal learning approach between image and text","author":"Portaz","year":"2019"},{"key":"ref46","article-title":"Towards zero-shot cross-lingual image retrieval","author":"Aggarwal","year":"2020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W15-1521"},{"key":"ref48","article-title":"Word translation without parallel data","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Conneau","year":"2018"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-demos.12"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00288"},{"key":"ref51","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1238"},{"key":"ref53","first-page":"29691","article-title":"Multi-lingual acquisition on multimodal pre-training for cross-modal retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang","year":"2022"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.728"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri","year":"2018"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3059295"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3150959"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_29"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123366"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350906"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3377875"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref72","article-title":"Adam: A method for stochastic optimization","volume-title":"Int. Conf. Learn. Representations","author":"Kingma","year":"2014"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2832602"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.36"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-056-4_050"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00272"},{"key":"ref77","article-title":"Use what you have: Video retrieval using representations from collaborative experts","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Liu","year":"2019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2020.3042067"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4330"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/10709365\/10530137.pdf?arnumber=10530137","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,10]],"date-time":"2024-10-10T11:24:47Z","timestamp":1728559487000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10530137\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11]]},"references-count":80,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2024.3400060","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11]]}}}