{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T17:54:33Z","timestamp":1772906073650,"version":"3.50.1"},"reference-count":44,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62106265"],"award-info":[{"award-number":["62106265"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/taslp.2023.3324540","type":"journal-article","created":{"date-parts":[[2023,10,13]],"date-time":"2023-10-13T18:10:57Z","timestamp":1697220657000},"page":"2153-2165","source":"Crossref","is-referenced-by-count":9,"title":["Modal Contrastive Learning Based End-to-End Text Image Machine Translation"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9787-6273","authenticated-orcid":false,"given":"Cong","family":"Ma","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-2070-1741","authenticated-orcid":false,"given":"Xu","family":"Han","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1053-5496","authenticated-orcid":false,"given":"Linghui","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6892-905X","authenticated-orcid":false,"given":"Yaping","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1028-3406","authenticated-orcid":false,"given":"Yang","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4911-4717","authenticated-orcid":false,"given":"Yu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9864-3818","authenticated-orcid":false,"given":"Chengqing","family":"Zong","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i14.17537"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-33-4543-0_30"},{"key":"ref3","first-page":"109","article-title":"Integrating optical character recognition and machine translation of historical documents","volume-title":"Proc. Workshop Lang. Technol. Resour. Tools Digit. Humanities","author":"Afli","year":"2016"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s10032-015-0247-x"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICDAR.2011.166"},{"key":"ref6","article-title":"Image translation network","volume-title":"Image Translation Model","author":"Jain","year":"2021"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/icpr48806.2021.9412281"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86331-9_7"},{"key":"ref9","first-page":"13","article-title":"ViLBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 32: Annu. Conf. Neural Inf. Process. Syst.","author":"Lu","year":"2019"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00692"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.452"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.43"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","first-page":"2017","article-title":"Spatial transformer networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst. 28: Annu. Conf. Neural Inf. Process. Syst.","author":"Jaderberg","year":"2015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.543"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1045"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00959"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11390-019-1923-y"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00481"},{"key":"ref23","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 3rd Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2646371"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3066903"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00285"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2018.02.006"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/559"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.397"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.nlpbt-1.8"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"ref33","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1310.4546"},{"key":"ref35","first-page":"5628","article-title":"A theoretical analysis of contrastive unsupervised representation learning","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Saunshi","year":"2019"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.439"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.280"},{"key":"ref38","article-title":"CERT: Contrastive self-supervised learning for language understanding","author":"Fang","year":"2020"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.72"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d17-1105"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.112"},{"key":"ref42","first-page":"1067","article-title":"Entity-level cross-modal learning improves multi-modal machine translation","volume-title":"Proc. Findings the Assoc. Comput. Linguistics: EMNLP","author":"Huang","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref44","article-title":"How2: A large-scale dataset for multimodal language understanding","volume-title":"Proc. NeurIPS","author":"Sanabria","year":"2018"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/10304349\/10284997.pdf?arnumber=10284997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,9]],"date-time":"2024-04-09T19:45:57Z","timestamp":1712691957000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10284997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":44,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3324540","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}