{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:38:45Z","timestamp":1783183125813,"version":"3.54.6"},"reference-count":49,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2020AAA0107904"],"award-info":[{"award-number":["2020AAA0107904"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62241604"],"award-info":[{"award-number":["62241604"]}],"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":["61866020"],"award-info":[{"award-number":["61866020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Natural Science Foundation Project of Yunnan Science and Technology Department","award":["202301AT070444"],"award-info":[{"award-number":["202301AT070444"]}]},{"name":"Yunnan Provincial Major Science and Technology Special Plan Projects","award":["202103AA080015"],"award-info":[{"award-number":["202103AA080015"]}]},{"name":"Yunnan Key Research Projects","award":["202203AA080004"],"award-info":[{"award-number":["202203AA080004"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE\/ACM Trans. Audio Speech Lang. Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/taslp.2023.3301210","type":"journal-article","created":{"date-parts":[[2023,8,2]],"date-time":"2023-08-02T17:47:01Z","timestamp":1690998421000},"page":"3015-3026","source":"Crossref","is-referenced-by-count":14,"title":["Layer-Level Progressive Transformer With Modality Difference Awareness for Multi-Modal Neural Machine Translation"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3522-7120","authenticated-orcid":false,"given":"Junjun","family":"Guo","sequence":"first","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3391-7582","authenticated-orcid":false,"given":"Junjie","family":"Ye","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6475-638X","authenticated-orcid":false,"given":"Yan","family":"Xiang","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4012-461X","authenticated-orcid":false,"given":"Zhengtao","family":"Yu","sequence":"additional","affiliation":[{"name":"Faculty of Information Engineering and Automation, Kunming University of Science and Technology, Kunming, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16376"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.06.010"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3138719"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3092187"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413715"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.26615\/978-954-452-073-1_007"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1400"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.12.076"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1175"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2360"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref45","first-page":"1","article-title":"Incorporating bert into neural machine translation","author":"zhu","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1642"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1162"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w16-3210"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1653"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.480"},{"key":"ref49","article-title":"Doubly attentive transformer machine translation","author":"arslan","year":"2018","journal-title":"CoRR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.400"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6439"},{"key":"ref9","first-page":"85","article-title":"Multimodal neural machine translation using CNN and transformer encoder","author":"takushima","year":"0","journal-title":"Advances in Natural Language Processing"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-1422"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s10489-022-03331-8"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.673"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.273"},{"key":"ref40","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013714"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413441"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.305"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.coling-main.380"},{"key":"ref33","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"0","journal-title":"Proc 6th Int Conf Learn Representations"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2019.04.044"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6402"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4718"},{"key":"ref39","first-page":"5098","article-title":"Noise-robust cross-modal interactive learning with text2image mask for multi-modal neural machine translation","author":"ye","year":"0","journal-title":"Proc 29th Int Conf Comput Linguistics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5822"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1105"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.eacl-main.281"},{"key":"ref26","article-title":"Multimodal attention for neural machine translation","author":"caglayan","year":"2016"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4746"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2020.11.024"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-6406"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1329"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1095"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2358"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01073"}],"container-title":["IEEE\/ACM Transactions on Audio, Speech, and Language Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6570655\/9970249\/10202177.pdf?arnumber=10202177","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T18:04:31Z","timestamp":1693245871000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10202177\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":49,"URL":"https:\/\/doi.org\/10.1109\/taslp.2023.3301210","relation":{},"ISSN":["2329-9290","2329-9304"],"issn-type":[{"value":"2329-9290","type":"print"},{"value":"2329-9304","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}