{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T07:23:47Z","timestamp":1782977027802,"version":"3.54.5"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,3,1]],"date-time":"2023-03-01T00:00:00Z","timestamp":1677628800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["DE190100626"],"award-info":[{"award-number":["DE190100626"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["226-2022-00051"],"award-info":[{"award-number":["226-2022-00051"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,3,1]]},"DOI":"10.1109\/tpami.2022.3181116","type":"journal-article","created":{"date-parts":[[2022,6,9]],"date-time":"2022-06-09T20:33:42Z","timestamp":1654806822000},"page":"3918-3932","source":"Crossref","is-referenced-by-count":113,"title":["Video Pivoting Unsupervised Multi-Modal Machine Translation"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6096-9858","authenticated-orcid":false,"given":"Mingjie","family":"Li","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Po-Yao","family":"Huang","sequence":"additional","affiliation":[{"name":"Facebook AI Research, Menlo Park, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7778-8807","authenticated-orcid":false,"given":"Xiaojun","family":"Chang","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, Australian Artificial Intelligence Institute, University of Technology Sydney, Ultimo, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Junjie","family":"Hu","sequence":"additional","affiliation":[{"name":"University of Wisconsin-Madison, Madison, WI, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0512-880X","authenticated-orcid":false,"given":"Yi","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Computer Science and Technology, Zhejiang University, Hangzhou, Zhejiang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Alex","family":"Hauptmann","sequence":"additional","affiliation":[{"name":"School of Computer Science, Carnegie Mellon University, Pittsburgh, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Multi-agent dual learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref2","first-page":"5998","article-title":"Attention is all you need","volume-title":"Proc. Neural Informat. Process. Syst. Conf.","author":"Vaswani"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1026"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1176"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-32-9748-7_4"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/p16-1009"},{"key":"ref8","article-title":"Cross-lingual language model pretraining","author":"Lample","year":"2019"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11976"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1631\/fitee.2100463"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.731"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-020-09250-0"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01086"},{"key":"ref15","article-title":"Keyframe segmentation and positional encoding for video-guided machine translation challenge 2020","author":"Hirasawa","year":"2020"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3115\/1273073.1273138"},{"key":"ref17","first-page":"12","article-title":"Deciphering foreign language","volume-title":"Proc. Annu. Meeting Assoc. Comput. Linguistics","author":"Ravi"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1549"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1399"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1005"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1119"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1297"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1019"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1293"},{"key":"ref25","first-page":"194","article-title":"FFA-IR: Towards an explainable and reliable medical report generation benchmark","volume-title":"Proc. 35th Conf. on Neural Informat. Process. Syst. Datasets Benchmarks Track","author":"Li"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00300"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.747"},{"key":"ref28","article-title":"Cross-lingual language model pretraining","volume-title":"Proc. Adv. Neural Informat. Process. Syst.","author":"Conneau"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref30","first-page":"7057","article-title":"MASS: Masked sequence to sequence pre-training for language generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Song"},{"key":"ref31","first-page":"4171","article-title":"When and why is unsupervised neural machine translation useless?","volume-title":"Proc. Annu. Conf. Eur. Assoc. Mach. Transl.","author":"Kim"},{"key":"ref32","first-page":"5926","article-title":"When does unsupervised machine translation work?","volume-title":"Proc. 5th Conf. Mach. Transl.","author":"Marchisio"},{"issue":"1","key":"ref33","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2346"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00065"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.283"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-017-9197-z"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref39","article-title":"Neural message passing on hybrid spatio-temporal visual and symbolic graphs for video understanding","author":"Mavroudi","year":"2019"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.3301922"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00582"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01088"},{"key":"ref44","article-title":"Classifying collisions with spatio-temporal action graph networks","author":"Herzig","year":"2018"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_25"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01020"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV45572.2020.9093361"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01067"},{"key":"ref49","article-title":"Neural machine translation by jointly learning to align and translate","author":"Bahdanau","year":"2014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/w16-2323"},{"key":"ref51","first-page":"820","article-title":"Dual learning for machine translation","volume-title":"Proc. Neural Informat. Process. Syst. Conf.","author":"He"},{"key":"ref52","article-title":"The concrete distribution: A continuous relaxation of discrete random variables","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Maddison"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref55","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","volume-title":"Proc. Neural Informat. Process. Syst.Workshop","author":"Kiros"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350894"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3323873.3325043"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01065"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-1269"},{"key":"ref63","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref65","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","volume-title":"Text Summarization Branches Out","author":"Lin"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref67","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref68","article-title":"Word translation without parallel data","author":"Conneau","year":"2017"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1042"},{"key":"ref70","article-title":"spaCy 2: Natural language understanding with Bloom embeddings, convolutional neural networks and incremental parsing","author":"Honnibal","year":"2017"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref73","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00957"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10036240\/09792411.pdf?arnumber=9792411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T17:28:43Z","timestamp":1751563723000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9792411\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,3,1]]},"references-count":74,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3181116","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,3,1]]}}}