{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T18:29:46Z","timestamp":1790879386211,"version":"4.1.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T00:00:00Z","timestamp":1669852800000},"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":["62176008"],"award-info":[{"award-number":["62176008"]}],"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":["62176002"],"award-info":[{"award-number":["62176002"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Beijing Academy of Artificial Intelligence"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022,12,1]]},"DOI":"10.1109\/tpami.2021.3132229","type":"journal-article","created":{"date-parts":[[2021,12,2]],"date-time":"2021-12-02T20:27:21Z","timestamp":1638476841000},"page":"9255-9268","source":"Crossref","is-referenced-by-count":22,"title":["Aligning Source Visual and Target Language Domains for Unpaired Video Captioning"],"prefix":"10.1109","volume":"44","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7715-5228","authenticated-orcid":false,"given":"Fenglin","family":"Liu","sequence":"first","affiliation":[{"name":"ADSPLAB, School of ECE, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1118-9710","authenticated-orcid":false,"given":"Xian","family":"Wu","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8365-7822","authenticated-orcid":false,"given":"Chenyu","family":"You","sequence":"additional","affiliation":[{"name":"Department of Electrical Engineering, Yale University, New Haven, CT, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8992-1006","authenticated-orcid":false,"given":"Shen","family":"Ge","sequence":"additional","affiliation":[{"name":"Tencent, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9999-6140","authenticated-orcid":false,"given":"Yuexian","family":"Zou","sequence":"additional","affiliation":[{"name":"ADSPLAB, School of ECE, Peking University, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8241-9320","authenticated-orcid":false,"given":"Xu","family":"Sun","sequence":"additional","affiliation":[{"name":"MOE Key Laboratory of Computational Linguistics School of EECS, Peking University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10804"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0636-x"},{"key":"ref76","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"chen","year":"2015"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N19-4009"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.29"},{"key":"ref75","article-title":"Pay less attention with lightweight and dynamic convolutions","author":"wu","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","first-page":"318","article-title":"Using context vectors in improving a machine translation system with bridge language","author":"zahabi","year":"2013","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref78","first-page":"74","article-title":"ROUGE: A package for automatic evaluation of summaries","author":"lin","year":"2004","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref79","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","author":"banerjee","year":"2005","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1082"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2017.7510508"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-110"},{"key":"ref30","article-title":"Towards data distillation for end-to-end spoken conversational question answering","author":"you","year":"2020"},{"key":"ref37","first-page":"484","article-title":"A comparison of pivot methods for phrase-based statistical machine translation","author":"utiyama","year":"2007","journal-title":"Proc Conf North Amer Chapter Assoc Comput Linguistics Hum Lang Technol"},{"key":"ref36","article-title":"Momentum contrastive voxel-wise representation learning for semi-supervised volumetric medical image segmentation","author":"you","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ISBI.2017.7950555"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2018.07.010"},{"key":"ref60","article-title":"Layer normalization","author":"ba","year":"2016"},{"key":"ref62","first-page":"1112","article-title":"Hierarchical LSTMs with adaptive attention for visual captioning","volume":"42","author":"gao","year":"2020","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.450"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_22"},{"key":"ref28","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2920899"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00273"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2924576"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.497"},{"key":"ref67","article-title":"Google's neural machine translation system: Bridging the gap between human and machine translation","author":"wu","year":"2016"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.121"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.347"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00854"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01277"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018167"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33018191"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref26","first-page":"6000","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853821"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12342"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref58","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":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref56","first-page":"6847","article-title":"Aligning visual regions and textual concepts for semantic-grounded image representations","author":"liu","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref55","first-page":"2048","article-title":"Show, attend and tell: Neural image caption generation with visual attention","author":"xu","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21236\/ADA164453"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00468"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.83"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-65"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414999"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2913499"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/s10590-008-9041-6"},{"key":"ref13","first-page":"1171","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","author":"bengio","year":"2015","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.111"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref16","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref81","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref17","first-page":"2242","article-title":"Unpaired image-to-image translation using cycle-consistent adversarial networks","author":"zhu","year":"2017","journal-title":"Proc IEEE Int Conf Comput Vis"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940007"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.337"},{"key":"ref83","first-page":"6077","article-title":"Bottom-up and top-down attention for image captioning and VQA","author":"anderson","year":"2018","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123448"},{"key":"ref80","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"Proc 32nd Ann Meeting Assoc for Computational Linguistics"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1173"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2818048.2820013"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16421"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01311"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00256"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i3.16353"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-876"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00751"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00425"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3042192"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350996"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123366"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_31"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9940446\/09633156.pdf?arnumber=9633156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,5]],"date-time":"2022-12-05T22:37:57Z","timestamp":1670279877000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9633156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,12,1]]},"references-count":87,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2021.3132229","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":[[2022,12,1]]}}}