{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,20]],"date-time":"2026-03-20T15:54:02Z","timestamp":1774022042000,"version":"3.50.1"},"reference-count":81,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,3,1]],"date-time":"2020-03-01T00:00:00Z","timestamp":1583020800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"NSF BIGDATA","award":["IIS-1546482"],"award-info":[{"award-number":["IIS-1546482"]}]},{"name":"NSF CRCNS","award":["IIS-1822575"],"award-info":[{"award-number":["IIS-1822575"]}]},{"name":"NSF CAREER","award":["IIS-1943251"],"award-info":[{"award-number":["IIS-1943251"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Signal Process."],"published-print":{"date-parts":[[2020,3]]},"DOI":"10.1109\/jstsp.2020.2998415","type":"journal-article","created":{"date-parts":[[2020,5,28]],"date-time":"2020-05-28T20:45:16Z","timestamp":1590698716000},"page":"577-591","source":"Crossref","is-referenced-by-count":2,"title":["Grounded Sequence to Sequence Transduction"],"prefix":"10.1109","volume":"14","author":[{"given":"Lucia","family":"Specia","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0634-6147","authenticated-orcid":false,"given":"Loic","family":"Barrault","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5992-3470","authenticated-orcid":false,"given":"Ozan","family":"Caglayan","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9340-958X","authenticated-orcid":false,"given":"Amanda","family":"Duarte","sequence":"additional","affiliation":[]},{"given":"Desmond","family":"Elliott","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2725-4476","authenticated-orcid":false,"given":"Spandana","family":"Gella","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0844-1391","authenticated-orcid":false,"given":"Nils","family":"Holzenberger","sequence":"additional","affiliation":[]},{"given":"Chiraag","family":"Lala","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8980-8270","authenticated-orcid":false,"given":"Sun Jae","family":"Lee","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7717-4090","authenticated-orcid":false,"given":"Jindrich","family":"Libovicky","sequence":"additional","affiliation":[]},{"given":"Pranava","family":"Madhyastha","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6663-8600","authenticated-orcid":false,"given":"Florian","family":"Metze","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2063-2377","authenticated-orcid":false,"given":"Karl","family":"Mulligan","sequence":"additional","affiliation":[]},{"given":"Alissa","family":"Ostapenko","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8637-1897","authenticated-orcid":false,"given":"Shruti","family":"Palaskar","sequence":"additional","affiliation":[]},{"given":"Ramon","family":"Sanabria","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0048-3893","authenticated-orcid":false,"given":"Josiah","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Raman","family":"Arora","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1047"},{"key":"ref72","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"0","journal-title":"Int Conf Mach Learn"},{"key":"ref71","doi-asserted-by":"crossref","first-page":"504","DOI":"10.1126\/science.1127647","article-title":"Reducing the dimensionality of data with neural networks","volume":"313","author":"hinton","year":"2006","journal-title":"Sci"},{"key":"ref70","first-page":"4171","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"0","journal-title":"2019 Conf North Amer Chapter Assoc Comput Linguistics Human Language Technologies Vol 1 (Long and Short Papers)"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1002\/1097-4679(196110)17:4<331::AID-JCLP2270170402>3.0.CO;2-D"},{"key":"ref77","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"0","journal-title":"ICML"},{"key":"ref74","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"0","journal-title":"Proc 28th ICML"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W18-6402"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639047"},{"key":"ref38","article-title":"Findings of the second shared task on multimodal machine translation and multilingual image description","author":"elliott","year":"2018","journal-title":"Proc 2nd Conf Mach Transl"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4301"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1058"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref32","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"0","journal-title":"3rd ICLR 2015 USA Conf Track Proc"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1515\/pralin-2017-0035"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2346"},{"key":"ref36","article-title":"Lip reading in the wild","author":"chung","year":"2016","journal-title":"Asian Conf Computer Vision"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/E17-3017"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472621"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/K16-1028"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.3115\/1218955.1219032"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1099"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-3348"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1105"},{"key":"ref64","first-page":"3381","article-title":"Highres: Highlight-based reference-less evaluation of summarization","author":"narayan","year":"0","journal-title":"57th Conf Assoc Comput Linguistics"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2587640"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1065"},{"key":"ref66","article-title":"CMU sinbads submission for the dstc7 AVSD challenge","author":"sanabria","year":"2019","journal-title":"7th Dialog Syst Technol Challenges Workshop AAAI"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W17-4746"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1659"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_31"},{"key":"ref69","doi-asserted-by":"crossref","first-page":"436","DOI":"10.1038\/nature14539","article-title":"Deep learning","volume":"521","author":"lecun","year":"2015","journal-title":"Nature"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1037\/0012-1649.43.2.479"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref20","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref22","article-title":"The kinetics human action video dataset","author":"kay","year":"2017","journal-title":"CoRR"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00685"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.495"},{"key":"ref25","first-page":"1","article-title":"Places: A 10 million image database for scene recognition","volume":"99","author":"zhou","year":"2017","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref50","article-title":"BLEU: A method for automatic evaluation of machine translation","author":"papineni","year":"2002","journal-title":"ACL"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3115\/1626355.1626389"},{"key":"ref59","article-title":"Pointing the unknown words","author":"g\u00fcl\u00e7ehre","year":"2016","journal-title":"54th Annu Meet Assoc Comput Linguist ACL 2016 - Long Pap"},{"key":"ref58","first-page":"2692","article-title":"Pointer networks","author":"vinyals","year":"2015","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref57","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Adv Neural Inf Process Syst"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2324"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404790"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2015.7404842"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00476"},{"key":"ref52","first-page":"3810","article-title":"Multimodal lexical translation","author":"lala","year":"0","journal-title":"Proc Lang Resources Eval Conf"},{"key":"ref10","first-page":"130","article-title":"Imagination improves multimodal translation","author":"elliott","year":"0","journal-title":"Proc Eighth Int Joint Conf Natural Lang Process"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1303"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"402","DOI":"10.18653\/v1\/K18-1039","article-title":"Lessons learned in multilingual grounded language learning","author":"k\u00e1d\u00e1r","year":"2018","journal-title":"22nd Conf Comput Natural Lang Learn"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-412"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462439"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682750"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00272"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-3210"},{"key":"ref18","year":"2018"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.3115\/1118108.1118117"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683540"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4900"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/S1364-6613(02)00029-3"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref8","article-title":"Multimodal attention for neural machine translation","author":"caglayan","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00051"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-2031"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2017.8268971"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W16-2209"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/W14-4012"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.303"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-8620"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_49"},{"key":"ref43","first-page":"289","article-title":"Hierarchical question-image co-attention for visual question answering","author":"lu","year":"0","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"}],"container-title":["IEEE Journal of Selected Topics in Signal Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4200690\/9126272\/09103248.pdf?arnumber=9103248","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T17:08:26Z","timestamp":1651079306000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9103248\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,3]]},"references-count":81,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/jstsp.2020.2998415","relation":{},"ISSN":["1932-4553","1941-0484"],"issn-type":[{"value":"1932-4553","type":"print"},{"value":"1941-0484","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,3]]}}}