{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,30]],"date-time":"2026-10-30T00:27:51Z","timestamp":1793320071506,"version":"4.5.0"},"reference-count":204,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2019,10,1]],"date-time":"2019-10-01T00:00:00Z","timestamp":1569888000000},"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":["61702448"],"award-info":[{"award-number":["61702448"]}],"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":["61672456"],"award-info":[{"award-number":["61672456"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2017QNA5008"],"award-info":[{"award-number":["2017QNA5008"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"crossref","award":["2017FZA5007"],"award-info":[{"award-number":["2017FZA5007"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100004835","name":"Zhejiang University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004835","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Knowl. Data Eng."],"published-print":{"date-parts":[[2019,10,1]]},"DOI":"10.1109\/tkde.2018.2872063","type":"journal-article","created":{"date-parts":[[2018,9,24]],"date-time":"2018-09-24T17:40:00Z","timestamp":1537810800000},"page":"1863-1883","source":"Crossref","is-referenced-by-count":547,"title":["A Survey of Multi-View Representation Learning"],"prefix":"10.1109","volume":"31","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6859-9038","authenticated-orcid":false,"given":"Yingming","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhongfei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","first-page":"3104","article-title":"Sequence to sequence learning with neural networks","author":"sutskever","year":"2014","journal-title":"Proc Conf Neural Inf Process Syst"},{"key":"ref172","article-title":"Unifying visual-semantic embeddings with multimodal neural language models","author":"kiros","year":"2014"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1109\/72.279181"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.515"},{"key":"ref173","article-title":"Translating videos to natural language using deep recurrent neural networks","author":"venugopalan","year":"2014"},{"key":"ref176","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2520371"},{"key":"ref175","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.279"},{"key":"ref178","article-title":"Neural machine translation by jointly learning to align and translate","volume":"abs 1409 473","author":"bahdanau","year":"2014"},{"key":"ref177","article-title":"Learning a recurrent visual representation for image caption generation","author":"chen","year":"2014"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.213"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874183"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/1281192.1281244"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/1401890.1401969"},{"key":"ref30","first-page":"2121","article-title":"Devise: A deep visual-semantic embedding model","author":"frome","year":"2013","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2014.2339736"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1181"},{"key":"ref35","first-page":"1097","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc 25th Int Conf Neural Inf Process Syst"},{"key":"ref34","first-page":"306","article-title":"Consistent collective matrix completion under joint low rank structure","author":"gunasekar","year":"2015","journal-title":"Proc Conf Artif Intell Statist"},{"key":"ref181","article-title":"Show, attend and tell: Neural image caption generation with visual attention","volume":"abs 1502 3044","author":"xu","year":"2015"},{"key":"ref180","article-title":"Recurrent models of visual attention","volume":"abs 1406 6247","author":"mnih","year":"2014"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2016.2519449"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806240"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2480340"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1613\/jair.3994"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1005"},{"key":"ref188","first-page":"4378","article-title":"Imagined visual representations as multimodal embeddings","author":"collell","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1613\/jair.4135"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2507401"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/279943.279962"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2460697"},{"key":"ref179","article-title":"Multiple object recognition with visual attention","volume":"abs 1412 7755","author":"ba","year":"2014"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/957142.957143"},{"key":"ref20","first-page":"1083","article-title":"On deep multi-view representation learning","author":"wang","year":"2015","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref22","article-title":"Deep captioning with multimodal recurrent neural networks (m-RNN)","author":"mao","year":"2014"},{"key":"ref21","article-title":"Deep visual-semantic alignments for generating image descriptions","volume":"abs 1412 2306","author":"karpathy","year":"2014"},{"key":"ref24","doi-asserted-by":"crossref","DOI":"10.1145\/1456650.1456651","article-title":"Data fusion","volume":"41","author":"bleiholder","year":"2009","journal-title":"ACM Comput Surv"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298878"},{"key":"ref26","article-title":"A survey on multi-view learning","author":"xu","year":"2013"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-010-0182-0"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-72927-3_8"},{"key":"ref51","first-page":"440","article-title":"Correlated random features for fast semi-supervised learning","author":"mcwilliams","year":"2013","journal-title":"Proc 20th Int Conf Neural Inf Process Syst"},{"key":"ref154","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/5236.001.0001","author":"rumelhart","year":"1986","journal-title":"Parallel Distributed Processing Explorations in the Microstructure of Cognition Vol 1 Foundations"},{"key":"ref153","first-page":"505","article-title":"Distance metric learning with application to clustering with side-information","author":"xing","year":"2002","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639140"},{"key":"ref155","first-page":"1607","article-title":"Replicated softmax: An undirected topic model","author":"hinton","year":"2009","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref150","first-page":"1481","article-title":"Exponential family harmoniums with an application to information retrieval","author":"welling","year":"2004","journal-title":"Proc 17th Int Conf Neural Inf Process Syst"},{"key":"ref152","first-page":"1806","article-title":"Multi-modal distance metric learning","author":"xie","year":"2013","journal-title":"Proc 23rd Int Joint Conf Artif Intell"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1162\/089976602760128018"},{"key":"ref146","doi-asserted-by":"crossref","first-page":"1485","DOI":"10.1109\/TCSVT.2012.2202075","article-title":"Sparse unsupervised dimensionality reduction for multiple view data","volume":"22","author":"han","year":"2012","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2014.2311377"},{"key":"ref148","first-page":"1070","article-title":"Supervised coupled dictionary learning with group structures for multi-modal retrieval","author":"zhuang","year":"2013","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref149","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2291214"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.2307\/2334380"},{"key":"ref58","article-title":"The canonical correlations of matrix pairs and their numerical computation","author":"golub","year":"1992"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2169972"},{"key":"ref56","first-page":"873","article-title":"Multi-label output codes using canonical correlation analysis","author":"zhang","year":"2011","journal-title":"Proc 14th Int Conf Artificial Intell"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1037"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-013-0658-4"},{"key":"ref53","article-title":"Two Step CCA: A new spectral method for estimating vector models of words","author":"dhillon","year":"2012","journal-title":"Proc 29th Int Conf Mach Learn"},{"key":"ref52","first-page":"199","article-title":"Multi-view learning of word embeddings via CCA","author":"dhillon","year":"2011","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.148"},{"key":"ref167","article-title":"Recurrent neural network based language model","volume":"2","author":"mikolov","year":"2010","journal-title":"Proc Annu Conf Int Speech Commun Assoc"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.144"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00526"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299016"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.114"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.285"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/P14-1068"},{"key":"ref160","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2016.XII.041"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-013-1362-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1162\/0899766042321814"},{"key":"ref6","article-title":"Deep boltzmann machines","volume":"1","author":"salakhutdinov","year":"2009","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref8","first-page":"1247","article-title":"Deep canonical correlation analysis","author":"andrew","year":"2013","journal-title":"Mach Learn Res"},{"key":"ref159","doi-asserted-by":"crossref","first-page":"619","DOI":"10.1145\/2671188.2749400","article-title":"Mutlimodal learning with deep boltzmann machine for emotion prediction in user generated videos","author":"pang","year":"2015","journal-title":"Proc 5th ACM Int Conf Multimedia Retrieval"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553391"},{"key":"ref157","first-page":"843","article-title":"Multimodal DBN for predicting high-quality answers in CQA portals","author":"hu","year":"2013","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref9","first-page":"430","article-title":"The missing link - A probabilistic model of document content and hypertext connectivity","author":"cohn","year":"2000","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref158","doi-asserted-by":"publisher","DOI":"10.1145\/2487575.2487612"},{"key":"ref46","first-page":"347","article-title":"Efficient dimensionality reduction for canonical correlation analysis","volume":"28","author":"avron","year":"2013","journal-title":"Proc 30th Int Conf Mach Learn"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1835804.1835846"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2008.4587353"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611972757.39"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1873987"},{"key":"ref44","article-title":"Multi-view dimensionality reduction via canonical correlation analysis","author":"foster","year":"2008"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390285"},{"key":"ref73","first-page":"199","article-title":"Structured sparse canonical correlation analysis","author":"chen","year":"2012","journal-title":"Proc Conf Artif Intell Statist"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1093\/biostatistics\/kxp008"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1145\/1273496.1273519"},{"key":"ref70","article-title":"A greedy approach to sparse canonical correlation analysis","author":"wiesel","year":"2008"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540112"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-011-0494-3"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1142\/S012906570000034X"},{"key":"ref75","article-title":"A kernel method for canonical correlation analysis","author":"akaho","year":"2001","journal-title":"Proc Int Meeting Psychometric Soc"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1093\/bioinformatics\/btg1045"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2011.02.011"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1137\/130919222"},{"key":"ref62","first-page":"91","article-title":"large scale canonical correlation analysis with iterative least squares","author":"lu","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref61","article-title":"Improved analysis of the subsampled randomized hadamard transform","volume":"abs 1011 1595","author":"tropp","year":"2010"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1111\/j.2517-6161.1996.tb02080.x"},{"key":"ref64","article-title":"Sparse canonical correlation analysis","author":"hardoon","year":"2007"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.2202\/1544-6115.1329"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1214\/009053604000000067"},{"key":"ref67","first-page":"2399","article-title":"Manifold regularization: A geometric framework for learning from labeled and unlabeled examples","volume":"7","author":"belkin","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1137\/050645506"},{"key":"ref69","article-title":"Finding musically meaningful words by sparse CCA","author":"torres","year":"2007","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.337"},{"key":"ref198","first-page":"1764","article-title":"Towards end-to-end speech recognition with recurrent neural networks","author":"graves","year":"2014","journal-title":"Proc 31st Int Conf Int Conf Mach Learn"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref193","article-title":"A neural conversational model","author":"vinyals","year":"2015"},{"key":"ref194","first-page":"3776","article-title":"Building end-to-end dialogue systems using generative hierarchical neural network models","volume":"16","author":"serban","year":"2016","journal-title":"Proc 13th AAAI Conf Artif Intell"},{"key":"ref195","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299101"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.293"},{"key":"ref95","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1038\/355161a0","article-title":"Self-organizing neural network that discovers surfaces in random-dot stereograms","volume":"355","author":"becker","year":"1992","journal-title":"Nature"},{"key":"ref94","article-title":"Large-scale approximate kernel canonical correlation analysis","volume":"abs 1511 4773","author":"wang","year":"2015","journal-title":"CoRR"},{"key":"ref190","first-page":"1146","article-title":"A multimodal lda model integrating textual, cognitive and visual modalities","author":"roller","year":"2013","journal-title":"Proc Conf Empirical Methods Natural Language Process"},{"key":"ref93","first-page":"1359","article-title":"Randomized nonlinear component analysis","author":"lopez-paz","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1044"},{"key":"ref92","first-page":"244","article-title":"Fastfood - computing hilbert space expansions in loglinear time","author":"le","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref192","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P16-1154"},{"key":"ref91","first-page":"485","article-title":"Nyström method versus random fourier features: A theoretical and empirical comparison","author":"yang","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref90","first-page":"682","article-title":"Using the nyström method to speed up kernel machines","author":"williams","year":"2000","journal-title":"Proc 13th Int Conf Neural Inf Process Syst"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(99)00075-1"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00067-8"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1080\/0954898X.1996.11978653"},{"key":"ref97","first-page":"363","article-title":"Canonical correlation analysis using artificial neural networks","author":"lai","year":"1998","journal-title":"Proc Eur Symp Artif Neural Netw"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6639047"},{"key":"ref81","first-page":"34","article-title":"Kernel CCA for multi-view learning of acoustic features using articulatory measurements","author":"arora","year":"2012","journal-title":"Proc Symp Mach Learning Speech Lang Process"},{"key":"ref84","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/4175.001.0001","author":"sch\u00f6lkopf","year":"2001","journal-title":"Learning With Kernels Support Vector Machines Regularization Optimization and Beyond"},{"key":"ref83","first-page":"2075","article-title":"Kernel methods for measuring independence","volume":"6","author":"gretton","year":"2005","journal-title":"J Mach Learn Res"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1145\/1871985.1871989"},{"key":"ref89","first-page":"707","article-title":"Incremental singular value decomposition of uncertain data with missing values","author":"brand","year":"2002","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref85","article-title":"The geometry of kernel canonical correlation analysis","author":"kuss","year":"2003"},{"key":"ref86","first-page":"361","article-title":"Statistical consistency of kernel canonical correlation analysis","volume":"8","author":"fukumizu","year":"2007","journal-title":"J Mach Learn Res"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-008-5085-3"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s11425-011-4245-2"},{"key":"ref200","doi-asserted-by":"publisher","DOI":"10.1145\/2964284.2984066"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1028"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2015.7178840"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1145\/2783258.2783273"},{"key":"ref204","first-page":"1309","article-title":"A hybrid collaborative filtering model with deep structure for recommender systems","author":"dong","year":"2017","journal-title":"Proc 31st AAAI Conf Artif Intell"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.1145\/2020408.2020480"},{"key":"ref202","article-title":"Collaborative topic regression with social matrix factorization for recommendation systems","author":"purushotham","year":"2012"},{"key":"ref127","doi-asserted-by":"publisher","DOI":"10.1006\/jcss.1997.1504"},{"key":"ref126","article-title":"Learning task-specific similarity","author":"shakhnarovich","year":"2005"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2015.2392052"},{"key":"ref124","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502107"},{"key":"ref129","first-page":"1753","article-title":"Spectral hashing","author":"weiss","year":"2008","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref128","doi-asserted-by":"publisher","DOI":"10.1145\/2600428.2609563"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995432"},{"key":"ref133","doi-asserted-by":"publisher","DOI":"10.1145\/2736277.2741667"},{"key":"ref134","article-title":"Word2visualvec: Cross-media retrieval by visual feature prediction","author":"dong","year":"2016"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1145\/2463676.2465274"},{"key":"ref132","first-page":"2333","article-title":"Learning deep structured semantic models for web search using clickthrough data","author":"huang","year":"2013","journal-title":"Proc ACM Int Conf Inf Knowl Manag"},{"key":"ref136","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/N15-1016"},{"key":"ref135","first-page":"595","article-title":"Multimodal neural language models","volume":"14","author":"kiros","year":"2014","journal-title":"Proc 31st Int Conf Mach Learn"},{"key":"ref138","first-page":"1223","article-title":"Large scale distributed deep networks","author":"dean","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref137","article-title":"Efficient estimation of word representations in vector space","author":"mikolov","year":"2013"},{"key":"ref139","article-title":"Zero-shot learning by convex combination of semantic embeddings","author":"norouzi","year":"2013"},{"key":"ref140","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298754"},{"key":"ref141","first-page":"2346","article-title":"Jointly modeling deep video and compositional text to bridge vision and language in a unified framework","author":"xu","year":"2015","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref142","first-page":"993","article-title":"Latent dirichlet allocation","volume":"3","author":"blei","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref143","first-page":"1903","article-title":"Simultaneous image classification and annotation","author":"wang","year":"2009","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref2","first-page":"1","article-title":"Kernel independent component analysis","volume":"3","author":"bach","year":"2002","journal-title":"J Mach Learn Res"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408965"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.2307\/2333955"},{"key":"ref145","author":"bishop","year":"2006","journal-title":"Pattern Recognition and Machine Learning"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/Allerton.2012.6483308"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1002\/cem.785"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1016\/S0169-7439(01)00155-1"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2009.5459205"},{"key":"ref105","first-page":"34","author":"rosipal","year":"2006","journal-title":"Overview and recent advances in partial least squares"},{"key":"ref104","first-page":"589","article-title":"Soft modeling: the basic design and some extensions","volume":"2","author":"wold","year":"1982","journal-title":"Systems under Indirect Observation"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298966"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ALLERTON.2015.7447071"},{"key":"ref111","first-page":"3","article-title":"Kernel cross-modal factor analysis for information fusion with application to bimodal emotion recognition","volume":"14","author":"wang","year":"2012","journal-title":"IEEE Trans Multimedia"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.142"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2013.6553737"},{"key":"ref10","first-page":"1107","article-title":"Matching words and pictures","volume":"3","author":"barnard","year":"2003","journal-title":"J Mach Learn Res"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/860458.860460"},{"key":"ref12","first-page":"982","article-title":"Factorized latent spaces with structured sparsity","author":"jia","year":"2010","journal-title":"Proc Advances in Neural Inf Process Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-40811-3_33"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.03.007"},{"key":"ref15","first-page":"633","article-title":"Mining associated text and images with dual-wing harmoniums","author":"xing","year":"2005","journal-title":"Proc 21st Conf Uncertainty Artif Intell"},{"key":"ref16","first-page":"361","article-title":"Predictive subspace learning for multi-view data: A large margin approach","author":"chen","year":"2010","journal-title":"Proc 23rd Int Conf Neural Inf Process Syst"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102363"},{"key":"ref17","first-page":"2231","article-title":"Multimodal learning with deep boltzmann machines","author":"srivastava","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref117","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/1113.003.0010","article-title":"Large margin rank boundaries for ordinal regression","author":"herbrich","year":"2000","journal-title":"Advances in Large Margin Classifiers"},{"key":"ref18","first-page":"689","article-title":"Multimodal deep learning","author":"ngiam","year":"2011","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654902"},{"key":"ref119","first-page":"263","article-title":"New ranking algorithms for parsing and tagging: Kernels over discrete structures, and the voted perceptron","author":"collins","year":"2002","journal-title":"Proc Annual Meeting of the Assoc Computational Linguistics"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1007\/s10791-009-9117-9"},{"key":"ref113","article-title":"Supervised cross-modal factor analysis","volume":"abs 1502 5134","author":"wang","year":"2015"},{"key":"ref116","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.70791"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1007\/s10994-010-5198-3"},{"key":"ref120","doi-asserted-by":"publisher","DOI":"10.1145\/1015330.1015415"},{"key":"ref121","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"ref122","first-page":"1360","article-title":"Learning hash functions for cross-view similarity search","author":"kumar","year":"2011","journal-title":"Proc 20nd Int Joint Conf Artif Intell"},{"key":"ref123","first-page":"1385","article-title":"Co-regularized hashing for multimodal data","author":"zhen","year":"2012","journal-title":"Proc Advances Neural Inf Process Syst"}],"container-title":["IEEE Transactions on Knowledge and Data Engineering"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/69\/8832290\/08471216.pdf?arnumber=8471216","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,10]],"date-time":"2024-07-10T14:22:48Z","timestamp":1720621368000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8471216\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2019,10,1]]},"references-count":204,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tkde.2018.2872063","relation":{},"ISSN":["1041-4347","1558-2191","2326-3865"],"issn-type":[{"value":"1041-4347","type":"print"},{"value":"1558-2191","type":"electronic"},{"value":"2326-3865","type":"electronic"}],"subject":[],"published":{"date-parts":[[2019,10,1]]}}}