{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T20:27:54Z","timestamp":1785270474397,"version":"3.55.0"},"reference-count":233,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","funder":[{"DOI":"10.13039\/501100000266","name":"Engineering and Physical Sciences Research Council (EPSRC) Fellowship DEFORM: Large Scale Shape Analysis of Deformable Models of Humans","doi-asserted-by":"publisher","award":["EP\/S010203\/1"],"award-info":[{"award-number":["EP\/S010203\/1"]}],"id":[{"id":"10.13039\/501100000266","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Proc. IEEE"],"published-print":{"date-parts":[[2021,5]]},"DOI":"10.1109\/jproc.2021.3074329","type":"journal-article","created":{"date-parts":[[2021,4,30]],"date-time":"2021-04-30T19:40:35Z","timestamp":1619811635000},"page":"863-890","source":"Crossref","is-referenced-by-count":156,"title":["Tensor Methods in Computer Vision and Deep Learning"],"prefix":"10.1109","volume":"109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0153-5210","authenticated-orcid":false,"given":"Yannis","family":"Panagakis","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4445-3429","authenticated-orcid":false,"given":"Jean","family":"Kossaifi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0650-1856","authenticated-orcid":false,"given":"Grigorios G.","family":"Chrysos","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7000-5179","authenticated-orcid":false,"given":"James","family":"Oldfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9175-477X","authenticated-orcid":false,"given":"Mihalis A.","family":"Nicolaou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anima","family":"Anandkumar","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5222-1740","authenticated-orcid":false,"given":"Stefanos","family":"Zafeiriou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref170","doi-asserted-by":"publisher","DOI":"10.1090\/S0025-5718-1981-0606517-5"},{"key":"ref172","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-22482-4_3"},{"key":"ref171","doi-asserted-by":"publisher","DOI":"10.1137\/140991546"},{"key":"ref174","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref173","first-page":"1","article-title":"Neural machine translation by jointly learning to align and translate","author":"bahdanau","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref176","first-page":"13945","article-title":"TESA: Tensor element self-attention via matricization","author":"babiloni","year":"2020","journal-title":"Proc IEEE\/CVF Conf Comput Vis Pattern Recognit (CVPR)"},{"key":"ref175","article-title":"Multi-head attention: Collaborate instead of concatenate","author":"cordonnier","year":"2020","journal-title":"arXiv 2006 16362"},{"key":"ref178","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00007"},{"key":"ref177","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01163-7"},{"key":"ref168","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3058891"},{"key":"ref169","doi-asserted-by":"publisher","DOI":"10.1002\/j.1538-7305.1967.tb03174.x"},{"key":"ref39","first-page":"119","article-title":"Multi-way analysis with applications in the chemical sciences","volume":"19","author":"smilde","year":"2005","journal-title":"J Chemometrics"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/2915921"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2021.3064182"},{"key":"ref32","first-page":"1","article-title":"Towards deep learning models resistant to adversarial attacks","author":"madry","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref31","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6617"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2013.2297439"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2017.2690524"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/MSP.2014.2298533"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1137\/07070111X"},{"key":"ref181","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-47969-4_30"},{"key":"ref180","first-page":"1","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref185","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2002.1047975"},{"key":"ref184","doi-asserted-by":"publisher","DOI":"10.1068\/p250443"},{"key":"ref183","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2009.08.002"},{"key":"ref182","doi-asserted-by":"publisher","DOI":"10.1109\/AFGR.2002.1004130"},{"key":"ref189","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01208-x"},{"key":"ref188","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.21"},{"key":"ref187","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5539853"},{"key":"ref186","doi-asserted-by":"publisher","DOI":"10.1007\/11527923_41"},{"key":"ref28","first-page":"1","article-title":"Deep multi-task representation learning: A tensor factorisation approach","author":"yang","year":"2017","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00610"},{"key":"ref179","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054469"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2018\/88"},{"key":"ref20","article-title":"Learning functions: When is deep better than shallow","author":"mhaskar","year":"2016","journal-title":"arXiv 1603 00988"},{"key":"ref22","first-page":"1","article-title":"Speeding-up convolutional neural networks using fine-tuned CP-decomposition","author":"lebedev","year":"2015","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref21","first-page":"442","article-title":"Tensorizing neural networks","author":"novikov","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.243"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/BIGCOMP.2017.7881725"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00801"},{"key":"ref25","first-page":"1","article-title":"Tensor regression networks","volume":"21","author":"kossaifi","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/HiPC.2016.031"},{"key":"ref51","author":"springer","year":"2019","journal-title":"cuTENSOR A High-Performance CUDA Library for Tensor Primitives"},{"key":"ref154","doi-asserted-by":"publisher","DOI":"10.1016\/S0045-7906(02)00045-9"},{"key":"ref153","doi-asserted-by":"publisher","DOI":"10.1109\/TSMC.1971.4308320"},{"key":"ref156","doi-asserted-by":"publisher","DOI":"10.1023\/A:1022967523886"},{"key":"ref155","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.1991.155142"},{"key":"ref150","article-title":"Defensive tensorization: Randomized tensor parametrization for robust neural networks","author":"bulat","year":"2020"},{"key":"ref152","article-title":"TensorShield: Tensor-based defense against adversarial attacks on images","author":"entezari","year":"2020","journal-title":"arXiv 2002 10252"},{"key":"ref151","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219910"},{"key":"ref146","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Medical Image Computing and Computer-Assisted Intervention&#x2014;MICCAI"},{"key":"ref147","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58526-6_31"},{"key":"ref148","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":"ref149","first-page":"1058","article-title":"Regularization of neural networks using DropConnect","volume":"28","author":"wan","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref59","author":"nickel","year":"2007","journal-title":"Scikit Tensor"},{"key":"ref58","year":"2019","journal-title":"Tensor Network"},{"key":"ref57","author":"ballester-ripoll","year":"2018","journal-title":"Tntorch&#x2014;Tensor Network Learning With PyTorch"},{"key":"ref56","first-page":"1","article-title":"Tensor train decomposition on TensorFlow (T3F)","volume":"21","author":"novikov","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref55","year":"2020","journal-title":"Tensorly-Torch"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3079856.3080246"},{"key":"ref53","article-title":"MXNet: A flexible and efficient machine learning library for heterogeneous distributed systems","volume":"abs 1512 1274","author":"chen","year":"2015","journal-title":"CoRR"},{"key":"ref52","article-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","author":"abadi","year":"2015"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2008.112"},{"key":"ref167","author":"nikol\u2019skii","year":"2013","journal-title":"Analysis III Spaces of Differentiable Functions"},{"key":"ref166","doi-asserted-by":"publisher","DOI":"10.2307\/3029337"},{"key":"ref165","doi-asserted-by":"publisher","DOI":"10.1137\/130932387"},{"key":"ref164","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2020.11.006"},{"key":"ref163","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00735"},{"key":"ref162","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref161","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.205"},{"key":"ref160","first-page":"1","article-title":"Multiplicative interactions and where to find them","author":"jayakumar","year":"2020","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2881476"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1201\/b16252"},{"key":"ref6","first-page":"2773","article-title":"Tensor decompositions for learning latent variable models","volume":"15","author":"anandkumar","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2165291"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2011.01.004"},{"key":"ref159","article-title":"Highway networks","author":"srivastava","year":"2015","journal-title":"arXiv 1505 00387"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1515\/9781400874668"},{"key":"ref49","first-page":"1237","article-title":"Flexible, high performance convolutional neural networks for image classification","author":"cire?an","year":"2011","journal-title":"Proc Intern Joint Conf Artificial Intel (IJCAI)"},{"key":"ref157","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2010.127"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/1102351.1102451"},{"key":"ref158","first-page":"3359","article-title":"Higher-order factorization machines","volume":"29","author":"blondel","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1002\/cpa.20132"},{"key":"ref45","first-page":"1","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553486"},{"key":"ref47","article-title":"Matrix rank minimization with applications","author":"maryam","year":"2002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1561\/2200000057"},{"key":"ref41","author":"cichocki","year":"2009","journal-title":"Nonnegative Matrix and Tensor Factorizations Applications to Exploratory Multi-Way Data Analysis and Blind Source Separation"},{"key":"ref44","first-page":"1","article-title":"TensorLy: Tensor learning in Python","volume":"20","author":"kossaifi","year":"2019","journal-title":"J Mach Learn Res"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1002\/1099-128X(200005\/06)14:3<105::AID-CEM582>3.0.CO;2-I"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1038\/44565"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/S0893-6080(00)00026-5"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1037\/h0071325"},{"key":"ref70","doi-asserted-by":"crossref","first-page":"559","DOI":"10.1080\/14786440109462720","article-title":"LIII. On lines and planes of closest fit to systems of points in space","volume":"2","author":"pearson","year":"1901","journal-title":"London Edinburgh and Dublin Philosophical Mag and J Sci"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.157"},{"key":"ref77","first-page":"1737","article-title":"Dictionary learning for massive matrix factorization","author":"mensch","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.250598"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1145\/1970392.1970395"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/0196-6774(90)90014-6"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1145\/2512329"},{"key":"ref60","author":"bader","year":"2015","journal-title":"MATLAB Tensor Toolbox Version 2 6"},{"key":"ref62","article-title":"The ITensor software library for tensor network calculations","author":"fishman","year":"2020","journal-title":"arXiv 2007 14822"},{"key":"ref61","author":"vervliet","year":"2016","journal-title":"Tensorlab 3 0"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00319"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2011.184"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2015.2430359"},{"key":"ref66","first-page":"19","article-title":"Online learning for matrix factorization and sparse coding","volume":"11","author":"mairal","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1002\/sapm192761164"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/BF02310791"},{"key":"ref69","first-page":"1","article-title":"Foundations of the PARAFAC procedure: Models and conditions for an &#x2018;explanatory&#x2019; multi-modal factor analysis","volume":"16","author":"harshman","year":"1970"},{"key":"ref197","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.641"},{"key":"ref198","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409067"},{"key":"ref199","doi-asserted-by":"publisher","DOI":"10.1162\/089976600300015349"},{"key":"ref193","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.163"},{"key":"ref194","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.815296"},{"key":"ref195","article-title":"Compositional hierarchical tensor factorization: Representing hierarchical intrinsic and extrinsic causal factors","author":"vasilescu","year":"2019","journal-title":"Proc ACM SIGKDD Conf Knowl Discovery Data Mining (KDD) Workshop Tensor Methods Emerging Data Science Challenges"},{"key":"ref196","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2015.2479456"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1137\/1038003"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1137\/130905010"},{"key":"ref190","doi-asserted-by":"publisher","DOI":"10.1145\/1185657.1185864"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2013.2254477"},{"key":"ref191","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2011.05.006"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.39"},{"key":"ref192","first-page":"iii-613","article-title":"Appearance-based tracking and recognition using the 3D trilinear tensor","volume":"3","author":"shao","year":"2004","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process (ICASSP)"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1088\/0266-5611\/27\/2\/025010"},{"key":"ref90","first-page":"382","volume":"46","author":"huber","year":"2011","journal-title":"Robust Statistics"},{"key":"ref98","first-page":"339","article-title":"Provable models for robust low-rank tensor completion","volume":"11","author":"huang","year":"2015","journal-title":"Pacific J Optim"},{"key":"ref99","article-title":"A new low-rank tensor model for video completion","author":"hu","year":"2015","journal-title":"arXiv 1509 02027"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1137\/S0097539792240406"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15558-1_57"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2018.03.017"},{"key":"ref81","first-page":"1800","article-title":"Scalable Bayesian low-rank decomposition of incomplete multiway tensors","volume":"32","author":"rai","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1137\/S0895479896305696"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/BF02289464"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2392756"},{"key":"ref89","article-title":"Tensor ring decomposition","volume":"abs 1606 5535","author":"zhao","year":"2016","journal-title":"CoRR"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1016\/j.laa.2011.04.019"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1137\/090752286"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1103\/PhysRevB.55.2164"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1007\/s00791-014-0218-7"},{"key":"ref200","first-page":"163","article-title":"Tensor analyzers","volume":"28","author":"tang","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2955134"},{"key":"ref100","first-page":"1763","article-title":"Generalized higher-order orthogonal iteration for tensor decomposition and completion","author":"liu","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref209","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2016.2642828"},{"key":"ref203","doi-asserted-by":"publisher","DOI":"10.1109\/BCC.2007.4430540"},{"key":"ref204","doi-asserted-by":"publisher","DOI":"10.1109\/BCC.2007.4430542"},{"key":"ref201","doi-asserted-by":"publisher","DOI":"10.3390\/s20092578"},{"key":"ref202","first-page":"1","article-title":"Multilinear latent conditioning for generating unseen attribute combinations","author":"georgopoulos","year":"2020","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref207","first-page":"239","article-title":"Expression transfer between photographs through multilinear AAM&#x2019;s","author":"mac\u00eado","year":"2006","journal-title":"Proc Brazilian Symp Comput Graph Image Process"},{"key":"ref208","doi-asserted-by":"publisher","DOI":"10.1145\/3338841"},{"key":"ref205","first-page":"776","article-title":"Multilinear principal component analysis of tensor objects for recognition","volume":"2","author":"lu","year":"2006","journal-title":"Proc IEEE 18th Int Conf Pattern Recognit (ICPR)"},{"key":"ref206","doi-asserted-by":"publisher","DOI":"10.1155\/2009\/713183"},{"key":"ref211","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2019.2904063"},{"key":"ref210","doi-asserted-by":"publisher","DOI":"10.1109\/ISCAS.2005.1466083"},{"key":"ref212","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-662-03978-6"},{"key":"ref213","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2197860"},{"key":"ref214","article-title":"Tensor networks for medical image classification","author":"selvan","year":"2020","journal-title":"arXiv 2004 10076"},{"key":"ref215","doi-asserted-by":"publisher","DOI":"10.1155\/2018\/8651930"},{"key":"ref216","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.14"},{"key":"ref217","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-10-7895-8_21"},{"key":"ref218","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33019151"},{"key":"ref219","doi-asserted-by":"publisher","DOI":"10.3390\/app10030797"},{"key":"ref220","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2611525"},{"key":"ref222","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2012.2187063"},{"key":"ref221","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2897316"},{"key":"ref229","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref228","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","volume":"abs 1704 4861","author":"howard","year":"2017","journal-title":"CoRR"},{"key":"ref227","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2019.8756619"},{"key":"ref226","doi-asserted-by":"publisher","DOI":"10.1137\/1.9781611973440.15"},{"key":"ref225","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2845450"},{"key":"ref224","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2474704"},{"key":"ref223","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2017.2714338"},{"key":"ref127","first-page":"1","article-title":"High-dimensional quantile tensor regression","volume":"21","author":"lu","year":"2020","journal-title":"J Mach Learn Res"},{"key":"ref126","first-page":"627","article-title":"A regression model in TensorPCA subspace for face image super-resolution reconstruction","volume":"3","author":"wu","year":"2006","journal-title":"Proc Int Conf Pattern Recognit (ICPR)"},{"key":"ref125","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.254"},{"key":"ref124","first-page":"1269","article-title":"Multilinear subspace regression: An orthogonal tensor decomposition approach","author":"zhao","year":"2011","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref129","first-page":"1","article-title":"Deep learning and quantum entanglement: Fundamental connections with implications to network design","author":"levine","year":"2018","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref128","first-page":"955","article-title":"Convolutional rectifier networks as generalized tensor decompositions","author":"cohen","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref130","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682231"},{"key":"ref133","article-title":"Beating the perils of non-convexity: Guaranteed training of neural networks using tensor methods","author":"janzamin","year":"2015","journal-title":"arXiv 1506 08473"},{"key":"ref134","article-title":"Tensor regression networks with various low-rank tensor approximations","volume":"abs 1712 9520","author":"cao","year":"2017","journal-title":"CoRR"},{"key":"ref131","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.05.034"},{"key":"ref132","first-page":"1","article-title":"Ultimate tensorization: Compressing convolutional and FC layers alike","author":"garipov","year":"2016","journal-title":"Proc NeurIPS Workshop Learn With Tensors"},{"key":"ref232","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref233","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","volume":"9","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref230","article-title":"Perfect dimensionality recovery by variational Bayesian PCA","volume":"25","author":"nakajima","year":"2012","journal-title":"Advances in neural information processing systems"},{"key":"ref231","first-page":"13714","article-title":"Convolutional tensor-train LSTM for spatio-temporal learning","volume":"33","author":"su","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref136","article-title":"Equivalent polyadic decompositions of matrix multiplication tensors","volume":"abs 1902 3950","author":"berger","year":"2019","journal-title":"CoRR"},{"key":"ref135","doi-asserted-by":"publisher","DOI":"10.1561\/2200000067"},{"key":"ref138","doi-asserted-by":"publisher","DOI":"10.5244\/C.28.88"},{"key":"ref137","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.355"},{"key":"ref139","first-page":"1","article-title":"Compression of deep convolutional neural networks for fast and low power mobile applications","author":"kim","year":"2016","journal-title":"Proc Int Conf Learn Represent (ICLR)"},{"key":"ref140","first-page":"5552","article-title":"Exploring unexplored tensor network decompositions for convolutional neural networks","author":"hayashi","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst (NeurIPS)"},{"key":"ref141","doi-asserted-by":"publisher","DOI":"10.1137\/070690729"},{"key":"ref142","first-page":"504","article-title":"Understanding generalization in deep learning via tensor methods","author":"li","year":"2020","journal-title":"Proc Int Conf Artif Intell Statist (AISTATS)"},{"key":"ref143","first-page":"7413","article-title":"Implicit regularization in deep matrix factorization","volume":"32","author":"arora","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref2","first-page":"3","article-title":"Tensors: Geometry and applications","volume":"381","author":"landsberg","year":"2012","journal-title":"Representation Theory"},{"key":"ref144","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00306"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01409-4"},{"key":"ref145","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref109","doi-asserted-by":"crossref","first-page":"2524","DOI":"10.1109\/TPAMI.2014.2342214","article-title":"Multilinear discriminant analysis for higher-order tensor data classification","volume":"36","author":"li","year":"2014","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2007.1096"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2006.884929"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2036813"},{"key":"ref105","first-page":"249","article-title":"Music genre classification using locality preserving non-negative tensor factorization and sparse representations","author":"panagakis","year":"2009","journal-title":"Proc Int Soc Music Inf Retr (ISMIR)"},{"key":"ref104","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TNN.2007.901277","article-title":"MPCA: Multilinear principal component analysis of tensor objects","volume":"19","author":"lu","year":"2008","journal-title":"IEEE Trans Neural Netw"},{"key":"ref103","author":"bertsekas","year":"1996","journal-title":"Constrained Optimization and Lagrange Multiplier Methods"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053701"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-012-4551-5"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/ISIT.2016.7541479"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/GlobalSIP.2014.7032166"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2783940"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.63"},{"key":"ref12","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":"ref13","first-page":"255","article-title":"Convolutional networks for images, speech, and time series","author":"lecun","year":"1998","journal-title":"The Handbook of Brain Theory and Neural Networks"},{"key":"ref14","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref118","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.2013.776499"},{"key":"ref17","first-page":"1329","article-title":"On the power of over-parametrization in neural networks with quadratic activation","author":"du","year":"2018","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref117","first-page":"1867","article-title":"Low-rank regression with tensor responses","author":"rabusseau","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2854560"},{"key":"ref19","first-page":"402","article-title":"Overfitting in neural nets: Backpropagation, conjugate gradient, and early stopping","author":"caruana","year":"2001","journal-title":"Proc Adv Neural Inf Process Syst (NIPS)"},{"key":"ref119","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23626-6_3"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.363"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.2018.2799931"},{"key":"ref116","article-title":"Global optimality in tensor factorization, deep learning, and beyond","author":"haeffele","year":"2015","journal-title":"arXiv 1506 07540"},{"key":"ref115","first-page":"4108","article-title":"Structured low-rank matrix factorization: Optimality, algorithm, and applications to image processing","volume":"5","author":"haeffele","year":"2014","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref120","first-page":"373","article-title":"Learning from multiway data: Simple and efficient tensor regression","volume":"48","author":"yu","year":"2016","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref121","first-page":"1","article-title":"Multilinear regression for embedded feature selection with application to fMRI analysis","author":"song","year":"2017","journal-title":"Proc AAAI Conf Artif Intell (AAAI)"},{"key":"ref122","first-page":"1444","article-title":"Multilinear multitask learning","volume":"28","author":"romera-paredes","year":"2013","journal-title":"Proc Int Conf Mach Learn (ICML)"},{"key":"ref123","doi-asserted-by":"publisher","DOI":"10.1007\/s12561-018-9215-6"}],"container-title":["Proceedings of the IEEE"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5\/9420072\/09420085.pdf?arnumber=9420085","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,10,6]],"date-time":"2021-10-06T03:06:21Z","timestamp":1633489581000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9420085\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,5]]},"references-count":233,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/jproc.2021.3074329","relation":{},"ISSN":["0018-9219","1558-2256"],"issn-type":[{"value":"0018-9219","type":"print"},{"value":"1558-2256","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,5]]}}}