{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T19:00:32Z","timestamp":1784228432897,"version":"3.55.0"},"reference-count":92,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,9,1]],"date-time":"2020-09-01T00:00:00Z","timestamp":1598918400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"FP7 ERC","award":["#340113"],"award-info":[{"award-number":["#340113"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2020,9,1]]},"DOI":"10.1109\/tpami.2019.2910523","type":"journal-article","created":{"date-parts":[[2020,4,22]],"date-time":"2020-04-22T20:43:32Z","timestamp":1587588212000},"page":"2065-2081","source":"Crossref","is-referenced-by-count":204,"title":["A Comprehensive Analysis of Deep Regression"],"prefix":"10.1109","volume":"42","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6927-8930","authenticated-orcid":false,"given":"Stephane","family":"Lathuiliere","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pablo","family":"Mesejo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5354-1084","authenticated-orcid":false,"given":"Xavier","family":"Alameda-Pineda","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5232-024X","authenticated-orcid":false,"given":"Radu","family":"Horaud","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref73","article-title":"Distribution-free multiple comparisons","author":"nemenyi","year":"1963"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/77.3.663"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.2307\/2531823"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/75.2.383"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2018.8451312"},{"key":"ref77","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref74","author":"conover","year":"1998","journal-title":"Practical Nonparametric Statistics"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.2307\/3001968"},{"key":"ref75","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.154"},{"key":"ref78","article-title":"Layer normalization","author":"ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2017.64"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2016.2582924"},{"key":"ref32","doi-asserted-by":"crossref","first-page":"437","DOI":"10.1007\/978-3-642-35289-8_26","article-title":"Practical recommendations for gradient-based training of deep architectures","author":"bengio","year":"2012","journal-title":"Neural Networks Trade Tricks of the trade"},{"key":"ref31","article-title":"On architectural choices in deep learning: From network structure to gradient convergence and parameter estimation","volume":"abs 1702 8670","author":"ithapu","year":"2017","journal-title":"ArXiv"},{"key":"ref30","first-page":"1097","article-title":"Deep convolutional neural network design patterns","volume":"abs 1611 847","author":"smith","year":"2016","journal-title":"CoRR"},{"key":"ref37","first-page":"4053","article-title":"Convolutional neural fabrics","author":"saxena","year":"2016","journal-title":"Proc 30th Int Conf Neural Inf Process Syst"},{"key":"ref36","first-page":"1","article-title":"Return of the devil in the details: Delving deep into convolutional nets","author":"chatfield","year":"2014","journal-title":"Proc British Mach Vis Conf"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2017.05.007"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.sigpro.2016.05.021"},{"key":"ref60","first-page":"1139","article-title":"On the importance of initialization and momentum in deep learning","volume":"28","author":"sutskever","year":"2013","journal-title":"Proc 30th Int Conf Int Conf Mach Learn"},{"key":"ref62","author":"fisher","year":"1925","journal-title":"Statistical Methods for Research Workers"},{"key":"ref61","article-title":"Keras","author":"chollet","year":"2015"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1038\/506150a"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/72.701181"},{"key":"ref64","article-title":"P-values: Misunderstood and misused","volume":"4","author":"vidgen","year":"2016","journal-title":"Frontiers in Physiology"},{"key":"ref27","first-page":"9","article-title":"Effiicient backprop","author":"lecun","year":"1998","journal-title":"Neural Netw"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1136\/bmj.322.7280.226"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2011.02.002"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1080\/01621459.1961.10482090"},{"key":"ref68","first-page":"65","article-title":"A simple sequentially rejective multiple test procedure","volume":"6","author":"holm","year":"1979","journal-title":"Scandinavian J Statist"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1093\/biomet\/75.4.800"},{"key":"ref2","first-page":"2879","article-title":"Face detection, pose estimation, and landmark localization in the wild","author":"zhu","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995458"},{"key":"ref20","first-page":"202","article-title":"Deepgum: Learning deep robust regression with a gaussian-uniform mixture model","author":"lathuili\u00e8re","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref22","first-page":"229","article-title":"Fashion Landmark Detection in the Wild","author":"liu","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2015.2464702"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.116"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.756"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.134"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0940-3"},{"key":"ref50","first-page":"625","article-title":"Why does unsupervised pre-training help deep learning?","volume":"11","author":"erhan","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref51","first-page":"3320","article-title":"How transferable are features in deep neural networks?","volume":"2","author":"yosinski","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.144"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.299"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.5244\/C.24.12"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"arXiv 1412 6980"},{"key":"ref58","article-title":"Adadelta: an adaptive learning rate method","author":"zeiler","year":"2012","journal-title":"arXiv 1212 5701"},{"key":"ref57","first-page":"26","article-title":"Rrmsprop: Divide the gradient by a running average of its recent magnitude","volume":"4","author":"tieleman","year":"2012","journal-title":"COURSERA Neural Netw Mach Learn"},{"key":"ref56","first-page":"2121","article-title":"Adaptive subgradient methods for online learning and stochastic optimization","volume":"12","author":"duchi","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1142\/S0129065715500124"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/5.784219"},{"key":"ref53","author":"goodfellow","year":"2016","journal-title":"Deep Learning"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TMI.2016.2535302"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23629-7_80"},{"key":"ref11","first-page":"1097","article-title":"ImageNet Classification with Deep Convolutional Neural Networks","author":"krizhevsky","year":"2012","journal-title":"Proc Neural Inf Process Syst"},{"key":"ref40","first-page":"1","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref14","first-page":"44","article-title":"Overfeat: Integrated recognition, localization and detection using convolutional networks","author":"sermanet","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.59"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00224"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532566"},{"key":"ref81","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"newell","year":"2016","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.137"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.324"},{"key":"ref83","first-page":"1799","article-title":"Joint training of a convolutional network and a graphical model for human pose estimation","author":"tompson","year":"2014","journal-title":"Proc 27th Int Conf Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.446"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.143"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247976"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.191"},{"key":"ref6","first-page":"3394","article-title":"Conditional regression forests for human pose estimation","author":"sun","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315258"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.601"},{"key":"ref8","doi-asserted-by":"crossref","first-page":"1178","DOI":"10.1109\/TIP.2008.924280","article-title":"Image-based human age estimation by manifold learning and locally adjusted robust regression","volume":"17","author":"guo","year":"2008","journal-title":"IEEE Trans Image Process"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2654165"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4409050"},{"key":"ref49","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":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206754"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.261"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2013.02.009"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2654165"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2482819"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref47","first-page":"1129","article-title":"Learning to parse images of articulated bodies","author":"ramanan","year":"2007","journal-title":"Proc 19th Int Conf Neural Inf Process Syst"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICIG.2013.133"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-012-0549-0"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9158589\/08686063.pdf?arnumber=8686063","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T14:00:04Z","timestamp":1651068004000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8686063\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,9,1]]},"references-count":92,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2019.2910523","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":[[2020,9,1]]}}}