{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,30]],"date-time":"2026-09-30T17:58:08Z","timestamp":1790791088671,"version":"4.1.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"11","license":[{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2018,11,1]],"date-time":"2018-11-01T00:00:00Z","timestamp":1541030400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Basic Research Program (973 Program) of China","award":["2013CB329403"],"award-info":[{"award-number":["2013CB329403"]}]},{"name":"NSF","award":["61620106010"],"award-info":[{"award-number":["61620106010"]}]},{"name":"NSF","award":["61621136008"],"award-info":[{"award-number":["61621136008"]}]},{"name":"NSF","award":["61332007"],"award-info":[{"award-number":["61332007"]}]},{"name":"Youth Top-notch Talent Support Program"},{"name":"Tsinghua Tiangong Institute for Intelligent Computing and the NVIDIA NVAIL Program"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2018,11,1]]},"DOI":"10.1109\/tpami.2017.2766142","type":"journal-article","created":{"date-parts":[[2017,10,24]],"date-time":"2017-10-24T18:21:17Z","timestamp":1508869277000},"page":"2762-2775","source":"Crossref","is-referenced-by-count":35,"title":["Max-Margin Deep Generative Models for (Semi-)Supervised Learning"],"prefix":"10.1109","volume":"40","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0912-9076","authenticated-orcid":false,"given":"Chongxuan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6254-2388","authenticated-orcid":false,"given":"Jun","family":"Zhu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"Reading digits in natural images with unsupervised feature learning","author":"netzer","year":"2011","journal-title":"Proc Int Conf Adv Neural Inf Process Syst Workshop Deep Learn Unsupervised Feature Learn"},{"key":"ref33","first-page":"1445","article-title":"Auxiliary\n deep generative models","author":"maal\u00f8e","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","article-title":"Statistical analysis with missing data","volume":"539","author":"little","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref31","article-title":"Network in network","author":"lin","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref30","first-page":"1718","article-title":"Generative moment matching\n networks","author":"li","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref37","first-page":"ii-1791","article-title":"Neural variational inference and learning in belief networks","author":"mnih","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref36","article-title":"Distributional smoothing with virtual adversarial training","volume":"1050","author":"miyato","year":"2015","journal-title":"Machine Learning and Statistics"},{"key":"ref35","first-page":"779","article-title":"Max-margin min-entropy models","author":"miller","year":"2012","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref34","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"matten","year":"2008","journal-title":"J Mach Learn Res"},{"key":"ref60","first-page":"2237","article-title":"MedLDA: Maximum margin\n supervised topic models","volume":"13","author":"zhu","year":"2012","journal-title":"J Mach Learn Res"},{"key":"ref62","first-page":"1799","article-title":"Bayesian inference with\n posterior regularization and applications to infinite latent SVMs","volume":"15","author":"zhu","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref61","first-page":"1073","article-title":"Gibbs max-margin topic models with data augmentation","volume":"15","author":"zhu","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref63","first-page":"1977","article-title":"Partially observed maximum\n entropy discrimination Markov networks","author":"zhu","year":"2008","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref28","first-page":"1837","article-title":"Max-margin deep generative models","author":"li","year":"2015","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref64","article-title":"Improved Bayesian logistic\n supervised topic models with data augmentation","author":"zhu","year":"2013","journal-title":"The Anterior Cruciate Ligament"},{"key":"ref27","article-title":"Convolutional deep belief networks for scalable\n unsupervised learning of hierarchical representations","author":"lee","year":"2009","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.2200\/S00196ED1V01Y200906AIM006"},{"key":"ref29","first-page":"177","article-title":"Learning to generate with\n memory","author":"li","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref2","first-page":"ii-226","article-title":"Deep generative stochastic networks\n trainable by backprop","author":"bengio","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref1","first-page":"1","article-title":"Hidden Markov support vector machines","author":"altun","year":"2003","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2014","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","first-page":"3581","article-title":"Semi-supervised learning with deep\n generative models","author":"kingma","year":"2014","journal-title":"Proc 27th Int Conf Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref23","first-page":"29","article-title":"The neural autoregressive distribution estimator","author":"larochelle","year":"2011","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref26","first-page":"562","article-title":"Deeply-supervised nets","author":"lee","year":"2015","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref25","first-page":"97","article-title":"Learning\n methods for generic object recognition with invariance to pose and lighting","author":"lecun","year":"2004","journal-title":"Proc IEEE Comp Soc Conf Comput Vis Pattern Recognit"},{"key":"ref50","first-page":"1929","article-title":"Dropout: A simple way to prevent neural networks from\n overfitting","volume":"15","author":"srivastava","year":"2014","journal-title":"J Mach Learn Res"},{"key":"ref51","article-title":"Deep learning using linear support vector machines","author":"tang","year":"2013","journal-title":"Proc Int Conf Mach Learn Challenges Represent Learn Workshop"},{"key":"ref59","article-title":"Stochastic pooling for regularization of deep convolutional neural networks","author":"zeiler","year":"2013","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/1553374.1553523"},{"key":"ref57","article-title":"On the quantitative analysis of decoder-based\n generative models","author":"wu","year":"2016","journal-title":"International Conference on Learning Representations"},{"key":"ref56","first-page":"3371","article-title":"Stacked denoising autoencoders: Learning useful representations in\n a deep network with a local denoising criterion","volume":"11","author":"vincent","year":"2010","journal-title":"J Mach Learn Res"},{"key":"ref55","author":"vapnik","year":"1998","journal-title":"Statistical Learning Theory"},{"key":"ref54","article-title":"Support vector machine learning for\n interdependent and structured output spaces","author":"tsochantaridis","year":"2004","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","article-title":"Theano: A Python framework for fast\n computation of mathematical expressions","author":"al-rfou","year":"2016"},{"key":"ref52","first-page":"25","article-title":"Max-margin\n Markov networks","author":"taskar","year":"2003","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298761"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2017.2688499"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995710"},{"key":"ref12","first-page":"258","article-title":"Training generative neural networks via maximum mean discrepancy optimization","author":"dziugaite","year":"2015","journal-title":"Proc Conf Uncertainty of Artificial Intelligence"},{"key":"ref13","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref14","first-page":"1319","article-title":"Maxout networks","author":"goodfellow","year":"2013","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","first-page":"1462","article-title":"Draw: A recurrent neural network for image generation","author":"gregor","year":"2015","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"ii-1242","article-title":"Deep autoregressive networks","author":"gregor","year":"2014","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref17","first-page":"171","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref18","article-title":"Neural networks for machine learning","author":"hinton","year":"2012"},{"key":"ref19","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Int Conf Mach Learning"},{"key":"ref4","article-title":"Reweighted wake-sleep","author":"bornschein","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","first-page":"899","article-title":"Generalized denoising auto-encoders as\n generative models","author":"bengio","year":"2013","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCOM.1983.1095851"},{"key":"ref5","article-title":"Importance weighted autoencoders","author":"burda","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/BF00994018"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.64"},{"key":"ref49","article-title":"Unsupervised and semi-supervised learning with categorical\n generative adversarial networks","author":"springenberg","year":"2016","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref9","first-page":"1486","article-title":"Deep generative image models using a\n laplacian pyramid of adversarial networks","author":"denton","year":"2015","journal-title":"Proc 28th Int Conf Adv Neural Inf Process Syst"},{"key":"ref46","first-page":"61","article-title":"Mean field\n theory for sigmoid belief networks","volume":"4","author":"saul","year":"1996","journal-title":"J AI Res"},{"key":"ref45","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s10107-010-0420-4"},{"key":"ref47","first-page":"3288","article-title":"Convolutional neural networks applied to house numbers digit classification","author":"sermanet","year":"2012","journal-title":"Proc Int Conf Pattern Recog"},{"key":"ref42","first-page":"2928","article-title":"Conditional generative moment-matching networks","author":"ren","year":"2016","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref41","first-page":"3546","article-title":"Semi-supervised learning with ladder networks","author":"rasmus","year":"2015","journal-title":"Proc Int Conf Adv Neural Inf Process Syst"},{"key":"ref44","first-page":"448","article-title":"Deep Boltzmann machines","author":"salakhutdinov","year":"2009","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref43","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"2014","journal-title":"Proc Int Conf Mach Learn"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielaam\/34\/8478843\/8081757-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/8478843\/08081757.pdf?arnumber=8081757","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,8]],"date-time":"2022-04-08T18:47:38Z","timestamp":1649443658000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/8081757\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,11,1]]},"references-count":65,"journal-issue":{"issue":"11"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2017.2766142","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":[[2018,11,1]]}}}