{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T17:16:39Z","timestamp":1790874999794,"version":"4.1.0"},"reference-count":56,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/tmm.2020.3008053","type":"journal-article","created":{"date-parts":[[2020,7,8]],"date-time":"2020-07-08T20:14:06Z","timestamp":1594239246000},"page":"2153-2161","source":"Crossref","is-referenced-by-count":13,"title":["Improving Generative Modelling in VAEs Using Multimodal Prior"],"prefix":"10.1109","volume":"23","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-8149-8151","authenticated-orcid":false,"given":"Vinayak","family":"Abrol","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7870-7098","authenticated-orcid":false,"given":"Pulkit","family":"Sharma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Arijit","family":"Patra","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Deep unsupervised clustering with Gaussian mixture variational autoencoders","author":"dilokthanakul","year":"2016"},{"key":"ref38","first-page":"1","article-title":"Demystifying MMD GANs","author":"bikowski","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref33","first-page":"1718","article-title":"Generative moment matching networks","author":"li","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref32","first-page":"513","article-title":"A kernel method for the two-sample-problem","author":"gretton","year":"0","journal-title":"Proc Int Conf Advances Neural Inf Process Syst"},{"key":"ref31","first-page":"1","article-title":"Bounded information rate variational autoencoders","author":"braithwaite","year":"0","journal-title":"Proc Deep Learn Day ACM Conf Knowl Discovery Data Mining"},{"key":"ref30","first-page":"1","article-title":"Preventing posterior collapse with delta-VAEs","author":"razavi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1214\/13-AOS1140"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/0016-660X(74)90009-9"},{"key":"ref35","first-page":"1107","article-title":"Step size adaptation in reproducing kernel hilbert space","volume":"7","author":"vishwanathan","year":"2006","journal-title":"J Mach Learn Res"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.24033\/asens.1013"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2895292"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2919948"},{"key":"ref29","article-title":"The mutual autoencoder: Controlling information in latent code representations","author":"phuong","year":"2018"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2013.2286083"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.50"},{"key":"ref20","first-page":"1","article-title":"MAE: Mutual posterior-divergence regularization for variational autoencoders","author":"ma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref22","first-page":"1","article-title":"Deep variational information bottleneck","author":"alemi","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01052"},{"key":"ref24","first-page":"1278","article-title":"Stochastic backpropagation and approximate inference in deep generative models","author":"rezende","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-10925-7_27"},{"key":"ref26","first-page":"52","article-title":"IntroVAE: Introspective variational autoencoders for photographic image synthesis","author":"huang","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref25","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref50","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref56","first-page":"864","article-title":"PixelSNAIL: An improved autoregressive generative model","author":"chen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","first-page":"4797","article-title":"Conditional image generation with pixelcnn decoders","author":"oord","year":"0","journal-title":"Proc Int Conf Advances Neural Inf Process Syst"},{"key":"ref54","first-page":"630","article-title":"Identity mappings in deep residual networks","author":"he","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref53","first-page":"1747","article-title":"Pixel recurrent neural networks","author":"oord","year":"0","journal-title":"Proc Int Conf Int Conf Mach Learn"},{"key":"ref52","first-page":"1","article-title":"Unsupervised representation learning with deep convolutional generative adversarial networks","author":"radford","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2591508"},{"key":"ref11","first-page":"2672","article-title":"Generative adversarial nets","author":"goodfellow","year":"0","journal-title":"Proc Int Conf Advances Neural Inf Process Syst"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123359"},{"key":"ref12","first-page":"5885","article-title":"Infovae: Information maximizing variational autoencoders","author":"zhao","year":"0","journal-title":"Proc Int Conf Assoc Advancement Artif Intell"},{"key":"ref13","first-page":"2172","article-title":"InfoGAN: Interpretable representation learning by information maximizing generative adversarial nets","author":"chen","year":"0","journal-title":"Proc Int Conf Advances Neural Inf Process Syst"},{"key":"ref14","first-page":"1558","article-title":"Autoencoding beyond pixels using a learned similarity metric","author":"larsen","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2898777"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858821"},{"key":"ref17","first-page":"4402","article-title":"Disentangling disentanglement in variational autoencoders","author":"mathieu","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref18","first-page":"1","article-title":"Variational lossy autoencoder","author":"chen","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_49"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2015.2477042"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2908352"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331240"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2851077"},{"key":"ref8","first-page":"1","article-title":"$\\beta$-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2016.2533858"},{"key":"ref49","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017"},{"key":"ref9","first-page":"1","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref46","first-page":"1704","article-title":"Conditional neural processes","author":"garnelo","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref45","first-page":"1","article-title":"Fast adaptation in generative models with generative matching networks","author":"bartunov","year":"0","journal-title":"Proc Int Conf Learn Representations Workshop"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref47","first-page":"8024","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"0","journal-title":"Proc Advances Neural Inf Process Syst"},{"key":"ref42","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","author":"sohn","year":"0","journal-title":"Proc Int Conf Advances Neural Inf Process Syst"},{"key":"ref41","first-page":"499","article-title":"A discriminative feature learning approach for deep face recognition","author":"wen","year":"0","journal-title":"Proc Eur Conf Comput Vision"},{"key":"ref44","first-page":"4354","article-title":"Been there, done that: Meta-learning with episodic recall","author":"ritter","year":"0","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","first-page":"1","article-title":"Latent constraints: Learning to generate conditionally from unconditional generative models","author":"engel","year":"0","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/9296985\/09136917.pdf?arnumber=9136917","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,5,10]],"date-time":"2022-05-10T14:51:35Z","timestamp":1652194295000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9136917\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tmm.2020.3008053","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]}}}