{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,12]],"date-time":"2025-11-12T14:20:27Z","timestamp":1762957227527,"version":"3.37.3"},"reference-count":74,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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. on Image Process."],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tip.2023.3299495","type":"journal-article","created":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T18:31:08Z","timestamp":1690914668000},"page":"4486-4500","source":"Crossref","is-referenced-by-count":11,"title":["VTAE: Variational Transformer Autoencoder With Manifolds Learning"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0263-1661","authenticated-orcid":false,"given":"Pourya","family":"Shamsolmoali","sequence":"first","affiliation":[{"name":"School of Communication and Electronic Engineering, East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7569-9018","authenticated-orcid":false,"given":"Masoumeh","family":"Zareapoor","sequence":"additional","affiliation":[{"name":"School of Automation, Xi’an Jiao Tong University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1634-9840","authenticated-orcid":false,"given":"Huiyu","family":"Zhou","sequence":"additional","affiliation":[{"name":"School of Computing and Mathematical Sciences, University of Leicester, Leicester, U.K"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Faculty of Engineering, School of Computer Science, The University of Sydney, Darlington, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2924-946X","authenticated-orcid":false,"given":"Xuelong","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Interaction and Applications, Ministry of Industry and Information Technology, and the School of Artificial Intelligence, OPtics and ElectroNics (iOPEN), Northwestern Polytechnical University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","first-page":"3859","article-title":"Dynamic routing between capsules","volume":"30","author":"sabour","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","first-page":"1018","article-title":"Explicit disentanglement of appearance and perspective in generative models","volume":"32","author":"skafte","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref12","first-page":"1","article-title":"Learning deep latent subspaces for image denoising","author":"yang","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"ref15","first-page":"1","article-title":"Unsupervised learning of group invariant and equivariant representations","author":"winter","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-45080-1_66"},{"key":"ref14","article-title":"Geometric deep learning: Grids, groups, graphs, geodesics, and gauges","author":"bronstein","year":"2021","journal-title":"arXiv 2104 13478"},{"key":"ref58","article-title":"Transformer-based conditional variational autoencoder for controllable story generation","author":"fang","year":"2021","journal-title":"arXiv 2101 00828"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref52","first-page":"8188","article-title":"Attentive group equivariant convolutional networks","author":"romero","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref11","article-title":"Improving latent variable descriptiveness with AutoGen","author":"mansbridge","year":"2018","journal-title":"arXiv 1806 04480"},{"key":"ref55","first-page":"3233","article-title":"Attend, infer, repeat: Fast scene understanding with generative models","volume":"29","author":"eslami","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01865"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00985"},{"key":"ref17","first-page":"1","article-title":"Learning flat latent manifolds with VAEs","author":"chen","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref16","first-page":"5361","article-title":"Equivariant flows: Exact likelihood generative learning for symmetric densities","author":"k\u00f6hler","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","first-page":"2017","article-title":"Spatial transformer networks","author":"jaderberg","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1","article-title":"Distribution-interpolation trade off in generative models","author":"le?niak","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref51","first-page":"3165","article-title":"Generalizing convolutional neural networks for equivariance to lie groups on arbitrary continuous data","author":"finzi","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01122"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30484-3_45"},{"key":"ref45","first-page":"1","article-title":"Magnification factors for the SOM and GTM algorithms","author":"bishop","year":"1997","journal-title":"Proc Workshop Self-Organizing Maps"},{"key":"ref48","first-page":"2990","article-title":"Group equivariant convolutional networks","author":"cohen","year":"2016","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3125687"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3166761"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00251"},{"key":"ref44","first-page":"1540","article-title":"Metrics for deep generative models","author":"chen","year":"2018","journal-title":"Proc Int Conf Artif Intel Statis"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3061286"},{"key":"ref49","first-page":"1","article-title":"Probabilistic spatial transformer networks","author":"schw\u00f6bel","year":"2022","journal-title":"Proc Conf Uncertainty Artif Intell"},{"key":"ref8","article-title":"beta-VAE: Learning basic visual concepts with a constrained variational framework","author":"higgins","year":"2016","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref7","first-page":"3581","article-title":"Semi-supervised learning with deep generative models","volume":"27","author":"kingma","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref9","first-page":"2615","article-title":"Isolating sources of disentanglement in variational autoencoders","volume":"31","author":"chen","year":"2018","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","article-title":"Auto-encoding variational Bayes","author":"kingma","year":"2013","journal-title":"arXiv 1312 6114"},{"key":"ref3","first-page":"1","article-title":"Generative adversarial nets","volume":"27","author":"goodfellow","year":"2014","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref6","first-page":"3111","article-title":"Distributed representations of words and phrases and their compositionality","volume":"26","author":"mikolov","year":"2013","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref5","first-page":"159","article-title":"Fixing a broken ELBO","author":"alemi","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref40","article-title":"Optimal transport maps for distribution preserving operations on latent spaces of generative models","author":"agustsson","year":"2019","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1126\/science.290.5500.2323"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1360\/jos161584"},{"key":"ref37","doi-asserted-by":"crossref","first-page":"2879","DOI":"10.1109\/TPAMI.2022.3185773","article-title":"Data augmentation in high dimensional low sample size setting using a geometry-based variational autoencoder","volume":"45","author":"chadebec","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref36","first-page":"1","article-title":"Variational autoencoders with Riemannian Brownian motion priors","author":"kalatzis","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01041"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20050-2_31"},{"key":"ref74","first-page":"2234","article-title":"Improved techniques for training GANs","volume":"29","author":"salimans","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3069498"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01098"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3014608"},{"key":"ref1","first-page":"2359","article-title":"Variational autoencoder with learned latent structure","author":"connor","year":"2021","journal-title":"Proc Int Conf Artif Intell Statist"},{"key":"ref39","first-page":"1","article-title":"A geometric perspective on variational autoencoders","author":"chadebec","year":"2022","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","first-page":"19487","article-title":"Rethinking conditional GAN training: An approach using geometrically structured latent manifolds","volume":"34","author":"ramasinghe","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2012.2227726"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00136"},{"key":"ref24","article-title":"Probabilistic autoencoder","author":"b\u00f6hm","year":"2020","journal-title":"arXiv 2006 05479"},{"key":"ref68","first-page":"2870","article-title":"Learning hierarchical priors in VAEs","volume":"32","author":"klushyn","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_6"},{"journal-title":"Learning multiple layers of features from tiny images","year":"2009","author":"krizhevsky","key":"ref67"},{"key":"ref26","first-page":"2649","article-title":"Disentangling by factorising","author":"kim","year":"2018","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref25","article-title":"From variational to deterministic autoencoders","author":"ghosh","year":"2020","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.10777"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00308"},{"key":"ref64","article-title":"EMNIST: An extension of MNIST to handwritten letters","author":"cohen","year":"2017","journal-title":"arXiv 1702 05373"},{"key":"ref63","article-title":"Fashion-MNIST: A novel image dataset for benchmarking machine learning algorithms","author":"xiao","year":"2017","journal-title":"ArXiv 1708 07747"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-86520-7_7"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref21","first-page":"1","article-title":"Learning structured output representation using deep conditional generative models","volume":"28","author":"sohn","year":"2015","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref65","first-page":"2018","article-title":"Large-scale celebfaces attributes (Celeba) dataset","volume":"15","author":"liu","year":"2018","journal-title":"Retrieved"},{"key":"ref28","first-page":"1","article-title":"Conditional generative modeling via learning the latent space","author":"ramasinghe","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref27","article-title":"Commutative lie group VAE for disentanglement learning","author":"zhu","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"1","article-title":"Conditional image generation by conditioning variational auto-encoders","author":"harvey","year":"2022","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref60","first-page":"2066","article-title":"Geodesic flow kernel for unsupervised domain adaptation","author":"gong","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1137\/141000439"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/83\/9991910\/10201469.pdf?arnumber=10201469","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,25]],"date-time":"2024-10-25T14:09:11Z","timestamp":1729865351000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10201469\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/tip.2023.3299495","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2023]]}}}