{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,26]],"date-time":"2026-02-26T15:28:52Z","timestamp":1772119732946,"version":"3.50.1"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T00:00:00Z","timestamp":1711929600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1007\/s00371-024-03338-x","type":"journal-article","created":{"date-parts":[[2024,4,1]],"date-time":"2024-04-01T11:01:38Z","timestamp":1711969298000},"page":"7491-7502","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["HGMVAE: hierarchical disentanglement in Gaussian mixture variational autoencoder"],"prefix":"10.1007","volume":"40","author":[{"given":"Jiashuang","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Yongqi","family":"Liu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-3227-3132","authenticated-orcid":false,"given":"Xiaoqin","family":"Du","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,4,1]]},"reference":[{"key":"3338_CR1","first-page":"53","volume":"35","author":"I Goodfellow","year":"2014","unstructured":"Goodfellow, I., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., Bengio, Y.: Generative adversarial nets. Neural Inf. Process. Syst. 35, 53\u201365 (2014)","journal-title":"Neural Inf. Process. Syst."},{"key":"3338_CR2","unstructured":"Radford, A., Metz, L., Chintala, S.: Unsupervised representation learning with deep convolutional generative adversarial networks. arXiv:1511.06434 (2015)"},{"key":"3338_CR3","doi-asserted-by":"crossref","unstructured":"Wang, X., Gupta, A.: Generative image modeling using style and structure adversarial networks. In: Computer Vision\u2013ECCV 2016: 14th European Conference, Amsterdam, The Netherlands, October 11\u201314, 2016, Proceedings, Part IV 14, pp. 318\u2013335 (2016). Springer","DOI":"10.1007\/978-3-319-46493-0_20"},{"key":"3338_CR4","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4401\u20134410 (2019)","DOI":"10.1109\/CVPR.2019.00453"},{"key":"3338_CR5","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv:1312.6114 (2013)"},{"key":"3338_CR6","unstructured":"Sohn, K., Lee, H., Yan, X.: Learning structured output representation using deep conditional generative models. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"key":"3338_CR7","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"3338_CR8","unstructured":"Van Den\u00a0Oord, A., Kalchbrenner, N., Kavukcuoglu, K.: Pixel recurrent neural networks. In: International Conference on Machine Learning, pp. 1747\u20131756. PMLR (2016)"},{"key":"3338_CR9","unstructured":"Salimans, T., Karpathy, A., Chen, X., Kingma, D.P.: Pixelcnn++: improving the pixelcnn with discretized logistic mixture likelihood and other modifications. arXiv:1701.05517 (2017)"},{"key":"3338_CR10","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3338_CR11","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"3338_CR12","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat gans on image synthesis. Adv. Neural Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"3338_CR13","unstructured":"Bank, D., Koenigstein, N., Giryes, R.: Autoencoders. arXiv:2003.05991 (2020)"},{"key":"3338_CR14","doi-asserted-by":"crossref","unstructured":"Michelucci, U.: An introduction to autoencoders. arXiv:2201.03898 (2022)","DOI":"10.1007\/978-1-4842-8020-1_9"},{"key":"3338_CR15","doi-asserted-by":"crossref","unstructured":"Reynolds, D.A., et al.: Gaussian mixture models. Encycl. Biom. 741(659\u2013663) (2009)","DOI":"10.1007\/978-0-387-73003-5_196"},{"key":"3338_CR16","unstructured":"Nalisnick, E., Hertel, L., Smyth, P.: Approximate inference for deep latent gaussian mixtures. In: NIPS Workshop on Bayesian Deep Learning, vol. 2, p. 131 (2016)"},{"key":"3338_CR17","doi-asserted-by":"crossref","unstructured":"Jiang, Z., Zheng, Y., Tan, H., Tang, B., Zhou, H.: Variational deep embedding: an unsupervised and generative approach to clustering. arXiv:1611.05148 (2016)","DOI":"10.24963\/ijcai.2017\/273"},{"key":"3338_CR18","unstructured":"Dilokthanakul, N., Mediano, P.A., Garnelo, M., Lee, M.C., Salimbeni, H., Arulkumaran, K., Shanahan, M.: Deep unsupervised clustering with gaussian mixture variational autoencoders. arXiv:1611.02648 (2016)"},{"key":"3338_CR19","unstructured":"Lee, D.B., Min, D., Lee, S., Hwang, S.J.: Meta-gmvae: Mixture of Gaussian vae for unsupervised meta-learning. In: International Conference on Learning Representations (2021)"},{"key":"3338_CR20","unstructured":"Bai, J., Kong, S., Gomes, C.P.: Gaussian mixture variational autoencoder with contrastive learning for multi-label classification. In: International Conference on Machine Learning, pp. 1383\u20131398. PMLR (2022)"},{"key":"3338_CR21","unstructured":"Figueroa, J.A.: Semi-supervised learning using deep generative models and auxiliary tasks. In: NeurIPS Workshop on Bayesian Deep Learning (2019)"},{"key":"3338_CR22","unstructured":"Collier, M., Urdiales, H.: Scalable deep unsupervised clustering with concrete gmvaes. arXiv:1909.08994 (2019)"},{"key":"3338_CR23","doi-asserted-by":"crossref","unstructured":"Yang, L., Cheung, N.-M., Li, J., Fang, J.: Deep clustering by gaussian mixture variational autoencoders with graph embedding. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 6440\u20136449 (2019)","DOI":"10.1109\/ICCV.2019.00654"},{"key":"3338_CR24","doi-asserted-by":"crossref","unstructured":"Abdulaziz, A., Zhou, J., Di\u00a0Fulvio, A., Altmann, Y., McLaughlin, S.: Semi-supervised gaussian mixture variational autoencoder for pulse shape discrimination. In: ICASSP 2022-2022 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3538\u20133542. IEEE (2022)","DOI":"10.1109\/ICASSP43922.2022.9747313"},{"issue":"8","key":"3338_CR25","doi-asserted-by":"publisher","first-page":"1798","DOI":"10.1109\/TPAMI.2013.50","volume":"35","author":"Y Bengio","year":"2013","unstructured":"Bengio, Y., Courville, A., Vincent, P.: Representation learning: a review and new perspectives. IEEE Trans. Pattern Anal. Mach. Intell. 35(8), 1798\u20131828 (2013)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3338_CR26","unstructured":"Bengio, Y.: The consciousness prior. arXiv:1709.08568 (2017)"},{"key":"3338_CR27","unstructured":"Higgins, I., Matthey, L., Pal, A., Burgess, C., Glorot, X., Botvinick, M., Mohamed, S., Lerchner, A.: beta-vae: learning basic visual concepts with a constrained variational framework. In: International Conference on Learning Representations (2017)"},{"key":"3338_CR28","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"key":"3338_CR29","unstructured":"Burgess, C.P., Higgins, I., Pal, A., Matthey, L., Watters, N., Desjardins, G., Lerchner, A.: Understanding disentangling in $$beta $$-vae. arXiv:1804.03599 (2018)"},{"key":"3338_CR30","doi-asserted-by":"publisher","first-page":"1229","DOI":"10.1007\/s00371-023-02843-9","volume":"40","author":"M-f Hu","year":"2023","unstructured":"Hu, M.-f, Liu, Z.-y, Liu, J.-w: mcvae: disentangling by mean constraint. Vis. Comput. 40, 1229\u20131243 (2023)","journal-title":"Vis. Comput."},{"key":"3338_CR31","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: International Conference on Machine Learning, pp. 2649\u20132658. PMLR (2018)"},{"key":"3338_CR32","unstructured":"Chen, R.T., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. Adv. Neural Inf. Process. Syst. 31 (2018)"},{"key":"3338_CR33","unstructured":"Zhao, S., Song, J., Ermon, S.: Infovae: Information maximizing variational autoencoders. arXiv:1706.02262 (2017)"},{"key":"3338_CR34","doi-asserted-by":"crossref","unstructured":"Gretton, A., Bousquet, O., Smola, A., Sch\u00f6lkopf, B.: Measuring statistical dependence with Hilbert\u2013Schmidt norms. In: Algorithmic Learning Theory: 16th International Conference, ALT 2005, Singapore, October 8\u201311, 2005. Proceedings 16, pp. 63\u201377. Springer (2005)","DOI":"10.1007\/11564089_7"},{"key":"3338_CR35","unstructured":"Esmaeili, B., Wu, H., Jain, S., Bozkurt, A., Siddharth, N., Paige, B., Brooks, D.H., Dy, J., Meent, J.-W.: Structured disentangled representations. In: The 22nd International Conference on Artificial Intelligence and Statistics, pp. 2525\u20132534. PMLR (2019)"},{"key":"3338_CR36","first-page":"19667","volume":"33","author":"A Vahdat","year":"2020","unstructured":"Vahdat, A., Kautz, J.: Nvae: a deep hierarchical variational autoencoder. Adv. Neural Inf. Process. Syst. 33, 19667\u201319679 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"11","key":"3338_CR37","doi-asserted-by":"publisher","first-page":"2278","DOI":"10.1109\/5.726791","volume":"86","author":"Y LeCun","year":"1998","unstructured":"LeCun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86(11), 2278\u20132324 (1998)","journal-title":"Proc. IEEE"},{"key":"3338_CR38","doi-asserted-by":"publisher","first-page":"53","DOI":"10.1016\/0377-0427(87)90125-7","volume":"20","author":"PJ Rousseeuw","year":"1987","unstructured":"Rousseeuw, P.J.: Silhouettes: a graphical aid to the interpretation and validation of cluster analysis. J. Comput. Appl. Math. 20, 53\u201365 (1987)","journal-title":"J. Comput. Appl. Math."},{"issue":"1","key":"3338_CR39","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1080\/03610927408827101","volume":"3","author":"T Cali\u0144ski","year":"1974","unstructured":"Cali\u0144ski, T., Harabasz, J.: A dendrite method for cluster analysis. Commun. Stat.-Theory Methods 3(1), 1\u201327 (1974)","journal-title":"Commun. Stat.-Theory Methods"},{"key":"3338_CR40","doi-asserted-by":"publisher","first-page":"224","DOI":"10.1109\/TPAMI.1979.4766909","volume":"2","author":"DL Davies","year":"1979","unstructured":"Davies, D.L., Bouldin, D.W.: A cluster separation measure. IEEE Trans. Pattern Anal. Mach. Intell. 2, 224\u2013227 (1979)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3338_CR41","unstructured":"Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9(11) (2008)"},{"key":"3338_CR42","doi-asserted-by":"crossref","unstructured":"Aubry, M., Maturana, D., Efros, A.A., Russell, B.C., Sivic, J.: Seeing 3d chairs: exemplar part-based 2d-3d alignment using a large dataset of cad models. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 3762\u20133769 (2014)","DOI":"10.1109\/CVPR.2014.487"},{"key":"3338_CR43","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Large-scale celebfaces attributes (celeba) dataset. Retrieved August 15(2018), 11 (2018)"},{"key":"3338_CR44","unstructured":"Xiao, H., Rasul, K., Vollgraf, R.: Fashion-mnist: a novel image dataset for benchmarking machine learning algorithms. arXiv:1708.07747 (2017)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03338-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-024-03338-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-024-03338-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T10:09:34Z","timestamp":1727690974000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-024-03338-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,4,1]]},"references-count":44,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2024,10]]}},"alternative-id":["3338"],"URL":"https:\/\/doi.org\/10.1007\/s00371-024-03338-x","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,4,1]]},"assertion":[{"value":"29 January 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 April 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that there are no conflicts of interest, we do not have any possible conflicts of interest. The authors confirm that the data supporting the findings of this study are available within the article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}