{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T21:59:12Z","timestamp":1793138352037,"version":"4.5.0"},"reference-count":65,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T00:00:00Z","timestamp":1636416000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Nat Commun"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>\n                    In order to better understand how the brain perceives faces, it is important to know what objective drives learning in the ventral visual stream. To answer this question, we model neural responses to faces in the macaque inferotemporal (IT) cortex with a deep self-supervised generative model,\n                    <jats:italic>\u03b2<\/jats:italic>\n                    -VAE, which disentangles sensory data into interpretable latent factors, such as gender or age. Our results demonstrate a strong correspondence between the generative factors discovered by\n                    <jats:italic>\u03b2<\/jats:italic>\n                    -VAE and those coded by single IT neurons, beyond that found for the baselines, including the handcrafted state-of-the-art model of face perception, the Active Appearance Model, and deep classifiers. Moreover,\n                    <jats:italic>\u03b2<\/jats:italic>\n                    -VAE is able to reconstruct novel face images using signals from just a handful of cells. Together our results imply that optimising the disentangling objective leads to representations that closely resemble those in the IT at the single unit level. This points at disentangling as a plausible learning objective for the visual brain.\n                  <\/jats:p>","DOI":"10.1038\/s41467-021-26751-5","type":"journal-article","created":{"date-parts":[[2021,11,9]],"date-time":"2021-11-09T06:02:38Z","timestamp":1636437758000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":120,"title":["Unsupervised deep learning identifies semantic disentanglement in single inferotemporal face patch neurons"],"prefix":"10.1038","volume":"12","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1890-2091","authenticated-orcid":false,"given":"Irina","family":"Higgins","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Le","family":"Chang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Victoria","family":"Langston","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2812-9917","authenticated-orcid":false,"given":"Demis","family":"Hassabis","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christopher","family":"Summerfield","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1083-1919","authenticated-orcid":false,"given":"Doris","family":"Tsao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7758-6896","authenticated-orcid":false,"given":"Matthew","family":"Botvinick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,11,9]]},"reference":[{"key":"26751_CR1","doi-asserted-by":"publisher","first-page":"415","DOI":"10.1016\/j.neuron.2012.01.010","volume":"73","author":"J DiCarlo","year":"2012","unstructured":"DiCarlo, J., Zoccolan, D. & Rust, N. How does the brain solve visual object recognition? Neuron 73, 415\u2013434 (2012).","journal-title":"Neuron"},{"key":"26751_CR2","doi-asserted-by":"publisher","first-page":"574","DOI":"10.1113\/jphysiol.1959.sp006308","volume":"124","author":"DH Hubel","year":"1959","unstructured":"Hubel, D. H. & Wiesel, T. N. Receptive fields of single neurones in the cat\u2019s striate cortex. J. Physiol. 124, 574\u2013591 (1959).","journal-title":"J. Physiol."},{"key":"26751_CR3","doi-asserted-by":"publisher","first-page":"1013","DOI":"10.1016\/j.cell.2017.05.011","volume":"169","author":"L Chang","year":"2017","unstructured":"Chang, L. & Tsao, D. Y. The code for facial identity in the primate brain. Cell 169, 1013\u20131028 (2017).","journal-title":"Cell"},{"key":"26751_CR4","doi-asserted-by":"publisher","first-page":"670","DOI":"10.1126\/science.1119983","volume":"311","author":"DY Tsao","year":"2006","unstructured":"Tsao, D. Y., Freiwald, W. A., Tootell, R. B. & Livingstone, M. S. A cortical region consisting entirely of face-selective cells. Science 311, 670\u2013674 (2006).","journal-title":"Science"},{"key":"26751_CR5","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1146\/annurev.neuro.30.051606.094238","volume":"31","author":"DY Tsao","year":"2008","unstructured":"Tsao, D. Y. & Livingstone, M. S. Mechanisms of face perception. Annu. Rev. Neurosci. 31, 411\u2013437 (2008).","journal-title":"Annu. Rev. Neurosci."},{"key":"26751_CR6","doi-asserted-by":"publisher","first-page":"2785","DOI":"10.1016\/j.cub.2021.04.014","volume":"31","author":"L Chang","year":"2021","unstructured":"Chang, L., Egger, B., Vetter, T. & Tsao, D. Y. Explaining face representation in the primate brain using different computational models. Current Biology 31, 2785\u20132795 (2021).","journal-title":"Current Biology"},{"key":"26751_CR7","doi-asserted-by":"publisher","first-page":"1546","DOI":"10.1038\/s41593-019-0520-2","volume":"22","author":"BA Richards","year":"2019","unstructured":"Richards, B. A. et al. A deep learning framework for neuroscience. Nat. Neurosci. 22, 1546\u20131726 (2019).","journal-title":"Nat. Neurosci."},{"key":"26751_CR8","doi-asserted-by":"publisher","first-page":"356","DOI":"10.1038\/nn.4244","volume":"19","author":"DLK Yamins","year":"2016","unstructured":"Yamins, D. L. K. & DiCarlo, J. J. Using goal-driven deep learning models to understand sensory cortex. Nat. Neurosci. 19, 356\u2013365 (2016).","journal-title":"Nat. Neurosci."},{"key":"26751_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S. & Sun, J. Delving deep into rectifiers: surpassing human-level performance on imagenet classification. In Proceedings of the IEEE International Conference on Computer Vision, ICCV. Vol. 1, 1026\u20131034 (ICCV, 2015).","DOI":"10.1109\/ICCV.2015.123"},{"key":"26751_CR10","doi-asserted-by":"publisher","first-page":"8619","DOI":"10.1073\/pnas.1403112111","volume":"111","author":"DLK Yamins","year":"2014","unstructured":"Yamins, D. L. K. et al. Performance-optimized hierarchical models predict neural responses in higher visual cortex. Proc. Natl Acad. Sci. USA 111, 8619\u20138624 (2014).","journal-title":"Proc. Natl Acad. Sci. USA"},{"key":"26751_CR11","doi-asserted-by":"crossref","unstructured":"Khaligh-Razavi, S. & Kriegeskorte, N. Deep supervised, but not unsupervised, models may explain IT cortical representation. PLoS Comput. Biol. 10, e1003915 (2014).","DOI":"10.1371\/journal.pcbi.1003915"},{"key":"26751_CR12","doi-asserted-by":"crossref","unstructured":"Bashivan, P., Kar, K. & DiCarlo, J. J. Neural population control via deep image synthesis. Science 364 eaav9436 (2019).","DOI":"10.1126\/science.aav9436"},{"key":"26751_CR13","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.jecp.2015.01.007","volume":"133","author":"L Slone","year":"2015","unstructured":"Slone, L. & Johnson, S. Infants\u2019 statistical learning: 2- and 5-month-olds\u2019 segmentation of continuous visual sequences. J. Exp. Child Psychol. 133, 47\u201356 (2015).","journal-title":"J. Exp. Child Psychol."},{"key":"26751_CR14","doi-asserted-by":"crossref","unstructured":"Lindsay, G. Convolutional neural networks as a model of the visual system: past, present, and future. J. Cogn. Neurosci. 33, 2017\u20132031 (2021).","DOI":"10.1162\/jocn_a_01544"},{"key":"26751_CR15","unstructured":"Thompson, J. A. F., Bengio, Y., Formisano, E. & Sch\u00f6nwiesner, M. How can deep learning advance computational modeling of sensory information processing? In NeurIPS Workshop on Representation Learning in Artificial and Biological Neural Networks Report number: MLINI\/2016\/04, arXiv:1810.08651v1 [cs.NE] (MLINI, 2016)."},{"key":"26751_CR16","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, 1798\u20131828 (2013).","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"26751_CR17","unstructured":"Higgins, I. et al. \u03b2-VAE: learning basic visual concepts with a constrained variational framework. In Proceedings of the 5th International Conference on Learning Representations, ICLR (ICLR, 2017)."},{"key":"26751_CR18","unstructured":"Burgess, C. P. et al. MONet: Unsupervised scene decomposition and representation. Preprint at https:\/\/arxiv.org\/abs\/1901.11390 (2019)."},{"key":"26751_CR19","doi-asserted-by":"publisher","unstructured":"Lee W., Kim D., Hong S. & Lee H. (2020) High-Fidelity Synthesis with Disentangled Representation. In: Vedaldi A., Bischof H., Brox T., Frahm JM. (eds) Computer Vision \u2013 ECCV 2020. ECCV 2020. Lecture Notes in Computer Science, vol 12371. Springer, Cham. https:\/\/doi.org\/10.1007\/978-3-030-58574-7_10","DOI":"10.1007\/978-3-030-58574-7_10"},{"key":"26751_CR20","doi-asserted-by":"publisher","first-page":"193 \u2013 202","DOI":"10.1007\/BF00344251","volume":"36","author":"K Fukushima","year":"1980","unstructured":"Fukushima, K. A self-organizing neural network model for a mechanism of pattern recognition unaffected by shift in position. Biol. Cybern. 36, 193 \u2013 202 (1980).","journal-title":"Biol. Cybern."},{"key":"26751_CR21","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.1038\/14819","volume":"2","author":"M Riesenhuber","year":"1999","unstructured":"Riesenhuber, M. & Poggio, T. Hierarchical models of object recognition in cortex. Nat. Neurosci. 2, 1019\u20131025 (1999).","journal-title":"Nat. Neurosci."},{"key":"26751_CR22","unstructured":"Higgins, I. et al. DARLA: improving zero-shot transfer in reinforcement learning. In Proceedings of the 34th International Conference on Machine Learning, PMLR. Vol. 70, 1480\u20131490 (ICML, 2017)."},{"key":"26751_CR23","unstructured":"Higgins, I. et al. SCAN: Learning hierarchical compositional visual concepts. In Proceedings of the 6th International Conference on Learning Representations, ICLR (ICLR, 2018)."},{"key":"26751_CR24","unstructured":"Achille, A. et al. Life-long disentangled representation learning with cross-domain latent homologies. In Proceedings of Advances in Neural Information Processing Systems, NeurIPS. Vol. 31, 9873\u20139883 (NeurIPS, 2018)."},{"key":"26751_CR25","doi-asserted-by":"publisher","first-page":"1733","DOI":"10.1152\/jn.01265.2006","volume":"98","author":"C Cadieu","year":"2007","unstructured":"Cadieu, C. et al. A model of v4 shape selectivity and invariance. J. Neurophysiol. 98, 1733\u20131750 (2007).","journal-title":"J. Neurophysiol."},{"key":"26751_CR26","doi-asserted-by":"publisher","first-page":"10005","DOI":"10.1523\/JNEUROSCI.5023-14.2015","volume":"35","author":"U G\u00fc\u00e7l\u00fc","year":"2015","unstructured":"G\u00fc\u00e7l\u00fc, U. & van Gerven, M. A. Deep neural networks reveal a gradient in the complexity of neural representations across the ventral stream. J. Neurosci. 35, 10005\u201310014 (2015).","journal-title":"J. Neurosci."},{"key":"26751_CR27","doi-asserted-by":"publisher","first-page":"e1006897","DOI":"10.1371\/journal.pcbi.1006897","volume":"15","author":"SA Cadena","year":"2019","unstructured":"Cadena, S. A. et al. Deep convolutional models improve predictions of macaque v1 responses to natural images. PLoS Comput. Biol. 15, e1006897 (2019).","journal-title":"PLoS Comput. Biol."},{"key":"26751_CR28","first-page":"1662","volume":"2","author":"N Kriegeskorte","year":"2008","unstructured":"Kriegeskorte, N., Mur, M. & Bandettini, P. Representational similarity analysis - connecting the branches of systems neuroscience. Front. Syst. Neurosci. 2, 1662\u20135137 (2008).","journal-title":"Front. Syst. Neurosci."},{"key":"26751_CR29","unstructured":"Eastwood, C. & Williams, C. K. I. A framework for the quantitative evaluation of disentangled representations. In Proceedings of the 6th International Conference on Learning Representations, ICLR (ICLR, 2018)."},{"key":"26751_CR30","first-page":"4114","volume":"97","author":"F Locatello","year":"2019","unstructured":"Locatello, F. et al. Challenging common assumptions in the unsupervised learning of disentangled representations. ICML 97, 4114\u20134124 (2019).","journal-title":"ICML"},{"key":"26751_CR31","unstructured":"Duan, S. et al. Unsupervised model selection for variational disentangled representation learning. In Proceedings of the 8th International Conference on Learning Representations, ICLR (ICLR, 2020)."},{"key":"26751_CR32","doi-asserted-by":"crossref","unstructured":"Omkar M. Parkhi, Andrea Vedaldi and Andrew Zisserman. Deep Face Recognition. In Xianghua Xie, Mark W. Jones, and Gary K. L. Tam, editors, Proceedings of the British Machine Vision Conference (BMVC), pages 41.1\u201341.12. BMVA Press, September 2015.","DOI":"10.5244\/C.29.41"},{"key":"26751_CR33","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-12623-6","volume":"10","author":"S Grossman","year":"2019","unstructured":"Grossman, S. et al. Convergent evolution of face spaces across human face-selective neuronal groups and deep convolutional networks. Nat. Commun. 10, 4934 (2019).","journal-title":"Nat. Commun."},{"key":"26751_CR34","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-019-09239-1","volume":"10","author":"K Dobs","year":"2019","unstructured":"Dobs, K., Isik, L., Pantazis, D. & Kanwisher, N. How face perception unfolds over time. Nat. Commun. 10, 1258 (2019).","journal-title":"Nat. Commun."},{"key":"26751_CR35","doi-asserted-by":"publisher","first-page":"504","DOI":"10.1126\/science.1127647","volume":"313","author":"GE Hinton","year":"2006","unstructured":"Hinton, G. E. & Salakhutdinov, R. Reducing the dimensionality of data with neural networks. Science 313, 504\u2013507 (2006).","journal-title":"Science"},{"key":"26751_CR36","unstructured":"Kingma, D. P. & Welling, M. Auto-encoding variational bayes. In Proceedings of the 1st International Conference on Learning Representations, ICLR (ICLR, 2014)."},{"key":"26751_CR37","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1038\/s42003-019-0438-y","volume":"2","author":"R VanRullen","year":"2019","unstructured":"VanRullen, R. & Reddy, L. Reconstructing faces from fMRI patterns using deep generative neural networks. Commun. Biol. 2, 1\u201310 (2019).","journal-title":"Commun. Biol."},{"key":"26751_CR38","doi-asserted-by":"crossref","unstructured":"G\u00e1sp\u00e1r, M. E., Polack, P.-O., Golshani, P., Lengyel, M. & Orb\u00e1n, G. Representational untangling by the firing rate nonlinearity in V1 simple cells. eLife 8, e43625 (2019).","DOI":"10.7554\/eLife.43625"},{"key":"26751_CR39","doi-asserted-by":"publisher","first-page":"1244","DOI":"10.1038\/nn767","volume":"4","author":"HO de Beeck","year":"2001","unstructured":"de Beeck, H. O., Wagemans, J. & Vogels, R. Inferotemporal neurons represent low-dimensional configurations of parameterized shapes. Nat. Neurosci. 4, 1244\u20131252 (2001).","journal-title":"Nat. Neurosci."},{"key":"26751_CR40","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1111\/j.1460-9568.2005.04202.x","volume":"22","author":"G Kayaert","year":"2005","unstructured":"Kayaert, G., Biederman, I., de Beeck, H. P. O. & Vogels, R. Tuning for shape dimensions in macaque inferior temporal cortex. Eur. J. Neurosci. 22, 212\u2013224 (2005).","journal-title":"Eur. J. Neurosci."},{"key":"26751_CR41","unstructured":"Higgins, I. et al. Towards a definition of disentangled representations. Theoretical Physics for Deep Learning Workshop, ICML (ICML, 2019)."},{"key":"26751_CR42","doi-asserted-by":"publisher","unstructured":"Leibo, J., Liao, Q. & Poggio, T. SUFR-W - Subtasks of unconstrained face recognition. 2014 International Conference on Computer Vision Theory and Applications (VISAPP). 113\u2013121 https:\/\/doi.org\/10.7910\/DVN\/SJV7QK (2014).","DOI":"10.7910\/DVN\/SJV7QK"},{"key":"26751_CR43","doi-asserted-by":"publisher","first-page":"764","DOI":"10.1038\/77666","volume":"3","author":"MJ Tarr","year":"2000","unstructured":"Tarr, M. J. & Gauthier, I. FFA: a flexible fusiform area for subordinate-level visual processing automatized by expertise. Nat. Neurosci. 3, 764\u2013769 (2000).","journal-title":"Nat. Neurosci."},{"key":"26751_CR44","first-page":"1391","volume":"1\u201316","author":"JN Wood","year":"2018","unstructured":"Wood, J. N. & Wood, S. M. W. The development of invariant object recognition requires visual experience with temporally smooth objects. J. Physiol. 1\u201316, 1391\u20131406 (2018).","journal-title":"J. Physiol."},{"key":"26751_CR45","doi-asserted-by":"publisher","first-page":"325","DOI":"10.1016\/j.tics.2018.02.004","volume":"22","author":"LB Smith","year":"2018","unstructured":"Smith, L. B., Jayaraman, S., Clerkin, E. & Yu, C. The developing infant creates a curriculum for statistical learning. Trends Cogn. Sci. 22, 325\u2013336 (2018).","journal-title":"Trends Cogn. Sci."},{"key":"26751_CR46","first-page":"127\u2014138","volume":"11","author":"K Friston","year":"2010","unstructured":"Friston, K. The free-energy principle: a unified brain theory? Nat. Rev. Neurosci. 11, 127\u2014138 (2010).","journal-title":"Nat. Rev. Neurosci."},{"key":"26751_CR47","unstructured":"Locatello, F. et al. Weakly-supervised disentanglement without compromises. In III, H. D. & Singh, A. (eds.) Proceedings of the 37th International Conference on Machine Learning, vol. 119, 6348\u20136359 (ICML, 2020)."},{"key":"26751_CR48","doi-asserted-by":"publisher","first-page":"245","DOI":"10.1016\/j.neuron.2017.06.011","volume":"95","author":"D Hassabis","year":"2017","unstructured":"Hassabis, D., Kumaran, D., Summerfield, C. & Botvinick, M. Neuroscience-inspired artificial intelligence. Neuron 95, 245\u2013258 (2017).","journal-title":"Neuron"},{"key":"26751_CR49","doi-asserted-by":"crossref","unstructured":"Bellmund, J. L. S., G\u00e4rdenfors, P., Moser, E. I. & Doeller, C. F. Navigating cognition: spatial codes for human thinking. Science 362, eaat6766 (2018).","DOI":"10.1126\/science.aat6766"},{"key":"26751_CR50","doi-asserted-by":"publisher","first-page":"1544 \u2013 1553","DOI":"10.1038\/s41593-019-0470-8","volume":"22","author":"Y Niv","year":"2019","unstructured":"Niv, Y. Learning task-state representations. Nat. Neurosci. 22, 1544 \u2013 1553 (2019).","journal-title":"Nat. Neurosci."},{"key":"26751_CR51","unstructured":"Martinez, A. & Benavente, R. AR Face Database. CVC Technical Report 24 (CVC, 1998)."},{"key":"26751_CR52","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X. & Tang, X. Deep learning face attributes in the wild. In 2015 IEEE International Conference on Computer Vision, ICCV, 3730\u20133738 (ICCV, 2015).","DOI":"10.1109\/ICCV.2015.425"},{"key":"26751_CR53","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.3758\/s13428-014-0532-5","volume":"47","author":"DS Ma","year":"2015","unstructured":"Ma, D. S., Correll, J. & Wittenbrink, B. The Chicago face database: a free stimulus set of faces and norming data. Behav. Res. Methods 47, 1122\u20131135 (2015).","journal-title":"Behav. Res. Methods"},{"key":"26751_CR54","unstructured":"Peer, P. CVL Face Database (Computer Vision Laboratory, University of Ljubljana, 1999)."},{"key":"26751_CR55","doi-asserted-by":"publisher","first-page":"295","DOI":"10.1016\/S0262-8856(97)00070-X","volume":"16","author":"P Phillips","year":"1998","unstructured":"Phillips, P., Wechsler, H., Huang, J. & Rauss, P. The FERET database and evaluation procedure for face recognition algorithms. Image Vision Comput. 16, 295\u2013306 (1998).","journal-title":"Image Vision Comput."},{"key":"26751_CR56","doi-asserted-by":"publisher","first-page":"1197","DOI":"10.3758\/s13428-015-0641-9","volume":"48","author":"N Strohminger","year":"2016","unstructured":"Strohminger, N. et al. The MR2: a multi-racial mega-resolution database of facial stimuli. Behav. Res. Methods 48, 1197\u2013204 (2016).","journal-title":"Behav. Res. Methods"},{"key":"26751_CR57","doi-asserted-by":"crossref","unstructured":"Gao, W. et al. The CAS-PEAL large-scale chinese face database and baseline evaluations. IEEE Trans. Syst. Man. Cybern. B Cybern. 38, 149\u2013161 (2008).","DOI":"10.1109\/TSMCA.2007.909557"},{"key":"26751_CR58","first-page":"1278","volume":"32","author":"DJ Rezende","year":"2014","unstructured":"Rezende, D. J., Mohamed, S. & Wierstra, D. Stochastic backpropagation and approximate inference in deep generative models. ICML 32, 1278\u20131286 (2014).","journal-title":"ICML"},{"key":"26751_CR59","unstructured":"G\u00fc\u00e7l\u00fct\u00fcrk, Y. et al. Reconstructing perceived faces from brain activations with deep adversarial neural decoding. In Proceedings of Advances in Neural Information Processing Systems, NeurIPS, Vol. 30, 4246\u20134257 (NeurIPS, 2017)."},{"key":"26751_CR60","doi-asserted-by":"publisher","first-page":"411","DOI":"10.1016\/S0893-6080(00)00026-5","volume":"13","author":"A Hyv\u00e4rinen","year":"2000","unstructured":"Hyv\u00e4rinen, A. & Oja, E. Independent component analysis: algorithms and applications. Neural Netw. 13, 411\u2013430 (2000).","journal-title":"Neural Netw."},{"key":"26751_CR61","doi-asserted-by":"crossref","unstructured":"Klare, B. F. et al. Suspect identification based on descriptive facial attributes. In IEEE International Joint Conference on Biometrics, 1\u20138 (IEEE, 2014).","DOI":"10.1109\/BTAS.2014.6996255"},{"key":"26751_CR62","unstructured":"Freund, R. J., Mohr, D. & Wilson, W. J.Statistical Methods (Academic Press, 2010)."},{"key":"26751_CR63","unstructured":"Ridgeway, K. & Mozer, M. C. Learning deep disentangled embeddings with the F-statistic loss. In Proceedings of Advances in Neural Information Processing Systems, NeurIPS, Vol. 31, 185\u2013194 (NeurIPS, 2017)."},{"key":"26751_CR64","doi-asserted-by":"publisher","first-page":"83","DOI":"10.1002\/nav.3800020109","volume":"2","author":"HW Kuhn","year":"1955","unstructured":"Kuhn, H. W. The Hungarian method for the assignment problem. Naval Research Logistics Quarterly 2, 83\u201397 (1955).","journal-title":"Naval Research Logistics Quarterly"},{"key":"26751_CR65","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1137\/0105003","volume":"5","author":"J Munkres","year":"1957","unstructured":"Munkres, J. Algorithms for the assignment and transportation problems. J. Soc. Ind. Appl. Math. 5, 32\u201338 (1957).","journal-title":"J. Soc. Ind. Appl. Math."}],"container-title":["Nature Communications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.nature.com\/articles\/s41467-021-26751-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-021-26751-5","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/www.nature.com\/articles\/s41467-021-26751-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T12:16:39Z","timestamp":1669983399000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.nature.com\/articles\/s41467-021-26751-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,11,9]]},"references-count":65,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2021,12]]}},"alternative-id":["26751"],"URL":"https:\/\/doi.org\/10.1038\/s41467-021-26751-5","relation":{},"ISSN":["2041-1723"],"issn-type":[{"value":"2041-1723","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,11,9]]},"assertion":[{"value":"15 December 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 October 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 November 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no competing interests.","order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}],"article-number":"6456"}}