{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,18]],"date-time":"2026-01-18T08:35:12Z","timestamp":1768725312208,"version":"3.49.0"},"reference-count":62,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T00:00:00Z","timestamp":1647907200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T00:00:00Z","timestamp":1647907200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100002920","name":"Research Grants Council, University Grants Committee","doi-asserted-by":"publisher","award":["No.24206219"],"award-info":[{"award-number":["No.24206219"]}],"id":[{"id":"10.13039\/501100002920","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2022,5]]},"DOI":"10.1007\/s11263-022-01598-5","type":"journal-article","created":{"date-parts":[[2022,3,22]],"date-time":"2022-03-22T06:02:50Z","timestamp":1647928970000},"page":"1259-1276","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":20,"title":["Disentangled Inference for GANs With Latently Invertible Autoencoder"],"prefix":"10.1007","volume":"130","author":[{"given":"Jiapeng","family":"Zhu","sequence":"first","affiliation":[]},{"given":"Deli","family":"Zhao","sequence":"additional","affiliation":[]},{"given":"Bo","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Bolei","family":"Zhou","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,3,22]]},"reference":[{"key":"1598_CR1","doi-asserted-by":"crossref","unstructured":"Abdal, R., Qin, Y., & Wonka, P. (2019). Image2StyleGAN: How to embed images into the StyleGAN latent space?. In Proceedings of international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2019.00453"},{"key":"1598_CR2","unstructured":"Antoniou, A., Storkey, A., & Edwards, H. (2017). Data augmentation generative adversarial networks. arXiv:1711.04340."},{"key":"1598_CR3","unstructured":"Arjovsky, M., Chintala, S., & Bottou, L. (2017). Wasserstein GAN. In arXiv:1701.07875."},{"key":"1598_CR4","doi-asserted-by":"publisher","first-page":"1373","DOI":"10.1162\/089976603321780317","volume":"15","author":"M Belkin","year":"2003","unstructured":"Belkin, M., & Niyogi, P. (2003). Laplacian eigenmaps for dimensionality reduction and data representation. Neural Computation, 15, 1373\u20131396.","journal-title":"Neural Computation"},{"key":"1598_CR5","unstructured":"Berthelot, D., Schumm, T., & Metz, L. (2017). BEGAN: Boundary equilibrium generative adversarial networks. arXiv:1703.10717."},{"key":"1598_CR6","doi-asserted-by":"crossref","unstructured":"Bowman, S. R., Vilnis, L., Vinyals, O., Dai, A. M., Jozefowicz, R., & Bengio, S. (2015). Generating sentences from a continuous space. In arXiv:1511.06349.","DOI":"10.18653\/v1\/K16-1002"},{"key":"1598_CR7","unstructured":"Brock, A., Donahue, J., & Simonyan, K. (2018). Large scale GAN training for high fidelity natural image synthesis. In arXiv:1809.11096."},{"key":"1598_CR8","unstructured":"Creswell, A., & Bharath, A. A. (2016). Inverting the generator of a generative adversarial network. In Proceedings of the 30th international conference on neural information processing."},{"key":"1598_CR9","unstructured":"Dinh, L., Krueger, D., & Bengio, Y. (2015). NICE: Non-linear independent components estimation. In International conference on learning representations (ICLR)."},{"key":"1598_CR10","unstructured":"Dinh, L., Sohl-Dickstein, J., & Bengio, S. (2017). Density estimation using Real NVP. In International conference on learning representations (ICLR)."},{"key":"1598_CR11","unstructured":"Doersch, C. (2016). Tutorial on variational autoencoders. arXiv:1606.05908."},{"key":"1598_CR12","unstructured":"Donahue, J., & Simonyan, K. (2019). Large scale adversarial representation learning. arXiv:1907.02544."},{"key":"1598_CR13","unstructured":"Donahue, J., Krahenbuhl, P., & Darrell, T. (2017). Adversarial feature learning. In International conference on learning representations (ICLR)."},{"key":"1598_CR14","unstructured":"Dumoulin, V., Belghazi, I., Poole, B., Mastropietro, O., Lamb, A., Arjovsky, M., & Courville, A. (2017). Adversarially learned inference. In International conference on learning representations (ICLR)."},{"issue":"6394","key":"1598_CR15","doi-asserted-by":"publisher","first-page":"1204","DOI":"10.1126\/science.aar6170","volume":"360","author":"SMA Eslami","year":"2018","unstructured":"Eslami, S. M. A., Rezende, D. J., Besse, F., Viola, F., Morcos, A. S., Garnelo, M., Ruderman, A., Rusu, A. A., Danihelka, I., Gregor, K., Reichert, D. P., Buesing, L., Weber, T., Vinyals, O., Rosenbaum, D., Rabinowitz, N., King, H., Hillier, C., Botvinick, M., & Hassabis, D. (2018). Neural scene representation and rendering. Science, 360(6394), 1204\u20131210.","journal-title":"Science"},{"key":"1598_CR16","unstructured":"Goodfellow, I. J., Pouget-Abadie, J., Mirza, M., Xu, B., Warde-Farley, D., Ozair, S., Courville, A., & Bengio, Y. (2014). Generative adversarial networks. In Proceedings of the 28th International Conference on Neural Information Processing Systems."},{"key":"1598_CR17","unstructured":"Grover, A., Dhar, M., & Ermon, S. (2017). Flow-GAN: Combining maximum likelihood and adversarial learning in generative models. In arXiv:1705.08868."},{"key":"1598_CR18","unstructured":"Gulrajani, I., Ahmed, F., Arjovsky, M., Dumoulin, V., & Courville, A. (2017). Improved training of Wasserstein GANs. In arXiv:1704.00028."},{"key":"1598_CR19","unstructured":"Heljakka, A., Solin, A., & Kannala, J. (2018). Pioneer networks: Progressively growing generative autoencoder. In arXiv:1807.03026."},{"key":"1598_CR20","doi-asserted-by":"crossref","unstructured":"Huang, X., & Belongie, S. (2017). Arbitrary style transfer in real-time with adaptive instance normalization. In Proceedings of international conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.167"},{"key":"1598_CR21","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J. Y., Zhou, T., & Efros, A. A. (2017). Image-to-image translation with conditional adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2017.632"},{"key":"1598_CR22","doi-asserted-by":"crossref","unstructured":"Johnson, J., Alahi, A., & Fei-Fei, L. (2016). Perceptual losses for real-time style transfer and super-resolution. arXiv:1603.08155.","DOI":"10.1007\/978-3-319-46475-6_43"},{"key":"1598_CR23","unstructured":"Karras, T., Aila, T., Laine, S., & Lehtinen, J. (2018a). Progressive growing of GANs for improved quality, stability, and variation. In Proceedings of the 6th international conference on learning representations (ICLR)."},{"key":"1598_CR24","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., & Aila, T. (2018b). A style-based generator architecture for generative adversarial networks. arXiv:1812.04948.","DOI":"10.1109\/CVPR.2019.00453"},{"key":"1598_CR25","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., & Aila, T. (2019). Analyzing and improving the image quality of StyleGAN. arXiv:1912.04958.","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"1598_CR26","unstructured":"Kingma, D. P., & Dhariwal, P. (2018). Glow: Generative flow with invertible 1x1 convolutions. In arXiv:1807.03039."},{"key":"1598_CR27","unstructured":"Kingma, D. P., & Welling, M. (2013). Auto-encoding variational Bayes. In Proceedings of the 2th international conference on learning representations (ICLR)."},{"key":"1598_CR28","unstructured":"Kingma, D. P., Salimans, T., Jozefowicz, R., Chen, X., Sutskever, I., & Welling, M. (2016). Improving variational inference with inverse autoregressive flow. In arXiv:1606.04934."},{"key":"1598_CR29","unstructured":"Larsen, A. B. L., S\u00f8nderby, S. K., Larochelle, H., & Winther, O. (2016). Autoencoding beyond pixels using a learned similarity metric. In International conference on machine learning (ICML), pp. 1558\u20131566."},{"key":"1598_CR30","unstructured":"Lehtinen, J., Munkberg, J., Hasselgren, J., Laine, S., Karras, T., Aittala, M., & Aila, T. (2018). Noise2Noise: Learning image restoration without clean data. In Proceedings of the 35th international conference on machine learning (ICML)."},{"key":"1598_CR31","unstructured":"Lipton, Z. C., & Tripathi, S. (2017). Precise recovery of latent vectors from generative adversarial networks. In International conference on learning representations (ICLR)."},{"key":"1598_CR32","unstructured":"Lucas, J., Tucker, G., Grosse, R., & Norouzi, M. (2019a). Understanding posterior collapse in generative latent variable models. In Proceedings of international conference on learning representations (ICLR)."},{"key":"1598_CR33","unstructured":"Lucas, T., Shmelkov, K., Alahari, K., Schmid, C., & Verbeek, J. (2019b). Adversarial training of partially invertible variational autoencoders. arXiv:1901.01091."},{"key":"1598_CR34","doi-asserted-by":"crossref","unstructured":"Luo, J., Xu, Y., Tang, C., & Lv, J. (2017). Learning inverse mapping by autoencoder based generative adversarial nets. In arXiv:1703.10094.","DOI":"10.1007\/978-3-319-70096-0_22"},{"key":"1598_CR35","unstructured":"Makhani, A. (2018). Implicit autoencoders. In arXiv:1805.09804."},{"key":"1598_CR36","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., & Frey, B. (2015). Adversarial autoencoders. In arXiv:1511.05644."},{"key":"1598_CR37","unstructured":"Mescheder, L., Geiger, A., & Nowozin, S. (2018). Which training methods for GANs do actually converge? arXiv:1801.04406."},{"key":"1598_CR38","unstructured":"van\u00a0den Oord, A., Dieleman, S., Zen, H., Simonyan, K., Vinyals, O., Graves, A., Kalchbrenner, N., Senior, A., & Kavukcuoglu, K. (2016). WaveNet: A generative model for raw audio. In arXiv:1609.03499."},{"key":"1598_CR39","unstructured":"van\u00a0den Oord, A., Li, Y., Babuschkin, I., Simonyan, K., Vinyals, O., Kavukcuoglu, K., van\u00a0den Driessche, G., Lockhart, E., Cobo, L. C., Stimberg, F., Casagrande, N., Grewe, D., Noury, S., Dieleman, S., Elsen, E., Kalchbrenner, N., Zen, H., Graves, A., King, H., Walters, T., Belov, D., & Hassabis, D. (2017). Parallel WaveNet: Fast high-fidelity speech synthesis. In arXiv:1711.10433."},{"key":"1598_CR40","unstructured":"van\u00a0den Oord, A., Li, Y., & Vinyals, O. (2018). Representation learning with contrastive predictive coding. arXiv:1807.03748."},{"key":"1598_CR41","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., & Hinton, G. (2008). Visualizing data using t-SNE. Journal of Machine Learning Research, 9, 2579\u20132605.","journal-title":"Journal of Machine Learning Research"},{"key":"1598_CR42","doi-asserted-by":"crossref","unstructured":"Pidhorskyi, S., Adjeroh. D. A., & Doretto, G. (2020). Adversarial latent autoencoders. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.01411"},{"key":"1598_CR43","unstructured":"Radford, A., Metz, L., & Chintala, S. (2016). Unsupervised representation learning with deep convolutional generative adversarial networks. In Proceedings of the 4th international conference on learning representations (ICLR)."},{"issue":"5500","key":"1598_CR44","doi-asserted-by":"publisher","first-page":"2323","DOI":"10.1126\/science.290.5500.2323","volume":"290","author":"ST Roweis","year":"2000","unstructured":"Roweis, S. T., & Saul, L. K. (2000). Nonlinear dimensionality reduction by locally linear embedding. Science, 290(5500), 2323\u20132326.","journal-title":"Science"},{"key":"1598_CR45","doi-asserted-by":"crossref","unstructured":"Sankaranarayanan, S., Balaji, Y., Castillo, C. D., & Chellappa, R. (2017). Generate to adapt: Aligning domains using generative adversarial networks. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00887"},{"key":"1598_CR46","doi-asserted-by":"crossref","unstructured":"Shen, Y., Gu, J., Tang, X., & Zhou, B. (2020a). Interpreting the latent space of GANs for semantic face editing. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR42600.2020.00926"},{"key":"1598_CR47","doi-asserted-by":"crossref","unstructured":"Shen, Y., Yang, C., Tang, X., & Zhou, B. (2020b). InterfaceGAN: Interpreting the disentangled face representation learned by GANs. IEEE transactions on pattern analysis and machine intelligence, 44(4), 2004\u20132018.","DOI":"10.1109\/TPAMI.2020.3034267"},{"key":"1598_CR48","unstructured":"Simonyan, K., & Zisserman, A. (2014). Very deep convolutional networks for large-scale image recognition. CoRR abs\/1409.1556."},{"key":"1598_CR49","unstructured":"Su, J., & Wu, G. (2018). f-VAEs: Improve VAEs with conditional flows. In arXiv:1809.05861."},{"issue":"5500","key":"1598_CR50","doi-asserted-by":"publisher","first-page":"2319","DOI":"10.1126\/science.290.5500.2319","volume":"290","author":"JB Tenenbaum","year":"2000","unstructured":"Tenenbaum, J. B., de Silva, V., & Langford, J. C. (2000). A global geometric framework for nonlinear dimensionality reduction. Science, 290(5500), 2319\u20132323.","journal-title":"Science"},{"key":"1598_CR51","unstructured":"Ulyanov, D., Vedaldi, A., & Lempitsky, V. (2017). It takes (only) two: Adversarial generator-encoder networks. In arXiv:1704.02304."},{"key":"1598_CR52","doi-asserted-by":"crossref","unstructured":"Wang, J., Yu, L., Zhang, W., Gong, Y., Xu, Y., Wang, B., Zhang, P., & Zhang, D. (2017). IRGAN: A minimax game for unifying generative and discriminative information retrieval models. In Proceedings of the 40th international ACM SIGIR conference on research and development in information retrieval.","DOI":"10.1145\/3077136.3080786"},{"key":"1598_CR53","unstructured":"Wu, J., Zhang, C., Xue, T., Freeman, W. T., & Tenenbaum, J. B. (2016). Learning a probabilistic latent space of object shapes via 3D generative adversarial modeling. In Proceedings of the 30th international conference on neural information processing."},{"key":"1598_CR54","unstructured":"Xiao, Z., Yan, Q., & Amit, Y. (2019). Generative latent flow. arXiv:1905.10485."},{"key":"1598_CR55","doi-asserted-by":"crossref","unstructured":"Yang, C., Shen, Y., & Zhou, B. (2021). Semantic hierarchy emerges in deep generative representations for scene synthesis. International Journal of Computer Vision, 129(5), 1451\u20131466.","DOI":"10.1007\/s11263-020-01429-5"},{"key":"1598_CR56","unstructured":"Yu, F., Seff, A., Zhang, Y., Song, S., Funkhouser, T., & Xiao, J. (2015). LSUN: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv:1506.03365."},{"key":"1598_CR57","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A. A., Shechtman, E., & Wang, O. (2018). The unreasonable effectiveness of deep features as a perceptual metric. In Proceedings of the IEEE conference on computer vision and pattern recognition (CVPR).","DOI":"10.1109\/CVPR.2018.00068"},{"issue":"1","key":"1598_CR58","doi-asserted-by":"publisher","first-page":"313","DOI":"10.1137\/S1064827502419154","volume":"26","author":"Z Zhang","year":"2004","unstructured":"Zhang, Z., & Zha, H. (2004). Principal manifolds and nonlinear dimensionality reduction via tangent space alignment. SIAM Journal on Scientific Computing, 26(1), 313\u2013338.","journal-title":"SIAM Journal on Scientific Computing"},{"key":"1598_CR59","unstructured":"Zhou, D., Weston, J., Gretton, A., Bousquet, O., & Sch\u00f6lkopf, B. (2003). Ranking on data manifolds. In Proceedings of the 16th international conference on neural information processing systems (NeurIPS)."},{"key":"1598_CR60","doi-asserted-by":"publisher","first-page":"487","DOI":"10.1038\/nature25988","volume":"555","author":"B Zhu","year":"2018","unstructured":"Zhu, B., Liu, J. Z., Cauley, S. F., Rosen, B. R., & Rosen, M. S. (2018). Image reconstruction by domain-transform manifold learning. Nature, 555, 487\u2013492.","journal-title":"Nature"},{"key":"1598_CR61","doi-asserted-by":"crossref","unstructured":"Zhu, J., Shen, Y., Zhao, D., & Zhou, B. (2020). In-domain GAN inversion for real image editing. In Proceedings of european conference on computer vision (ECCV).","DOI":"10.1007\/978-3-030-58520-4_35"},{"key":"1598_CR62","doi-asserted-by":"crossref","unstructured":"Zhu, J. Y., Park, T., Isola, P., & Efros, A. A. (2017). Unpaired image-to-image translation using cycle-consistent adversarial networks. In International conference on computer vision (ICCV).","DOI":"10.1109\/ICCV.2017.244"}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01598-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11263-022-01598-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-022-01598-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,4,27]],"date-time":"2022-04-27T11:18:22Z","timestamp":1651058302000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11263-022-01598-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,3,22]]},"references-count":62,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2022,5]]}},"alternative-id":["1598"],"URL":"https:\/\/doi.org\/10.1007\/s11263-022-01598-5","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,3,22]]},"assertion":[{"value":"1 May 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 January 2022","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"22 March 2022","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}