{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T15:50:50Z","timestamp":1742917850678,"version":"3.40.3"},"publisher-location":"Cham","reference-count":42,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031090363"},{"type":"electronic","value":"9783031090370"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-09037-0_45","type":"book-chapter","created":{"date-parts":[[2022,6,1]],"date-time":"2022-06-01T04:26:16Z","timestamp":1654057576000},"page":"553-566","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Compositing Foreground and\u00a0Background Using Variational Autoencoders"],"prefix":"10.1007","author":[{"given":"Zezhen","family":"Zeng","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathon","family":"Hare","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Adam","family":"Pr\u00fcgel-Bennett","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,6,2]]},"reference":[{"key":"45_CR1","doi-asserted-by":"crossref","unstructured":"Bouchacourt, D., Tomioka, R., Nowozin, S.: Multi-level variational autoencoder: learning disentangled representations from grouped observations. In: Proceedings of the AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.11867"},{"key":"45_CR2","unstructured":"Brock, A., Lim, T., Ritchie, J.M., Weston, N.: Neural photo editing with introspective adversarial networks. In: Proceedings of International Conference on Learning Representations (2017)"},{"key":"45_CR3","unstructured":"Burgess, C.P., et al.: Monet: unsupervised scene decomposition and representation. arXiv preprint arXiv:1901.11390 (2019)"},{"key":"45_CR4","unstructured":"Che, T., Li, Y., Jacob, A.P., Bengio, Y., Li, W.: Mode regularized generative adversarial networks. In: Proceedings of International Conference on Learning Representations (2017)"},{"key":"45_CR5","unstructured":"Chen, M., Arti\u00e8res, T., Denoyer, L.: Unsupervised object segmentation by redrawing. In: Advances in Neural Information Processing Systems (2019)"},{"key":"45_CR6","unstructured":"Chen, T.Q., Li, X., Grosse, R.B., Duvenaud, D.K.: Isolating sources of disentanglement in variational autoencoders. In: Advances in Neural Information Processing Systems, pp. 2610\u20132620 (2018)"},{"key":"45_CR7","unstructured":"Chen, X., Duan, Y., Houthooft, R., Schulman, J., Sutskever, I., Abbeel, P.: InfoGAN: interpretable representation learning by information maximizing generative adversarial nets. In: Advances in Neural Information Processing Systems. pp. 2172\u20132180 (2016)"},{"key":"45_CR8","unstructured":"Cheung, B., Livezey, J.A., Bansal, A.K., Olshausen, B.A.: Discovering hidden factors of variation in deep networks. arXiv preprint arXiv:1412.6583 (2014)"},{"key":"45_CR9","doi-asserted-by":"crossref","unstructured":"Crawford, E., Pineau, J.: Spatially invariant unsupervised object detection with convolutional neural networks. In: Proceedings of the AAAI Conference on Artificial Intelligence. pp. 3412\u20133420 (2019)","DOI":"10.1609\/aaai.v33i01.33013412"},{"key":"45_CR10","unstructured":"Cui, K., Zhang, G., Zhan, F., Huang, J., Lu, S.: Fbc-gan: diverse and flexible image synthesis via foreground-background composition. arXiv preprint arXiv:2107.03166 (2021)"},{"key":"45_CR11","doi-asserted-by":"crossref","unstructured":"Dubrovina, A., Xia, F., Achlioptas, P., Shalah, M., Groscot, R., Guibas, L.J.: Composite shape modeling via latent space factorization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8140\u20138149 (2019)","DOI":"10.1109\/ICCV.2019.00823"},{"key":"45_CR12","unstructured":"Engelcke, M., Kosiorek, A.R., Jones, O.P., Posner, I.: Genesis: generative scene inference and sampling with object-centric latent representations. In: International Conference on Learning Representations (2020)"},{"key":"45_CR13","doi-asserted-by":"crossref","unstructured":"Esser, P., Sutter, E., Ommer, B.: A variational u-net for conditional appearance and shape generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 8857\u20138866 (2018)","DOI":"10.1109\/CVPR.2018.00923"},{"key":"45_CR14","unstructured":"Greff, K., et al.: Multi-object representation learning with iterative variational inference. In: International Conference on Machine Learning, pp. 2424\u20132433. PMLR (2019)"},{"key":"45_CR15","doi-asserted-by":"crossref","unstructured":"Harsh Jha, A., Anand, S., Singh, M., Veeravasarapu, V.: Disentangling factors of variation with cycle-consistent variational auto-encoders. In: Proceedings of the European Conference on Computer Vision (ECCV), pp. 805\u2013820 (2018)","DOI":"10.1007\/978-3-030-01219-9_49"},{"key":"45_CR16","unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems, pp. 6626\u20136637 (2017)"},{"key":"45_CR17","unstructured":"Higgins, I., et al.: Beta-VAE: learning basic visual concepts with a constrained variational framework. In: Proceedings of International Conference on Learning Representations (2017)"},{"key":"45_CR18","unstructured":"Hoffman, M.D., Johnson, M.J.: Elbo surgery: yet another way to carve up the variational evidence lower bound. In: Workshop in Advances in Approximate Bayesian Inference (2016)"},{"key":"45_CR19","unstructured":"Huang, H., He, R., Sun, Z., Tan, T., et al.: IntroVAE: introspective variational autoencoders for photographic image synthesis. In: Advances in Neural Information Processing Systems, pp. 52\u201363 (2018)"},{"key":"45_CR20","unstructured":"Khosla, A., Jayadevaprakash, N., Yao, B., Fei-Fei, L.: Novel dataset for fine-grained image categorization. In: First Workshop on Fine-Grained Visual Categorization, IEEE Conference on Computer Vision and Pattern Recognition, Colorado Springs, CO (June 2011)"},{"key":"45_CR21","unstructured":"Kim, H., Mnih, A.: Disentangling by factorising. In: International Conference on Machine Learning, pp. 2649\u20132658. PMLR (2018)"},{"key":"45_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: Proceedings of International Conference on Learning Representations (2015)"},{"key":"45_CR23","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: Proceedings of International Conference on Learning Representations (2013)"},{"key":"45_CR24","doi-asserted-by":"crossref","unstructured":"Krause, J., Stark, M., Deng, J., Fei-Fei, L.: 3d object representations for fine-grained categorization. In: 4th International IEEE Workshop on 3D Representation and Recognition (3dRR-13), Sydney, Australia (2013)","DOI":"10.1109\/ICCVW.2013.77"},{"key":"45_CR25","unstructured":"Kumar, A., Sattigeri, P., Balakrishnan, A.: Variational inference of disentangled latent concepts from unlabeled observations. arXiv preprint arXiv:1711.00848 (2017)"},{"key":"45_CR26","doi-asserted-by":"crossref","unstructured":"Li, Y., Singh, K.K., Ojha, U., Lee, Y.J.: Mixnmatch: multifactor disentanglement and encoding for conditional image generation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2020)","DOI":"10.1109\/CVPR42600.2020.00806"},{"key":"45_CR27","doi-asserted-by":"crossref","unstructured":"Lin, C.H., Yumer, E., Wang, O., Shechtman, E., Lucey, S.: ST-GAN: spatial transformer generative adversarial networks for image compositing. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9455\u20139464 (2018)","DOI":"10.1109\/CVPR.2018.00985"},{"key":"45_CR28","unstructured":"Lin, Z., et al.: Space: unsupervised object-oriented scene representation via spatial attention and decomposition. In: Proceedings of International Conference on Learning Representations (2020)"},{"key":"45_CR29","unstructured":"Makhzani, A., Shlens, J., Jaitly, N., Goodfellow, I., Frey, B.: Adversarial autoencoders. In: Proceedings of International Conference on Learning Representations (2016)"},{"key":"45_CR30","unstructured":"Mathieu, M.F., Zhao, J.J., Zhao, J., Ramesh, A., Sprechmann, P., LeCun, Y.: Disentangling factors of variation in deep representation using adversarial training. In: Advances in Neural Information Processing Systems, pp. 5040\u20135048 (2016)"},{"key":"45_CR31","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"45_CR32","unstructured":"Nash, C., et al.: The multi-entity variational autoencoder. In: NeurIPS Workshops (2017)"},{"key":"45_CR33","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"234","DOI":"10.1007\/978-3-319-24574-4_28","volume-title":"Medical Image Computing and Computer-Assisted Intervention \u2013 MICCAI 2015","author":"O Ronneberger","year":"2015","unstructured":"Ronneberger, O., Fischer, P., Brox, T.: U-Net: convolutional networks for biomedical image segmentation. In: Navab, N., Hornegger, J., Wells, W.M., Frangi, A.F. (eds.) MICCAI 2015. LNCS, vol. 9351, pp. 234\u2013241. Springer, Cham (2015). https:\/\/doi.org\/10.1007\/978-3-319-24574-4_28"},{"key":"45_CR34","doi-asserted-by":"crossref","unstructured":"Schor, N., Katzir, O., Zhang, H., Cohen-Or, D.: Componet: learning to generate the unseen by part synthesis and composition. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 8759\u20138768 (2019)","DOI":"10.1109\/ICCV.2019.00885"},{"key":"45_CR35","doi-asserted-by":"crossref","unstructured":"Singh, K.K., Ojha, U., Lee, Y.J.: Finegan: unsupervised hierarchical disentanglement for fine-grained object generation and discovery. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2019)","DOI":"10.1109\/CVPR.2019.00665"},{"issue":"1","key":"45_CR36","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1207\/s15516709cog1401_3","volume":"14","author":"ES Spelke","year":"1990","unstructured":"Spelke, E.S.: Principles of object perception. Cogn. Sci. 14(1), 29\u201356 (1990)","journal-title":"Cogn. Sci."},{"key":"45_CR37","unstructured":"Srivastava, A., Valkov, L., Russell, C., Gutmann, M.U., Sutton, C.: VEEGAN: reducing mode collapse in GANs using implicit variational learning. In: Advances in Neural Information Processing Systems, pp. 3308\u20133318 (2017)"},{"key":"45_CR38","unstructured":"Szab\u00f3, A., Hu, Q., Portenier, T., Zwicker, M., Favaro, P.: Challenges in disentangling independent factors of variation. arXiv preprint arXiv:1711.02245 (2017)"},{"key":"45_CR39","unstructured":"Welinder, P., et al.: Caltech-ucsd birds 200 (2010)"},{"key":"45_CR40","unstructured":"Xiao, T., Hong, J., Ma, J.: DNA-GAN: learning disentangled representations from multi-attribute images. arXiv preprint arXiv:1711.05415 (2017)"},{"key":"45_CR41","unstructured":"Yang, J., Kannan, A., Batra, D., Parikh, D.: LR-GAN: layered recursive generative adversarial networks for image generation. arXiv preprint arXiv:1703.01560 (2017)"},{"key":"45_CR42","unstructured":"Zhao, S., Song, J., Ermon, S.: InfoVAE: information maximizing variational autoencoders. arXiv preprint arXiv:1706.02262 (2017)"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-09037-0_45","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,27]],"date-time":"2023-06-27T15:30:38Z","timestamp":1687879838000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-09037-0_45"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031090363","9783031090370"],"references-count":42,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-09037-0_45","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"2 June 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Paris","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icprai2022.sciencesconf.org\/1.6.If","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}