{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T17:17:17Z","timestamp":1777569437344,"version":"3.51.4"},"publisher-location":"Cham","reference-count":41,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200496","type":"print"},{"value":"9783031200502","type":"electronic"}],"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\/978-3-031-20050-2_5","type":"book-chapter","created":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:09:58Z","timestamp":1666908598000},"page":"70-86","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":22,"title":["Improved Masked Image Generation with\u00a0Token-Critic"],"prefix":"10.1007","author":[{"given":"Jos\u00e9","family":"Lezama","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huiwen","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Irfan","family":"Essa","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,10,28]]},"reference":[{"key":"5_CR1","unstructured":"Austin, J., Johnson, D., Ho, J., Tarlow, D., van den Berg, R.: Structured denoising diffusion models in discrete state-spaces. In: 34th Proceedings of the International Conference on Advances in Neural Information Processing Systems 34 (2021)"},{"key":"5_CR2","unstructured":"Ba, J.L., Kiros, J.R., Hinton, G.E.: Layer normalization. arXiv preprint arXiv:1607.06450 (2016)"},{"key":"5_CR3","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"5_CR4","unstructured":"Brown, T., et al.: Language models are few-shot learners. In: NeurIPS (2020)"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MasKGIT: masked generative image transformer. arXiv preprint arXiv:2202.04200 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"5_CR6","unstructured":"Chen, M., Radford, A., Child, R., Wu, J., Jun, H., Luan, D., SutsKever, I.: generative pretraining from pixels. In: International Conference on Machine Learning, pp. 1691\u20131703. PMLR (2020)"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Deng, J., et al.: ImageUet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"5_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"5_CR9","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: 34th Proceedings of the International Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"5_CR10","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. In: ICLR (2021)"},{"key":"5_CR11","unstructured":"Esser, P., Rombach, R., Blattmann, A., Ommer, B.: Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis. In: 34th Proceedings of the International Conference on Advances in Neural Information Processing Systems (2021)"},{"key":"5_CR12","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"5_CR13","doi-asserted-by":"crossref","unstructured":"Ghazvininejad, M., Levy, O., Liu, Y., Zettlemoyer, L.: Mask-predict: parallel decoding of conditional masked language models. In: EMNLP-IJCNLP (2019)","DOI":"10.18653\/v1\/D19-1633"},{"key":"5_CR14","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: NeurIPS (2014)"},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Gu, J., Kong, X.: Fully non-autoregressive neural machine translation: tricks of the trade. In: Findings of ACL-IJCNLP (2021)","DOI":"10.18653\/v1\/2021.findings-acl.11"},{"key":"5_CR16","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. arXiv preprint arXiv:2111.14822 (2021)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"5_CR18","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: 30th Proceedings of the International Conference on Advances in Neural Information Processing Systems (2017)"},{"issue":"47","key":"5_CR19","first-page":"1","volume":"23","author":"J Ho","year":"2022","unstructured":"Ho, J., Saharia, C., Chan, W., Fleet, D.J., Norouzi, M., Salimans, T.: Cascaded diffusion models for high fidelity image generation. J. Mach. Learn. Res. 23(47), 1\u201333 (2022)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR20","unstructured":"Hoogeboom, E., Nielsen, D., Jaini, P., Forr\u00e9, P., Welling, M.: Argmax flows and multinomial diffusion: Learning categorical distributions. In: Thirty-Fifth Conference on Neural Information Processing Systems (2021)"},{"key":"5_CR21","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of StyleGAN. In: CVPR (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"5_CR22","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"5_CR23","unstructured":"Kingma, D.P., Salimans, T., Poole, B., Ho, J.: Variational diffusion models. arXiv preprint arXiv:2107.00630 (2021)"},{"key":"5_CR24","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"5_CR25","doi-asserted-by":"crossref","unstructured":"Kong, X., Jiang, L., Chang, H., Zhang, H., Hao, Y., Gong, H., Essa, I.: BLT: bidirectional layout transformer for controllable layout generation. arXiv preprint arXiv:2112.05112 (2021)","DOI":"10.1007\/978-3-031-19790-1_29"},{"key":"5_CR26","doi-asserted-by":"crossref","unstructured":"Kong, X., Zhang, Z., Hovy, E.: Incorporating a local translation mechanism into non-autoregressive translation. arXiv preprint arXiv:2011.06132 (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.79"},{"key":"5_CR27","unstructured":"Kynk\u00e4\u00e4nniemi, T., Karras, T., Laine, S., Lehtinen, J., Aila, T.: Improved precision and recall metric for assessing generative models. In: 32nd Proceedings of the International Conference on Advances in Neural Information Processing Systems 32 (2019)"},{"key":"5_CR28","unstructured":"Nichol, A., Dhariwal, P.: Improved denoising diffusion probabilistic models. arXiv preprint arXiv:2102.09672 (2021)"},{"key":"5_CR29","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Guyon, I., von Luxburg, U., Bengio, S., Wallach, H.M., Fergus, R., Vishwanathan, S.V.N., Garnett, R. (eds.) NeurIPS (2017)"},{"key":"5_CR30","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: Meila, M., Zhang, T. (eds.) ICML (2021)"},{"key":"5_CR31","unstructured":"Razavi, A., Van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with VQ-VAE-2. In: 32nd Proceedings of the International Conference on Advances in Neural Information Processing Systems (2019)"},{"key":"5_CR32","unstructured":"Rezende, D., Mohamed, S.: Variational inference with normalizing flows. In: International Conference on Machine Learning, pp. 1530\u20131538 (2015)"},{"key":"5_CR33","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: 29th Proceedings of the International Conference on Advances in Neural Information Processing Systems (2016)"},{"key":"5_CR34","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: Stylegan-xl: Scaling styleGan to large diverse datasets. arXiv preprint arXiv:2202.00273 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"5_CR35","unstructured":"Seff, A., Zhou, W., Damani, F., Doyle, A., Adams, R.P.: Discrete object generation with reversible inductive construction. In: 32nd Proceedings of the International Conference on Advances in Neural Information Processing Systems (2019)"},{"key":"5_CR36","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"5_CR37","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"5_CR38","unstructured":"Vahdat, A., Kautz, J.: Nvae: a deep hierarchical variational autoencoder. In: Proceedings of the International Conference on Advances in Neural Information Processing Systems (2020)"},{"key":"5_CR39","unstructured":"Vaswani, A., et al.: Attention is all you need. In: 30tth Proceedings of the International Conference on Advances in Neural Information Processing systems (2017)"},{"key":"5_CR40","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved VQGAN. arXiv preprint arXiv:2110.04627 (2021)"},{"key":"5_CR41","unstructured":"Zhang, Z., et al.: M6-UFC: unifying multi-modal controls for conditional image synthesis. arXiv preprint arXiv:2105.14211 (2021)"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20050-2_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,10,27]],"date-time":"2022-10-27T22:23:11Z","timestamp":1666909391000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20050-2_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200496","9783031200502"],"references-count":41,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20050-2_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"28 October 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","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":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1645","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"28% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.21","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3.91","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}