{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:33:48Z","timestamp":1742913228636,"version":"3.40.3"},"publisher-location":"Cham","reference-count":31,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031431524"},{"type":"electronic","value":"9783031431531"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023]]},"DOI":"10.1007\/978-3-031-43153-1_33","type":"book-chapter","created":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T21:01:55Z","timestamp":1693861315000},"page":"393-405","update-policy":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Enhancing Hierarchical Vector Quantized Autoencoders for\u00a0Image Synthesis Through Multiple Decoders"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0009-0003-4006-3575","authenticated-orcid":false,"given":"Dario","family":"Serez","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-0523-6042","authenticated-orcid":false,"given":"Marco","family":"Cristani","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-8645-2328","authenticated-orcid":false,"given":"Vittorio","family":"Murino","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0002-2262-4872","authenticated-orcid":false,"given":"Alessio","family":"Del Bue","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/2.zoppoz.workers.dev:443\/https\/orcid.org\/0000-0001-5259-1496","authenticated-orcid":false,"given":"Pietro","family":"Morerio","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,5]]},"reference":[{"key":"33_CR1","unstructured":"Adiban, M., Stefanov, K., Siniscalchi, S.M., Salvi, G.: Hierarchical residual learning based vector quantized variational autoencoder for image reconstruction and generation. In: British Machine Vision Conference (2022)"},{"key":"33_CR2","doi-asserted-by":"crossref","unstructured":"Chang, H., Zhang, H., Jiang, L., Liu, C., Freeman, W.T.: MaskGIT: masked generative image transformer. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11315\u201311325 (2022)","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"33_CR3","doi-asserted-by":"publisher","unstructured":"Deng, J., Dong, W., Socher, R., Li, L.J., Li, K., Fei-Fei, L.: Imagenet: a large-scale hierarchical image database. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 248\u2013255 (2009). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/CVPR.2009.5206848","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"33_CR4","unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., Sutskever, I.: Jukebox: a generative model for music. arXiv:abs\/2005.00341 (2020)"},{"key":"33_CR5","unstructured":"Dosovitskiy, A., et al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv:abs\/2010.11929 (2021)"},{"key":"33_CR6","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12868\u201312878 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"33_CR7","unstructured":"Fauw, J.D., Dieleman, S., Simonyan, K.: Hierarchical autoregressive image models with auxiliary decoders. arXiv:abs\/1903.04933 (2019)"},{"key":"33_CR8","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: NIPS (2017)"},{"key":"33_CR9","doi-asserted-by":"crossref","unstructured":"Isola, P., Zhu, J.Y., Zhou, T., Efros, A.A.: Image-to-image translation with conditional adversarial networks. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5967\u20135976 (2017)","DOI":"10.1109\/CVPR.2017.632"},{"key":"33_CR10","unstructured":"Jang, E., Gu, S.S., Poole, B.: Categorical reparameterization with gumbel-softmax. arXiv:abs\/1611.01144 (2017)"},{"key":"33_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"33_CR12","unstructured":"Kaiser, \u0141., et al.: Fast decoding in sequence models using discrete latent variables. In: International Conference on Machine Learning (2018)"},{"key":"33_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. CoRR abs\/1412.6980 (2015)"},{"key":"33_CR14","doi-asserted-by":"crossref","unstructured":"Lee, D., Kim, C., Kim, S., Cho, M., Han, W.S.: Autoregressive image generation using residual quantization. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 11513\u201311522 (2022)","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"33_CR15","doi-asserted-by":"crossref","unstructured":"Liu, Z., Luo, P., Wang, X., Tang, X.: Deep learning face attributes in the wild. In: Proceedings of International Conference on Computer Vision (ICCV), December (2015)","DOI":"10.1109\/ICCV.2015.425"},{"key":"33_CR16","unstructured":"Maddison, C.J., Mnih, A., Teh, Y.W.: The concrete distribution: a continuous relaxation of discrete random variables. arXiv:abs\/1611.00712 (2017)"},{"key":"33_CR17","doi-asserted-by":"publisher","unstructured":"Detlefsen, N.S., et al.: TorchMetrics - Measuring Reproducibility in PyTorch (2022). https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.21105\/joss.04101, https:\/\/2.zoppoz.workers.dev:443\/https\/github.com\/Lightning-AI\/metrics","DOI":"10.21105\/joss.04101"},{"key":"33_CR18","unstructured":"van den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: NIPS (2017)"},{"key":"33_CR19","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"33_CR20","unstructured":"Razavi, A., Van den Oord, A., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"33_CR21","unstructured":"Roy, A., Vaswani, A., Neelakantan, A., Parmar, N.: Theory and experiments on vector quantized autoencoders. arXiv:abs\/1805.11063 (2018)"},{"key":"33_CR22","unstructured":"Salimans, T., Goodfellow, I., Zaremba, W., Cheung, V., Radford, A., Chen, X.: Improved techniques for training GANs. In: Advances in Neural Information Processing Systems, vol. 29 (2016)"},{"key":"33_CR23","doi-asserted-by":"crossref","unstructured":"Sauer, A., Schwarz, K., Geiger, A.: Stylegan-xl: scaling stylegan to large diverse datasets. In: ACM SIGGRAPH 2022 Conference Proceedings, pp. 1\u201310 (2022)","DOI":"10.1145\/3528233.3530738"},{"key":"33_CR24","doi-asserted-by":"crossref","unstructured":"Karras, T., Samuli Laine, T.A.: A style-based generator architecture for generative adversarial networks. IEEE 3 (2019). https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/8953766","DOI":"10.1109\/CVPR.2019.00453"},{"key":"33_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"33_CR26","doi-asserted-by":"publisher","first-page":"600","DOI":"10.1109\/TIP.2003.819861","volume":"13","author":"Z Wang","year":"2004","unstructured":"Wang, Z., Bovik, A.C., Sheikh, H.R., Simoncelli, E.P.: Image quality assessment: from error visibility to structural similarity. IEEE Trans. Image Process. 13, 600\u2013612 (2004)","journal-title":"IEEE Trans. Image Process."},{"key":"33_CR27","first-page":"4524","volume":"33","author":"W Williams","year":"2020","unstructured":"Williams, W., Ringer, S., Ash, T., MacLeod, D., Dougherty, J., Hughes, J.: Hierarchical quantized autoencoders. Adv. Neural. Inf. Process. Syst. 33, 4524\u20134535 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"33_CR28","unstructured":"Yu, J., et al.: Vector-quantized image modeling with improved vqgan. arXiv:abs\/2110.04627 (2022)"},{"key":"33_CR29","unstructured":"Yu, J., et al.: Scaling autoregressive models for content-rich text-to-image generation. arXiv:abs\/2206.10789 (2022)"},{"key":"33_CR30","doi-asserted-by":"crossref","unstructured":"Zhang, R., Isola, P., Efros, A.A., Shechtman, E., Wang, O.: The unreasonable effectiveness of deep features as a perceptual metric. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 586\u2013595 (2018)","DOI":"10.1109\/CVPR.2018.00068"},{"key":"33_CR31","first-page":"23412","volume":"35","author":"C Zheng","year":"2022","unstructured":"Zheng, C., Vuong, T.L., Cai, J., Phung, D.: MOVQ: modulating quantized vectors for high-fidelity image generation. Adv. Neural. Inf. Process. Syst. 35, 23412\u201323425 (2022)","journal-title":"Adv. Neural. Inf. Process. Syst."}],"container-title":["Lecture Notes in Computer Science","Image Analysis and Processing \u2013 ICIAP 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-43153-1_33","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,13]],"date-time":"2024-03-13T11:38:11Z","timestamp":1710329891000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/link.springer.com\/10.1007\/978-3-031-43153-1_33"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031431524","9783031431531"],"references-count":31,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1007\/978-3-031-43153-1_33","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"5 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIAP","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image Analysis and Processing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Udine","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"22","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"iciap2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/www.iciap2023.org\/","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":"144","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":"85","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":"7","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":"59% - 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","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","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)"}},{"value":"https:\/\/2.zoppoz.workers.dev:443\/https\/iciap2023.org\/satellite-event\/workshops\/","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}