{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:19:34Z","timestamp":1782317974429,"version":"3.54.5"},"reference-count":68,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"12","license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Research Grants Council","award":["CityU 11216122"],"award-info":[{"award-number":["CityU 11216122"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1109\/tpami.2024.3424835","type":"journal-article","created":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T18:29:03Z","timestamp":1720549743000},"page":"9612-9629","source":"Crossref","is-referenced-by-count":9,"title":["High-Fidelity and Efficient Pluralistic Image Completion With Transformers"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2421-3484","authenticated-orcid":false,"given":"Ziyu","family":"Wan","sequence":"first","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0009-2315","authenticated-orcid":false,"given":"Jingbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4642-4373","authenticated-orcid":false,"given":"Dongdong","family":"Chen","sequence":"additional","affiliation":[{"name":"Microsoft Cloud+AI, Redmond, WA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7014-5377","authenticated-orcid":false,"given":"Jing","family":"Liao","sequence":"additional","affiliation":[{"name":"Department of Computer Science, City University of Hong Kong, Hong Kong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00282"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3163183"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3256372"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00183"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.488"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.624"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00427"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"ref14","article-title":"Towards deeper understanding of variational autoencoding models","author":"Zhao","year":"2017"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref16","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref17","first-page":"4055","article-title":"Image transformer","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Parmar"},{"key":"ref18","first-page":"4790","article-title":"Conditional image generation with pixelCNN decoders","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van den Oord"},{"key":"ref19","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref20","article-title":"EdgeConnect: Generative image inpainting with adversarial edge learning","author":"Nazeri","year":"2019"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_47"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref23","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01212"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372454"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01717"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475436"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383296"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276382"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185578"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2839351"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3165587"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3001267"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3188169"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01122"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"ref45","article-title":"Large scale image completion via co-modulated generative adversarial networks","author":"Zhao","year":"2021"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01106"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"issue":"8","key":"ref52","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref53","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref54","article-title":"Instance normalization: The missing ingredient for fast stylization","author":"Ulyanov","year":"2016"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref58","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref59","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref60","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01390"},{"key":"ref63","first-page":"23412","article-title":"MoVQ: Modulating quantized vectors for high-fidelity image generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zheng"},{"key":"ref64","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref67","article-title":"Toward multimodal image-to-image translation","author":"Zhu","year":"2017"},{"key":"ref68","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/10746266\/10591425.pdf?arnumber=10591425","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T23:27:16Z","timestamp":1732663636000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10591425\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":68,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3424835","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12]]}}}