{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,18]],"date-time":"2026-04-18T16:21:11Z","timestamp":1776529271803,"version":"3.51.2"},"reference-count":81,"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"}],"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.2024.3403695","type":"journal-article","created":{"date-parts":[[2024,5,21]],"date-time":"2024-05-21T17:24:59Z","timestamp":1716312299000},"page":"8320-8333","source":"Crossref","is-referenced-by-count":5,"title":["Bridging Global Context Interactions for High-Fidelity Pluralistic Image Completion"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3584-9640","authenticated-orcid":false,"given":"Chuanxia","family":"Zheng","sequence":"first","affiliation":[{"name":"Engineering Science Department, University of Oxford, Oxford, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3664-572X","authenticated-orcid":false,"given":"Guoxian","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance Inc, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5264-2572","authenticated-orcid":false,"given":"Tat-Jen","family":"Cham","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Nanyang Technological University, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9444-3763","authenticated-orcid":false,"given":"Jianfei","family":"Cai","sequence":"additional","affiliation":[{"name":"Department of Data Science & AI, Monash University, Clayton, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Luo","sequence":"additional","affiliation":[{"name":"ByteDance Inc, Mountain View, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9977-8247","authenticated-orcid":false,"given":"Dinh","family":"Phung","sequence":"additional","affiliation":[{"name":"Department of Data Science & AI, Monash University, Clayton, VIC, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2003.1211538"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01517-0"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.278"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073659"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00577"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01113"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01502-7"},{"key":"ref16","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475436"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01106"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3384406"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"1","key":"ref21","first-page":"4171","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2019","journal-title":"NAACL-HLT"},{"issue":"8","key":"ref22","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref23","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Saharia"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref25","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhu"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref27","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01122"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02084"},{"key":"ref32","article-title":"Unified discrete diffusion for simultaneous vision-language generation","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Hu"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276382"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/83.935036"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238360"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.815261"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2004.10"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-11752-2_43"},{"key":"ref41","first-page":"901","article-title":"Shepard convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ren"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/5.726791"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref46","article-title":"PanoDiffusion: 360-degree panorama outpainting via diffusion","volume-title":"Proc. 12th Int. Conf. Learn. Representations","author":"Wu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.624"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_1"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201393"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00183"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.434"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_1"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00457"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00753"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_1"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00778"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01390"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00647"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00248"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00925"},{"key":"ref62","article-title":"Large scale image completion via co-modulated generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.128"},{"key":"ref64","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"van den Oord"},{"key":"ref65","first-page":"14866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. 33rd Int. Conf. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref66","first-page":"3518","article-title":"Imagebart: Bidirectional context with multinomial diffusion for autoregressive image synthesis","volume-title":"Proc. Int. Conf. Adv. Neural Inf. Process. Syst.","author":"Esser"},{"key":"ref67","article-title":"Vector-quantized image modeling with improved VQGAN","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01063"},{"key":"ref70","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref71","first-page":"4487","article-title":"Generative adversarial transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hudson"},{"issue":"34","key":"ref72","first-page":"14745","article-title":"TransGAN: Two transformers can make one strong GAN","author":"Jiang","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00064"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref75","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":"ref76","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref78","first-page":"7354","article-title":"Self-attention generative adversarial networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Zhang"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref80","first-page":"6626","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume-title":"Proc. 31st Int. Conf. Neural Inf. Process. Syst.","author":"Heusel"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2019.00154"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10746266\/10535740.pdf?arnumber=10535740","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T00:21:03Z","timestamp":1732666863000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10535740\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12]]},"references-count":81,"journal-issue":{"issue":"12"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3403695","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]]}}}