{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T17:55:15Z","timestamp":1775066115761,"version":"3.50.1"},"reference-count":64,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62331006"],"award-info":[{"award-number":["62331006"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62171038"],"award-info":[{"award-number":["62171038"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62088101"],"award-info":[{"award-number":["62088101"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tpami.2024.3384406","type":"journal-article","created":{"date-parts":[[2024,4,2]],"date-time":"2024-04-02T18:48:35Z","timestamp":1712083715000},"page":"6652-6668","source":"Crossref","is-referenced-by-count":29,"title":["Transformer Based Pluralistic Image Completion With Reduced Information Loss"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7457-2090","authenticated-orcid":false,"given":"Qiankun","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3345-0553","authenticated-orcid":false,"given":"Yuqi","family":"Jiang","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9095-4462","authenticated-orcid":false,"given":"Zhentao","family":"Tan","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6677-694X","authenticated-orcid":false,"given":"Ying","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Beijing Institute of Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3028-0755","authenticated-orcid":false,"given":"Qi","family":"Chu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9522-6157","authenticated-orcid":false,"given":"Gang","family":"Hua","sequence":"additional","affiliation":[{"name":"Wormpex AI Research LLC, Bellevue, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4417-9316","authenticated-orcid":false,"given":"Nenghai","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, University of Science and Technology of China, Hefei, Anhui, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_2"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00384"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/1531326.1531330"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076487"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2006.141"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.815261"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2004.833105"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01252-6_6"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00408"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00465"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475436"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref14","first-page":"1691","article-title":"Generative pretraining from pixels","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Chen"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref16","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723009"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref20","first-page":"3","article-title":"Autoencoders, minimum description length, and Helmholtz free energy","volume":"6","author":"Hinton","year":"1994","journal-title":"Neural Inf. Process. Syst."},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-23783-6_41"},{"key":"ref22","volume-title":"A Non-Linear Dimensionality Reduction Method for Improving Nearest Neighbour Classification","author":"Min","year":"2005"},{"key":"ref23","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref24","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Van Oord"},{"key":"ref25","first-page":"4797","article-title":"Conditional image generation with PixelCNN decoders","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Oord"},{"key":"ref26","first-page":"6309","article-title":"Neural discrete representation learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"van den Oord"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref28","first-page":"14 866","article-title":"Generating diverse high-fidelity images with VQ-VAE-2","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Razavi"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25130"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01432"},{"key":"ref32","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref33","first-page":"5696","article-title":"OmniVL: One foundation model for image-language and video-language tasks","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20056-4_15"},{"key":"ref35","first-page":"1","article-title":"BEIT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00213"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/344779.344972"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/383259.383296"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1276377.1276382"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3209702"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00153"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00578"},{"key":"ref45","first-page":"1","article-title":"Large scale image completion via co-modulated generative adversarial networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhao"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01106"},{"key":"ref49","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016"},{"issue":"8","key":"ref50","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00550"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref54","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref55","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref56","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109461"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_43"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01122"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref62","first-page":"6629","article-title":"GANs trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Neural Inf. Process. Syst."},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10666888\/10488726.pdf?arnumber=10488726","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T04:38:05Z","timestamp":1725683885000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10488726\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":64,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2024.3384406","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":[[2024,10]]}}}