{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:42:45Z","timestamp":1791913365965,"version":"4.3.4"},"reference-count":71,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,1]],"date-time":"2025-10-01T00:00:00Z","timestamp":1759276800000},"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. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1109\/tcsvt.2025.3571944","type":"journal-article","created":{"date-parts":[[2025,5,20]],"date-time":"2025-05-20T13:17:05Z","timestamp":1747747025000},"page":"10500-10515","source":"Crossref","is-referenced-by-count":13,"title":["Generative Latent Coding for Ultra-Low Bitrate Image and Video Compression"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-4278-9400","authenticated-orcid":false,"given":"Linfeng","family":"Qi","sequence":"first","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8814-9691","authenticated-orcid":false,"given":"Zhaoyang","family":"Jia","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4559-0086","authenticated-orcid":false,"given":"Jiahao","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5635-2916","authenticated-orcid":false,"given":"Bin","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2188-3028","authenticated-orcid":false,"given":"Houqiang","family":"Li","sequence":"additional","affiliation":[{"name":"MoE Key Laboratory of Brain-Inspired Intelligent Perception and Cognition, University of Science and Technology of China, Hefei, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5383-6424","authenticated-orcid":false,"given":"Yan","family":"Lu","sequence":"additional","affiliation":[{"name":"Microsoft Research Asia, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/103085.103089"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3101953"},{"key":"ref3","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Ball\u00e9"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00796"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3089491"},{"key":"ref6","article-title":"EVC: Towards real-time neural image compression with mask decay","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00155"},{"key":"ref9","first-page":"18114","article-title":"Deep contextual video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Li"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3427426"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3233221"},{"key":"ref12","article-title":"End-to-end optimized image compression","volume-title":"Proc. 5th Int. Conf. Learn. Represent. (ICLR)","author":"Ball\u00e9"},{"key":"ref13","article-title":"Improving statistical fidelity for neural image compression with implicit local likelihood models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Muckley"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1603.08155"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.5555\/2969033.2969125"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3045810"},{"key":"ref17","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Van Den Oord"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00119"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/dcc58796.2024.00028"},{"key":"ref21","first-page":"30599","article-title":"Towards robust blind face restoration with codebook lookup transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhou"},{"key":"ref22","article-title":"Clic 2020: Challenge on learned image compression, 2020","author":"Toderici","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/214"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02466"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02465"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3455576"},{"key":"ref27","article-title":"Context-adaptive entropy model for end-to-end optimized image compression","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lee"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02166"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3580499"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01039"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00031"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICME46284.2020.9102750"},{"key":"ref33","article-title":"Text+ sketch: Image compression at ultra low rates","volume-title":"Proc. Workshop Neural Compress., Inf. Theory Appl. (ICML)","author":"Lei"},{"key":"ref34","first-page":"11913","article-title":"High-fidelity generative image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mentzer"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00187"},{"key":"ref36","article-title":"High-fidelity image compression with score-based generative models","author":"Hoogeboom","year":"2023","journal-title":"arXiv:2305.18231"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412185"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02138"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3317424"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","volume":"33","author":"Ho"},{"key":"ref41","article-title":"Towards image compression with perfect realism at ultra-low bitrates","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Careil"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ACSSC.2003.1292216"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2988453"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00583"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3372352"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_12"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00592"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72848-8_18"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3360248"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612530"},{"key":"ref52","article-title":"Variational lossy autoencoder","author":"Chen","year":"2016","journal-title":"arXiv:1611.02731"},{"key":"ref53","first-page":"1747","article-title":"Pixel recurrent neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Van Den Oord"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547845"},{"key":"ref56","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014","journal-title":"arXiv:1409.1556"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref60","article-title":"Fixing weight decay regularization in Adam","author":"Loshchilov","year":"2018"},{"key":"ref61","volume-title":"Kodak Lossless True Color Image Suite"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3339825.3394937"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532610"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref67","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.","volume":"30","author":"Heusel"},{"key":"ref68","article-title":"Demystifying MMD GANs","author":"Bi\u0144kowski","year":"2018","journal-title":"arXiv:1801.01401"},{"key":"ref69","volume-title":"Calculation of Average PSNR Differences Between RD-curves","author":"Bj\u00f8ntegaard","year":"2001"},{"issue":"11","key":"ref70","article-title":"Visualizing data using t-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref71","article-title":"CogVideoX: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv:2408.06072"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11192799\/11007732.pdf?arnumber=11007732","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,6]],"date-time":"2025-10-06T17:39:44Z","timestamp":1759772384000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11007732\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10]]},"references-count":71,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3571944","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10]]}}}