{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T22:11:12Z","timestamp":1778623872982,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"am","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,1]],"date-time":"2023-08-01T00:00:00Z","timestamp":1690848000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"HPI Research Center in Machine Learning and Data Science at UC Irvine"},{"DOI":"10.13039\/501100008982","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100008982","id-type":"DOI","asserted-by":"publisher"}]},{"name":"NSF CAREER Award","award":["2047418"],"award-info":[{"award-number":["2047418"]}]},{"name":"NSF","award":["2003237"],"award-info":[{"award-number":["2003237"]}]},{"name":"NSF","award":["2007719"],"award-info":[{"award-number":["2007719"]}]},{"DOI":"10.13039\/100000015","name":"U.S. Department of Energy","doi-asserted-by":"publisher","award":["DE-SC0022331"],"award-info":[{"award-number":["DE-SC0022331"]}],"id":[{"id":"10.13039\/100000015","id-type":"DOI","asserted-by":"publisher"}]},{"name":"IN PART by gifts from Qualcomm and Disney"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,8]]},"DOI":"10.1109\/tpami.2023.3260684","type":"journal-article","created":{"date-parts":[[2023,3,22]],"date-time":"2023-03-22T17:53:01Z","timestamp":1679507581000},"page":"9908-9921","source":"Crossref","is-referenced-by-count":11,"title":["Insights From Generative Modeling for Neural Video Compression"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3154-4150","authenticated-orcid":false,"given":"Ruihan","family":"Yang","sequence":"first","affiliation":[{"name":"Department of Computer Science, University of California Irvine, Irvine, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8943-0354","authenticated-orcid":false,"given":"Yibo","family":"Yang","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California Irvine, Irvine, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6387-8062","authenticated-orcid":false,"given":"Joseph","family":"Marino","sequence":"additional","affiliation":[{"name":"DeepMind, California Institute of Technology, Pasadena, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7836-7839","authenticated-orcid":false,"given":"Stephan","family":"Mandt","sequence":"additional","affiliation":[{"name":"Department of Computer Science, University of California Irvine, Irvine, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1561\/9781638281757"},{"key":"ref2","first-page":"10771","article-title":"Joint autoregressive and hierarchical priors for learned image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Minnen"},{"key":"ref3","article-title":"Improving inference for neural image compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref4","article-title":"BPG image format","author":"Bellard","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00853"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2003.815165"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2012.2221191"},{"key":"ref8","article-title":"NICE: Non-linear independent components estimation","author":"Dinh","year":"2014"},{"key":"ref9","article-title":"Density estimation using real NVP","author":"Dinh","year":"2016"},{"key":"ref10","first-page":"1","article-title":"Improving sequential latent variable models with autoregressive flows","volume-title":"Proc. Symp. Adv. Approx. Bayesian Inference","author":"Marino"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01126"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6825"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00360"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_27"},{"key":"ref15","article-title":"Deep generative video compression with temporal autoregressive transforms","volume-title":"Proc. ICML Workshop Invertible Neural Netw. Normalizing Flows, Explicit Likelihood Models","author":"Yang"},{"key":"ref16","first-page":"2338","article-title":"Masked autoregressive flow for density estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Papamakarios"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/jstsp.2020.3034501"},{"key":"ref18","first-page":"2980","article-title":"A recurrent latent variable model for sequential data","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chung"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1002\/0471200611"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00355"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/79.733497"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1115\/1.3662552"},{"key":"ref23","article-title":"Differential quantization of communication signals","author":"Cutler","year":"1952"},{"key":"ref24","article-title":"Normalizing flows for probabilistic modeling and inference","volume":"22","author":"Papamakarios","year":"2021","journal-title":"J. Mach. Learn. Res."},{"key":"ref25","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4615-3626-0"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/79.952802"},{"key":"ref28","first-page":"1792","article-title":"Understanding and mitigating exploding inverses in invertible neural networks","volume-title":"Proc. 24th Int. Conf. Artif. Intell. Statist.","author":"Behrmann"},{"key":"ref29","first-page":"10215","article-title":"Glow: Generative flow with invertible 1x1 convolutions","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref30","first-page":"2175","article-title":"RNADE: The real-valued neural autoregressive density-estimator","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Uria"},{"key":"ref31","first-page":"3874","article-title":"Compression with flows via local bits-back coding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ho"},{"key":"ref32","article-title":"End-to-end optimized image compression","volume-title":"Proc. 5th Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref33","article-title":"Lossy image compression with compressive autoencoders","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Theis"},{"key":"ref34","first-page":"6158","article-title":"Deep state space models for unconditional word generation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Schmidt"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1338"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1080\/02664769823151"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00713"},{"key":"ref38","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Denton"},{"key":"ref39","first-page":"5670","article-title":"Disentangled sequential autoencoder","volume-title":"Proc. 35th Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref40","first-page":"3483","article-title":"Learning structured output representation using deep conditional generative models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Sohn","year":"2015"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00324"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.577"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00461"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/PCS.2016.7906310"},{"key":"ref45","article-title":"Estimating or propagating gradients through stochastic neurons for conditional computation","author":"Bengio","year":"2013"},{"key":"ref46","article-title":"Variational image compression with a scale hyperprior","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Ball\u00e9"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP40778.2020.9190935"},{"key":"ref48","first-page":"10670","article-title":"Variational Bayesian quantization","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Yang"},{"key":"ref49","article-title":"Compression without quantization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Flamich"},{"key":"ref50","article-title":"Lossy image compression with normalizing flows","author":"Helminger","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_26"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00652"},{"key":"ref53","article-title":"Deep generative video compression","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2019.2892608"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305033"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.316"},{"key":"ref57","article-title":"Stochastic variational video prediction","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Babaeizadeh"},{"key":"ref58","first-page":"613","article-title":"Generating videos with scene dynamics","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Vondrick"},{"key":"ref59","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018"},{"key":"ref60","first-page":"1530","article-title":"Variational inference with normalizing flows","volume-title":"Proc. 32nd Int. Conf. Mach. Learn.","author":"Rezende"},{"key":"ref61","first-page":"4743","article-title":"Improved variational inference with inverse autoregressive flow","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kingma"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00666"},{"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\/ACSSC.2003.1292216"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054074"},{"key":"ref68","article-title":"Computationally efficient neural image compression","author":"Johnston","year":"2019"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2020.3043590"},{"key":"ref70","first-page":"2078","article-title":"Neural autoregressive flows","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Huang"},{"key":"ref71","article-title":"VCT: A video compression transformer","author":"Mentzer","year":"2022"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref73","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/ieeexplore.ieee.org\/ielam\/34\/10169863\/10078276-aam.pdf","content-type":"application\/pdf","content-version":"am","intended-application":"syndication"},{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10169863\/10078276.pdf?arnumber=10078276","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,9]],"date-time":"2024-07-09T18:27:46Z","timestamp":1720549666000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10078276\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8]]},"references-count":73,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3260684","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":[[2023,8]]}}}