{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T18:00:55Z","timestamp":1781287255018,"version":"3.54.1"},"reference-count":71,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100010418","name":"IITP","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100010418","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007107","name":"KAIST","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007107","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,6]]},"DOI":"10.1109\/cvpr52729.2023.01770","type":"proceedings-article","created":{"date-parts":[[2023,8,22]],"date-time":"2023-08-22T17:30:52Z","timestamp":1692725452000},"page":"18456-18466","source":"Crossref","is-referenced-by-count":116,"title":["Video Probabilistic Diffusion Models in Projected Latent Space"],"prefix":"10.1109","author":[{"given":"Sihyun","family":"Yu","sequence":"first","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kihyuk","family":"Sohn","sequence":"additional","affiliation":[{"name":"Google Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Subin","family":"Kim","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinwoo","family":"Shin","sequence":"additional","affiliation":[{"name":"KAIST"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Generative adversarial nets","author":"goodfellow","year":"2014","journal-title":"Advances in neural information processing systems"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref12","article-title":"Long video generation with time-agnostic vqgan and time-sensitive trans-former","author":"ge","year":"0","journal-title":"European Conference on Computer Vision"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.510"},{"key":"ref15","article-title":"Vector quan-tized diffusion model for text-to-image synthesis","author":"gu","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref59","article-title":"Score-based generative modeling in latent space","author":"vahdat","year":"2021","journal-title":"Neural Information Processing Systems"},{"key":"ref14","article-title":"Latent neural differential equations for video generation","author":"gordon","year":"0","journal-title":"NeurIPS 2020 Workshop on Pre-registration in Machine Learning"},{"key":"ref58","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"unterthiner","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref53","article-title":"Score-based generative modeling through stochastic differential equations","author":"song","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref52","article-title":"Generative modeling by estimating gradients of the data distribution","author":"song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"StyleVideoGAN: A temporal generative model using a pretrained StyleGAN","author":"fox","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref55","article-title":"A good image generator is what you need for high-resolution video synthesis","author":"tian","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref54","article-title":"UCF10l: A dataset of 101 human actions classes from videos in the wild","author":"soomro","year":"2012","journal-title":"ArXiv Preprint"},{"key":"ref17","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"he","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref16","article-title":"Flexible diffusion modeling of long videos","author":"harvey","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref19","article-title":"Denoising diffusion probabilistic models","author":"ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref18","article-title":"Im-agen video: High definition video generation with diffusion models","author":"ho","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref51","article-title":"Denoising diffusion implicit models","author":"song","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref50","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref46","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"singer","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897982"},{"key":"ref48","article-title":"Epigraf: Rethinking training of 3d gans","author":"skorokhodov","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","article-title":"Improved techniques for training GANs","author":"salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref49","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","author":"sohl-dickstein","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref8","article-title":"Jukebox: A generative model for music","author":"dhariwal","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref7","article-title":"Adver-sarial video generation on complex datasets","author":"clark","year":"2019","journal-title":"ArXiv Preprint"},{"key":"ref9","article-title":"Diffusion models beat GANs on image synthesis","author":"dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref4","article-title":"Is space-time attention all you need for video understanding?","author":"bertasius","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref3","article-title":"Wasserstein generative adversarial networks","author":"arjovsky","year":"2017","journal-title":"International Conference on Machine Learning"},{"key":"ref6","article-title":"Efficient geometry-aware 3d generative adversarial networks","author":"eric","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref5","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref40","article-title":"Hierarchical text-conditional image generation with clip latents","author":"ramesh","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26094"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00286"},{"key":"ref37","article-title":"Parallel wavenet: Fast high-fidelity speech synthesis","author":"oord","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00322"},{"key":"ref31","article-title":"Diffwave: A versatile diffusion model for audio synthesis","author":"kong","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref30","article-title":"Auto-encoding variational bayes","author":"kingma","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref33","article-title":"Decoupled weight de-cay regularization","author":"loshchilov","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref32","article-title":"Generative spoken language modeling from raw audio","author":"lakhotia","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref2","article-title":"Towards a human-like open-domain chatbot","author":"adiwardana","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref1","article-title":"Towards high resolution video generation with pro-gressive growing of sliced Wasserstein GANs","author":"acharya","year":"2018","journal-title":"ArXiv Preprint"},{"key":"ref39","article-title":"Latent video transformer","author":"rakhimov","year":"2020","journal-title":"ArXiv Preprint"},{"key":"ref38","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"poole","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref71","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"zhou","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref24","article-title":"Video pixel networks","author":"kalchbrenner","year":"0","journal-title":"International Conference on Machine Learning"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00190"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2020.09.016"},{"key":"ref67","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","author":"yu","year":"0","journal-title":"The Tenth International Conference on Learning Representations"},{"key":"ref26","article-title":"Progressive growing of GANs for improved quality, stability, and variation","author":"karras","year":"0","journal-title":"International Conference on Learning Representations"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.223"},{"key":"ref69","article-title":"Fast sampling of diffusion models with exponential integrator","author":"zhang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref20","article-title":"Classifier-free diffusion guidance","author":"ho","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref64","article-title":"Learning to generate time-lapse videos using multi-stage dy-namic generative adversarial networks","author":"xiong","year":"0","journal-title":"IEEE Conference on Computer Vision and Pattern Recognition"},{"key":"ref63","article-title":"Scaling autoregressive video models","author":"weissenborn","year":"2020","journal-title":"International Conference on Learning Representations"},{"key":"ref22","article-title":"Diffusion models for video prediction and infilling","author":"hoppe","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref66","article-title":"Diffusion probabilistic modeling for video generation","author":"yang","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref21","article-title":"Video diffusion models","author":"ho","year":"2022","journal-title":"ArXiv Preprint"},{"key":"ref65","article-title":"VideoGPT: Video generation using VQ-VAE and transformers","author":"yan","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref27","article-title":"Alias-free generative adversarial networks","author":"karras","year":"2021","journal-title":"ArXiv Preprint"},{"key":"ref29","article-title":"Scalable neural video representations with learnable positional features","author":"kim","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref60","article-title":"Neural discrete representation learning","author":"van den oord","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref62","article-title":"Generating videos with scene dynamics","author":"vondrick","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref61","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Advances in neural information processing systems"}],"event":{"name":"2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Vancouver, BC, Canada","start":{"date-parts":[[2023,6,17]]},"end":{"date-parts":[[2023,6,24]]}},"container-title":["2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"https:\/\/2.zoppoz.workers.dev:443\/http\/xplorestaging.ieee.org\/ielx7\/10203037\/10203050\/10203977.pdf?arnumber=10203977","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T17:56:19Z","timestamp":1694454979000},"score":1,"resource":{"primary":{"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/ieeexplore.ieee.org\/document\/10203977\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6]]},"references-count":71,"URL":"https:\/\/2.zoppoz.workers.dev:443\/https\/doi.org\/10.1109\/cvpr52729.2023.01770","relation":{},"subject":[],"published":{"date-parts":[[2023,6]]}}}