{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,7]],"date-time":"2026-04-07T13:56:58Z","timestamp":1775570218308,"version":"3.50.1"},"reference-count":37,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003725","name":"National Research Foundation of Korea","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003725","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100006785","name":"Google","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100006785","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,10,1]]},"DOI":"10.1109\/iccv51070.2023.00719","type":"proceedings-article","created":{"date-parts":[[2024,1,15]],"date-time":"2024-01-15T15:55:59Z","timestamp":1705334159000},"page":"7788-7798","source":"Crossref","is-referenced-by-count":22,"title":["The Power of Sound (TPoS): Audio Reactive Video Generation with Stable Diffusion"],"prefix":"10.1109","author":[{"given":"Yujin","family":"Jeong","sequence":"first","affiliation":[{"name":"Korea University,Department of Computer Science and Engineering,Seoul,Korea,02841"}]},{"given":"Wonjeong","family":"Ryoo","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}]},{"given":"Seunghyun","family":"Lee","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}]},{"given":"Dabin","family":"Seo","sequence":"additional","affiliation":[{"name":"Korea University,Department of Computer Science and Engineering,Seoul,Korea,02841"}]},{"given":"Wonmin","family":"Byeon","sequence":"additional","affiliation":[{"name":"NVIDIA Research,Santa Clara,USA,95050"}]},{"given":"Sangpil","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of Artificial Intelligence,Seoul,Korea,02841"}]},{"given":"Jinkyu","family":"Kim","sequence":"additional","affiliation":[{"name":"Korea University,Department of Computer Science and Engineering,Seoul,Korea,02841"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592450"},{"key":"ref2","article-title":"The stable artist: Steering semantics in diffusion latent space","author":"Brack","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58583-9_42"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref7","article-title":"Automatic realistic music video generation from segments of youtube videos","author":"Gross","year":"2019"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref9","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022"},{"key":"ref10","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref11","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"issue":"4","key":"ref13","first-page":"10","article-title":"Tr\u00e4umerai: Dreaming music with stylegan","volume":"2","author":"Jeong","year":"2021"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"ref16","first-page":"852","article-title":"Alias-free generative adversarial networks","volume":"34","author":"Karras","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref17","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref18","first-page":"14042","article-title":"Ccvs: context-aware controllable video synthesis","volume":"34","author":"Le Moing","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00337"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref23","article-title":"Dreamix: Video diffusion models are general video editors","author":"Molad","year":"2023"},{"key":"ref24","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2680"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref31","article-title":"Improved techniques for training gans","volume":"29","author":"Salimans","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref32","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01388"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref35","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref36","article-title":"Phenaki: Variable length video generation from open domain textual description","author":"Villegas","year":"2022"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00189"}],"event":{"name":"2023 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Paris, France","start":{"date-parts":[[2023,10,1]]},"end":{"date-parts":[[2023,10,6]]}},"container-title":["2023 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10376473\/10376477\/10377529.pdf?arnumber=10377529","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,17]],"date-time":"2024-01-17T20:37:48Z","timestamp":1705523868000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10377529\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,1]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51070.2023.00719","relation":{},"subject":[],"published":{"date-parts":[[2023,10,1]]}}}