{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:21:21Z","timestamp":1780392081117,"version":"3.54.1"},"reference-count":31,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,14]],"date-time":"2025-09-14T00:00:00Z","timestamp":1757808000000},"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":[],"published-print":{"date-parts":[[2025,9,14]]},"DOI":"10.1109\/icip55913.2025.11084391","type":"proceedings-article","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T19:41:38Z","timestamp":1755546098000},"page":"1079-1084","source":"Crossref","is-referenced-by-count":1,"title":["RAVEN: Rethinking Adversarial Video Generation with Efficient Tri-Plane Networks"],"prefix":"10.1109","author":[{"given":"Partha","family":"Ghosh","sequence":"first","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Soubhik","family":"Sanyal","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Cordelia","family":"Schmid","sequence":"additional","affiliation":[{"name":"PSL Research University,Inria, École Normale Supérieure, CNRS"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bernhard","family":"Sch\u00f6lkopf","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen,Germany"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i8.28717"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00097"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00580"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.01008"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01129"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref11","article-title":"Phenaki: Variable length video generation from open domain textual descriptions","volume-title":"ICML","author":"Villegas"},{"key":"ref12","article-title":"Godiva: Generating open-domain videos from natural descriptions","author":"Wu","year":"2021"},{"key":"ref13","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref15","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref16","article-title":"Generating long videos of dynamic scenes","author":"Brooks","year":"2022","journal-title":"NIPS"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02231-3"},{"key":"ref19","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","volume-title":"ICLR","author":"Hong"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"},{"key":"ref22","article-title":"Faceforensics: A large-scale video dataset for forgery detection in human faces","author":"R\u00f6ssler","year":"2018"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref25","article-title":"Dwnet: Dense warp-based network for pose-guided human video generation","author":"Zablotskaia","year":"2019"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref28","article-title":"Stylegan-t: Unlocking the power of gans for fast large-scale text-to-image synthesis","volume-title":"ICML","author":"Sauer"},{"key":"ref29","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref31","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","volume-title":"ICLR","author":"Yu"}],"event":{"name":"2025 IEEE International Conference on Image Processing (ICIP)","location":"Anchorage, AK, USA","start":{"date-parts":[[2025,9,14]]},"end":{"date-parts":[[2025,9,17]]}},"container-title":["2025 IEEE International Conference on Image Processing (ICIP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11084272\/11083968\/11084391.pdf?arnumber=11084391","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T05:04:02Z","timestamp":1755579842000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11084391\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,14]]},"references-count":31,"URL":"https:\/\/doi.org\/10.1109\/icip55913.2025.11084391","relation":{},"subject":[],"published":{"date-parts":[[2025,9,14]]}}}