{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T17:42:16Z","timestamp":1777657336645,"version":"3.51.4"},"reference-count":32,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,7,15]],"date-time":"2024-07-15T00:00:00Z","timestamp":1721001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003453","name":"Natural Science Foundation of Guangdong Province","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100003453","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,7,15]]},"DOI":"10.1109\/icme57554.2024.10688119","type":"proceedings-article","created":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T17:24:16Z","timestamp":1727717056000},"page":"1-6","source":"Crossref","is-referenced-by-count":6,"title":["DrivingGen: Efficient Safety-Critical Driving Video Generation with Latent Diffusion Models"],"prefix":"10.1109","author":[{"given":"Zipeng","family":"Guo","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University,School of Intelligent Systems Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuchen","family":"Zhou","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Intelligent Systems Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chao","family":"Gou","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,School of Intelligent Systems Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JRFID.2022.3207017"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01164"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2023.3309274"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref5","article-title":"Videocomposer: Compositional video synthesis with motion controllability","author":"Wang","year":"2023"},{"key":"ref6","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"ICLR"},{"key":"ref7","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022","journal-title":"ICLR"},{"key":"ref8","article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","author":"An","year":"2023"},{"key":"ref9","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022"},{"key":"ref10","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref12","article-title":"Video diffusion models","author":"Ho","year":"2022"},{"key":"ref13","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref14","first-page":"23 371","article-title":"Mcvd-masked conditional video diffusion for prediction, generation, and interpolation","volume":"35","author":"Voleti","year":"2022","journal-title":"NeurIPS"},{"key":"ref15","article-title":"Drivingdiffusion: Layout-guided multiview driving scene video generation with latent diffusion model","author":"Li","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00718"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TIV.2024.3384989"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02080"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/s11227-021-04151-2"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3309309"},{"issue":"1","key":"ref21","first-page":"404","article-title":"Cascade learning for driver facial monitoring","volume":"8","author":"Gou","year":"2022","journal-title":"IEEE T-IV"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197145"},{"key":"ref23","article-title":"Street-view image generation from a bird\u2019s-eye view layout","author":"Swerdlow","year":"2023"},{"key":"ref24","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"NeurIPS"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00715"},{"key":"ref26","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"ICLR"},{"key":"ref27","article-title":"Towards a unified view of parameter-efficient transfer learning","author":"He","year":"2021","journal-title":"ICLR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01770"},{"key":"ref29","article-title":"Dota: unsupervised detection of traffic anomaly in driving videos","author":"Yao","year":"2022","journal-title":"IEEE T-PAMI"},{"key":"ref30","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref31","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS Workshop","author":"Ho"},{"key":"ref32","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"ICML.","author":"Radford","year":"2021"}],"event":{"name":"2024 IEEE International Conference on Multimedia and Expo (ICME)","location":"Niagara Falls, ON, Canada","start":{"date-parts":[[2024,7,15]]},"end":{"date-parts":[[2024,7,19]]}},"container-title":["2024 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10685847\/10687354\/10688119.pdf?arnumber=10688119","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T06:23:19Z","timestamp":1727763799000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10688119\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,7,15]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icme57554.2024.10688119","relation":{},"subject":[],"published":{"date-parts":[[2024,7,15]]}}}