{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T07:21:57Z","timestamp":1794036117271,"version":"4.8.0"},"reference-count":33,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,6,16]],"date-time":"2024-06-16T00:00:00Z","timestamp":1718496000000},"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":[[2024,6,16]]},"DOI":"10.1109\/cvpr52733.2024.00789","type":"proceedings-article","created":{"date-parts":[[2024,9,16]],"date-time":"2024-09-16T13:34:53Z","timestamp":1726493693000},"page":"8261-8270","source":"Crossref","is-referenced-by-count":12,"title":["Fairy: Fast Parallelized Instruction-Guided Video-to-Video Synthesis"],"prefix":"10.1109","author":[{"given":"Bichen","family":"Wu","sequence":"first","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ching-Yao","family":"Chuang","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyan","family":"Wang","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yichen","family":"Jia","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kapil","family":"Krishnakumar","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tong","family":"Xiao","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Liang","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Licheng","family":"Yu","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Peter","family":"Vajda","sequence":"additional","affiliation":[{"name":"GenAI, Meta"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"Exploring video-to-video synthesis: A comparative analysis of rerender, tokenflow, and gen-l"},{"key":"ref2","volume-title":"pytorch documentation","year":"2023"},{"key":"ref3","volume-title":"Stock footage video, royalty-free hd, 4k video clips","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref5","first-page":"18392","article-title":"In-structpix2pix: Learning to follow image editing instructions","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Brooks","year":"2023"},{"key":"ref6","first-page":"23040","article-title":"Stable-video: Text-driven consistency-aware diffusion video editing","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Chai","year":"2023"},{"key":"ref7","article-title":"Emu: Enhancing image generation models using photogenic needles in a haystack","author":"Dai","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","first-page":"13610","article-title":"Tap-vid: A benchmark for tracking any point in a video","volume":"35","author":"Doersch","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref10","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"arXiv preprint"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2022","journal-title":"arXiv preprint"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323006"},{"key":"ref13","first-page":"26565","article-title":"Elucidating the design space of diffusion-based generative models","volume":"35","author":"Karras","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480546"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01376"},{"key":"ref17","article-title":"Video-p2p: Video editing with cross-attention control","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","article-title":"Evalcrafter: Benchmarking and evaluating large video generation models","author":"Liu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","article-title":"Codef: Content deformation fields for temporally consistent video processing","author":"Ouyang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017","journal-title":"arXiv preprint"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"issue":"2","key":"ref22","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref24","volume-title":"Disco diffusion v5.2 - warp fusion","author":"Alexander"},{"key":"ref25","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","first-page":"25278","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume":"35","author":"Schuhmann","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref27","article-title":"Emergent correspondence from image diffusion","author":"Tang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref29","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref30","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref31","article-title":"Videocomposer: Compositional video synthesis with motion controllability","author":"Wang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"}],"event":{"name":"2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","location":"Seattle, WA, USA","start":{"date-parts":[[2024,6,16]]},"end":{"date-parts":[[2024,6,22]]}},"container-title":["2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10654794\/10654797\/10657491.pdf?arnumber=10657491","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T20:52:41Z","timestamp":1771966361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10657491\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,6,16]]},"references-count":33,"URL":"https:\/\/doi.org\/10.1109\/cvpr52733.2024.00789","relation":{},"subject":[],"published":{"date-parts":[[2024,6,16]]}}}