{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T05:17:28Z","timestamp":1732771048068,"version":"3.29.0"},"reference-count":41,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T00:00:00Z","timestamp":1726358400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,9,15]],"date-time":"2024-09-15T00:00:00Z","timestamp":1726358400000},"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\/501100002367","name":"Chinese Academy of Sciences","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002367","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,9,15]]},"DOI":"10.1109\/ijcb62174.2024.10744427","type":"proceedings-article","created":{"date-parts":[[2024,11,11]],"date-time":"2024-11-11T18:38:05Z","timestamp":1731350285000},"page":"1-10","source":"Crossref","is-referenced-by-count":0,"title":["EditHuman: Fine-Grained Text-Driven Human Video Editing"],"prefix":"10.1109","author":[{"given":"Kaiduo","family":"Zhang","sequence":"first","affiliation":[{"name":"Institute of Automation, CASIA,New Laboratory of Pattern Recognition,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Muyi","family":"Sun","sequence":"additional","affiliation":[{"name":"Beijing University of Posts and Telecommunications,School of AI,Beijing,China,100876"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junxing","family":"Hu","sequence":"additional","affiliation":[{"name":"Institute of Automation, CASIA,New Laboratory of Pattern Recognition,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kunbo","family":"Zhang","sequence":"additional","affiliation":[{"name":"Institute of Automation, CASIA,New Laboratory of Pattern Recognition,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[{"name":"Institute of Automation, CASIA,New Laboratory of Pattern Recognition,Beijing,China,100190"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"article-title":"Videodreamer: Customized multi-subject text-to-video generation with disen-mix finetuning","year":"2023","author":"Chen","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref5","first-page":"16890","article-title":"Cogview2: Faster and better text-to-image generation via hierarchical transformers","volume":"35","author":"Ding","year":"2022","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01237-3_37"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"article-title":"Imagen video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref10"},{"key":"ref11","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"article-title":"Classifier-free diffusion guidance","year":"2022","author":"Ho","key":"ref12"},{"journal-title":"Video diffusion models","year":"2022","author":"Ho","key":"ref13"},{"article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","year":"2022","author":"Hong","key":"ref14"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_26"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123309"},{"article-title":"Dreamix: Video diffusion models are general video editors","year":"2023","author":"Molad","key":"ref22"},{"article-title":"Glide: Towards photorealistic image generationand editing with text-guided diffusion models","year":"2021","author":"Nichol","key":"ref23"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref27","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"},{"article-title":"Knn-diffusion: Image generation via large-scale retrieval","year":"2022","author":"Sheynin","key":"ref28"},{"article-title":"Denoising diffusion implicit models","year":"2020","author":"Song","key":"ref29"},{"article-title":"Score-based generative modeling through stochastic differential equations","year":"2020","author":"Song","key":"ref30"},{"article-title":"Ucf101: A dataset of 101 human actions classes from videos in the wild","year":"2012","author":"Soomro","key":"ref31"},{"article-title":"Phenaki: Variable length video generation from open domain textual description","year":"2022","author":"Villegas","key":"ref32"},{"article-title":"Godiva: Generating open-domain videos from natural descriptions","year":"2021","author":"Wu","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"article-title":"Text-to-image diffusion model in generative ai: A survey","year":"2023","author":"Zhang","key":"ref36"},{"article-title":"Humandiffusion: a coarse-to-fine alignment diffusion framework for controllable text-driven person image generation","year":"2022","author":"Zhang","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"article-title":"Controlvideo: Training-free controllable text-to-video generation","year":"2023","author":"Zhang","key":"ref40"},{"article-title":"Magicvideo: Efficient video generation with latent diffusion models","year":"2022","author":"Zhou","key":"ref41"}],"event":{"name":"2024 IEEE International Joint Conference on Biometrics (IJCB)","start":{"date-parts":[[2024,9,15]]},"location":"Buffalo, NY, USA","end":{"date-parts":[[2024,9,18]]}},"container-title":["2024 IEEE International Joint Conference on Biometrics (IJCB)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10744408\/10744424\/10744427.pdf?arnumber=10744427","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T06:58:10Z","timestamp":1732690690000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10744427\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,15]]},"references-count":41,"URL":"https:\/\/doi.org\/10.1109\/ijcb62174.2024.10744427","relation":{},"subject":[],"published":{"date-parts":[[2024,9,15]]}}}