{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:23Z","timestamp":1778048363011,"version":"3.51.4"},"reference-count":60,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00421","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"4325-4334","source":"Crossref","is-referenced-by-count":0,"title":["VividAnimator: An End-to-End Audio and Pose-driven Half-Body Human Animation Framework"],"prefix":"10.1109","author":[{"given":"Donglin","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongyuan","family":"Li","sequence":"additional","affiliation":[{"name":"Image Derivative Inc"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tianhang","family":"Liu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junming","family":"Huang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoda","family":"Yang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chi","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weiwei","family":"Xu","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","author":"Baevski","year":"2020"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0506"},{"key":"ref4","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","author":"Chang","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32241"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01964"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3087709"},{"key":"ref8","article-title":"Omniavatar: Efficient audio-driven avatar video generation with adaptive body animation","author":"Gan","year":"2025"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687571"},{"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\/CVPR.2018.00762"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.6721"},{"key":"ref13","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","author":"Heusel","year":"2018"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref15","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2024"},{"key":"ref16","article-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency","author":"Jiang","year":"2025"},{"key":"ref17","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2022"},{"key":"ref18","article-title":"Let them talk: Audio-driven multi-person conversational video generation","author":"Kong","year":"2025"},{"key":"ref19","volume-title":"Flux: Official inference repository for flux.1 models","year":"2024"},{"key":"ref20","article-title":"Latentsync: Taming audio-conditioned latent diffusion models for lip sync with syncnet supervision","author":"Li","year":"2025"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8552-4_8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccvw69036.2025.00213"},{"key":"ref23","article-title":"Cyberhost: A one-stage diffusion framework for audio-driven talking body generation","volume-title":"The Thirteenth International Conference on Learning Representations","author":"Lin"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01285"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01270"},{"key":"ref26","article-title":"Tango: Co-speech gesture video reenactment with hierarchical audio motion embedding and diffusion interpolation","author":"Liu","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680693"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v40i10.37746"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00516"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00938"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref33","article-title":"Chatanyone: Stylized real-time portrait video generation with hierarchical motion diffusion model","author":"Qi","year":"2025"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"6","key":"ref35","doi-asserted-by":"crossref","DOI":"10.1145\/3687980","article-title":"Human4dit: 360-degree human video generation with 4d diffusion transformer","volume":"43","author":"Shao","year":"2024","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00372"},{"key":"ref37","article-title":"Emo2: End-effector guided audio-driven avatar video generation","author":"Tian","year":"2025"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01965"},{"key":"ref39","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2019"},{"key":"ref40","article-title":"Neural discrete representation learning","author":"van den Oord","year":"2018"},{"key":"ref41","article-title":"Fantasytalking2: Timestep-layer adaptive preference optimization for audio-driven portrait animation","author":"Wang","year":"2025"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref45","article-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animations","author":"Wei","year":"2024"},{"key":"ref46","article-title":"One shot, one talk: Whole-body talking avatar from a single image","author":"Xiang","year":"2024"},{"key":"ref47","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024"},{"key":"ref48","article-title":"Magicanimate: Temporally consistent human image animation using diffusion model","author":"Xu","year":"2023"},{"key":"ref49","article-title":"Showmaker: Creating high-fidelity 2d human video via fine-grained diffusion modeling","author":"Yang","year":"2024","journal-title":"NeurIPS"},{"key":"ref50","article-title":"Megactor-\u03c3: Unlocking flexible mixed-modal control in portrait animation with diffusion transformer","author":"Yang","year":"2024"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref52","article-title":"Sonic: Safe social navigation with adaptive conformal inference and constrained reinforcement learning","author":"Yao","year":"2025"},{"key":"ref53","volume-title":"video-subtitle-remover","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_1"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref57","article-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2025"},{"key":"ref58","article-title":"Realisdance: Equip controllable character animation with realistic hands","author":"Zhou","year":"2024"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00841"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492696.pdf?arnumber=11492696","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:59:43Z","timestamp":1778047183000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492696\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00421","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}