{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:12:26Z","timestamp":1778051546017,"version":"3.51.4"},"reference-count":82,"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\/wacv61042.2026.00372","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3813-3824","source":"Crossref","is-referenced-by-count":0,"title":["MuseDance: A Diffusion-based Music-Driven Image Animation System"],"prefix":"10.1109","author":[{"given":"Zhikang","family":"Dong","sequence":"first","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Weituo","family":"Hao","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ju-Chiang","family":"Wang","sequence":"additional","affiliation":[{"name":"Bytedance"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Apple"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pawel","family":"Polak","sequence":"additional","affiliation":[{"name":"Stony Brook University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480559"},{"key":"ref2","article-title":"Stochastic variational video prediction","author":"Babaeizadeh","year":"2017"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888933"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596767"},{"key":"ref5","article-title":"The million song dataset","volume-title":"Proceedings of the 12th International Conference on Music Information Retrieval (ISMIR 2011)","author":"Bertin-Mahieux"},{"key":"ref6","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596787"},{"key":"ref9","volume-title":"Video generation models as world simulators","author":"Brooks","year":"2024"},{"key":"ref10","first-page":"1877","article-title":"Language models are few-shot learners","volume":"33","author":"Brown","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref11","article-title":"Synthesizer sound matching using audio spectrogram transformers","author":"Bruford","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00770"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref14","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","volume-title":"Forty-first International Conference on Machine Learning","author":"Chang"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_27"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00987"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TDPVT.2004.1335262"},{"key":"ref18","volume-title":"Openmmlab pose estimation tool-box and benchmark","year":"2020"},{"key":"ref19","first-page":"1174","article-title":"Stochastic video generation with a learned prior","volume-title":"International conference on machine learning","author":"Denton"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01804"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/AIxSET62544.2024.00018"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/AIMHC59811.2024.00045"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01214"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2003.1238420"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-698"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21315"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00762"},{"key":"ref29","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023"},{"key":"ref30","author":"G\u00fc\u00e7l\u00fc","year":"2016","journal-title":"Brains on beats"},{"key":"ref31","article-title":"Musicinfuser: Making video diffusion listen and dance","author":"Hong","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"ref33","first-page":"8153","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Hu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01256"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref37","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref38","volume-title":"Kling video model","year":"2024"},{"key":"ref40","article-title":"Stochastic adversarial video prediction","author":"Lee","year":"2018"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096853"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12233"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00442"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00337"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01973"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3127905"},{"key":"ref48","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref49","author":"Pons","year":"2019","journal-title":"musicnn: Pre-trained convolutional neural networks for music audio tagging"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"issue":"2","key":"ref51","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00985"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.308"},{"key":"ref55","first-page":"32","article-title":"First order motion model for image animation","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref57","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00361"},{"key":"ref60","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref61","article-title":"Lamda: Language models for dialog applications","author":"Thoppilan","year":"2022"},{"key":"ref62","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref64","first-page":"6","article-title":"Aist dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","author":"Tsuchida","year":"2019","journal-title":"ISMIR"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00165"},{"key":"ref66","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref67","article-title":"Decomposing motion and content for natural video sequence prediction","author":"Villegas","year":"2017"},{"key":"ref68","first-page":"29","article-title":"Generating videos with scene dynamics","author":"Vondrick","year":"2016","journal-title":"Advances in neural information processing systems"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00891"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00502"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1145\/1964921.1964927"},{"key":"ref73","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","author":"Xu","year":"2024"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref75","doi-asserted-by":"crossref","DOI":"10.36227\/techrxiv.176049719.90048379\/v1","article-title":"Generative ai for simulating real world dynamics applications and challenges","author":"Yao","year":"2025"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"ref77","article-title":"Lm2d: Lyrics-and music-driven dance synthesis","author":"Yin","year":"2024"},{"key":"ref78","article-title":"Generating videos with dynamics-aware implicit generative adversarial networks","author":"Yu","year":"2022"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref80","article-title":"Implementing dialog-based music recommendations for videos","author":"Zhang","year":"2025"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref83","first-page":"145","article-title":"Champ: Controllable and consistent human image animation with 3d parametric guidance","volume-title":"European Conference on Computer Vision","author":"Zhu"}],"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\/11492589.pdf?arnumber=11492589","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:17:14Z","timestamp":1778048234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492589\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":82,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00372","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}