{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,8]],"date-time":"2026-07-08T15:53:07Z","timestamp":1783525987081,"version":"3.55.0"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01274","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"13730-13740","source":"Crossref","is-referenced-by-count":2,"title":["Video Motion Graphs"],"prefix":"10.1109","author":[{"given":"Haiyang","family":"Liu","sequence":"first","affiliation":[{"name":"The University of Tokyo"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhan","family":"Xu","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Fa-Ting","family":"Hong","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hsin-Ping","family":"Huang","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yi","family":"Zhou","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Adobe Research"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref4","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","year":"2023"},{"key":"ref5","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01482"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00351"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref10","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser","year":"2024"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_22"},{"key":"ref12","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00220"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00220"},{"key":"ref15","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"arXiv preprint"},{"key":"ref16","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"arXiv preprint","author":"Hu","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00668"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00938"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02079"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ISTEL.2008.4651368"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/1401132.1401202"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref26","article-title":"Cyberhost: Taming audiodriven avatar diffusion model with region codebook attention","author":"Lin","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","article-title":"Motion-x: A largescale 3d expressive whole-body human motion dataset","author":"Lin","year":"2024","journal-title":"Advances in Neural Information Processing Systems, 36"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548400"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"ref30","article-title":"Tango: Co-speech gesture video reenactment with hierarchical audio motion embedding and diffusion interpolation","author":"Liu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.478"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00352"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00183"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"ref36","article-title":"Actanywhere: Subject-aware video background generation","author":"Pan","year":"2024","journal-title":"arXiv preprint"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58568-6_7"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01427"},{"key":"ref39","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","year":"2021"},{"key":"ref40","first-page":"8821","article-title":"Zero-shot text-to-image generation","volume-title":"International conference on machine learning","author":"Ramesh","year":"2021"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2009.2034992"},{"key":"ref44","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv preprint"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01422"},{"key":"ref46","first-page":"4693","article-title":"Towards end-to-end prosody transfer for expressive speech synthesis with tacotron","volume-title":"international conference on machine learning","author":"Skerry-Ryan","year":"2018"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.21437\/ICSLP.1994-538"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00502"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-024-4592-3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01729"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3687761"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref55","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.52202\/079017-1263"},{"key":"ref58","article-title":"Zipir: Latent pyramid diffusion transformer for high-resolution image restoration","author":"Yu","year":"2025","journal-title":"arXiv preprint"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","article-title":"Mimicmotion: High-quality human motion video generation with confidence-aware pose guidance","author":"Zhang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00341"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11444105.pdf?arnumber=11444105","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:21:25Z","timestamp":1777530085000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444105\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01274","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}