{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:30Z","timestamp":1777888950970,"version":"3.51.4"},"reference-count":73,"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\/iccv51701.2025.00954","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10239-10250","source":"Crossref","is-referenced-by-count":0,"title":["Controllable and Expressive One-Shot Video Head Swapping"],"prefix":"10.1109","author":[{"given":"Chaonan","family":"Ji","sequence":"first","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jinwei","family":"Qi","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bang","family":"Zhang","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liefeng","family":"Bo","sequence":"additional","affiliation":[{"name":"Alibaba Group"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","volume-title":"Forty-first International Conference on Machine Learning, ICML 2024","author":"Chang","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3378466"},{"key":"ref3","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"CoRR"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_32"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413630"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00812"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680734"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00757"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00151"},{"key":"ref12","article-title":"Liveportrait: Efficient portrait animation with stitching and retargeting control","author":"Guo","year":"2024","journal-title":"CoRR"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"ref14","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"The Twelfth International Conference on Learning Representations, ICLR 2024","author":"Guo","year":"2024"},{"key":"ref15","article-title":"Latent video diffusion models for high-fidelity long video generation","author":"He","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref19","article-title":"FLOAT: generative motion latent flow matching for audio-driven talking portrait","author":"Ki","year":"2024","journal-title":"CoRR"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01051"},{"key":"ref21","article-title":"Obamanet: Photo-realistic lip-sync from text","author":"Kumar","year":"2018","journal-title":"CoRR"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00505"},{"key":"ref23","article-title":"Faceshifter: Towards high fidelity and occlusion aware face swapping","author":"Li","year":"2019","journal-title":"CoRR"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01049"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01049"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109628"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681198"},{"key":"ref29","article-title":"Mediapipe: A framework for building perception pipelines","author":"Lugaresi","year":"2019"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref31","article-title":"Follow-your-click: Open-domain regional image animation via short prompts","author":"Ma","year":"2024","journal-title":"CoRR"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2017-950"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3155571"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00049"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20102"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00281"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref41","article-title":"Style and pose control for image synthesis of humans from a single monocular view","author":"Sarkar","year":"2021","journal-title":"CoRR"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01052"},{"key":"ref43","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"The Eleventh International Conference on Learning Representations, ICLR 2023","author":"Singer","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3146783"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/129"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/141"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02486"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01969"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591517"},{"key":"ref53","article-title":"Hs-diffusion: Semantic-mixing diffusion for head swapping","author":"Wang","year":"2023"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2021\/157"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3449075"},{"key":"ref57","article-title":"Aniportrait: Audio-driven synthesis of photorealistic portrait animation","author":"Wei","year":"2024","journal-title":"CoRR"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475280"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657459"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2024.3365804"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00749"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref65","article-title":"Ip adapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"CoRR"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02116"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687618"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"ref70","article-title":"Controlvideo: Training-free controllable text-to-video generation","volume-title":"The Twelfth International Conference on Learning Representa tions, ICLR 2024","author":"Zhang","year":"2024"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00828"},{"key":"ref73","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"CoRR"}],"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\/11445793.pdf?arnumber=11445793","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:03:26Z","timestamp":1777611806000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445793\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00954","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}