{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:12:48Z","timestamp":1774419168487,"version":"3.50.1"},"reference-count":39,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,4,6]],"date-time":"2025-04-06T00:00:00Z","timestamp":1743897600000},"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"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889218","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Anima\n                    <sup>2<\/sup>\n                    : Cross-Species Animal Animation through Image-to-Video Synthesis with Subject Alignment"],"prefix":"10.1109","author":[{"given":"Yuanfeng","family":"Xu","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuhao","family":"Chen","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhongzhan","family":"Huang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zijian","family":"He","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guangrun","family":"Wang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.image.2025.117277"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00725"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref5","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72643-9_8"},{"key":"ref7","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref8","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":"ref9","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","author":"Hu","year":"2023"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5842"},{"key":"ref11","first-page":"70376","article-title":"Scalelong: Towards more stable training of diffusion model via scaling network long skip connection","volume":"36","author":"Huang","year":"2023","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01376"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02037"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00190"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1038\/s41593-018-0209-y"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01844"},{"key":"ref22","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref24","article-title":"Vase: Object-centric appearance and shape manipulation of real videos","author":"Peruzzo","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref29","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01344"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00055"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00633"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00147"},{"key":"ref36","article-title":"Aptv2: Benchmarking animal pose estimation and tracking with a large-scale dataset and beyond","author":"Yang","year":"2023"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00364"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611863"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3450630"}],"event":{"name":"ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Hyderabad, India","start":{"date-parts":[[2025,4,6]]},"end":{"date-parts":[[2025,4,11]]}},"container-title":["ICASSP 2025 - 2025 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10887540\/10887541\/10889218.pdf?arnumber=10889218","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:21:02Z","timestamp":1774416062000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889218\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":39,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889218","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}