{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:24:10Z","timestamp":1774419850595,"version":"3.50.1"},"reference-count":35,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10890233","type":"proceedings-article","created":{"date-parts":[[2025,3,11]],"date-time":"2025-03-11T13:33:09Z","timestamp":1741699989000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Follow-Your-MultiPose: Tuning-Free Multi-Character Text-to-Video Generation via Pose Guidance"],"prefix":"10.1109","author":[{"given":"Beiyuan","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yue","family":"Ma","sequence":"additional","affiliation":[{"name":"Computer Science Engineer, The Hong Kong University of Science and Technology, Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chunlei","family":"Fu","sequence":"additional","affiliation":[{"name":"School of Big Data and Software Engineering, Chongqing University, Chongqing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xinyang","family":"Song","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China;  New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenan","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China\n4 New Laboratory of Pattern Recognition (NLPR), Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziqiang","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Civitai","volume-title":"Civitai","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00603"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3018224"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00690"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00756"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref7","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv preprint"},{"issue":"2","key":"ref8","first-page":"3","article-title":"Hierarchical text-conditional image generation with clip latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01042"},{"key":"ref10","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia","year":"2022","journal-title":"Advances in neural information processing systems"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28206"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.02073"},{"key":"ref13","article-title":"Advancing pose-guided image synthesis with progressive conditional diffusion models","author":"Shen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00578"},{"key":"ref16","article-title":"Llama2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref18","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref21","article-title":"Controlvideo: Adding conditional control for one shot text-to-video editing","author":"Zhao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref24","article-title":"First order motion model for image animation","volume":"32","author":"Siarohin","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref26","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00455"},{"key":"ref28","article-title":"Follow-Your-Click: Open-domain Regional Image Animation via Short Prompts","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00909"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687587"},{"key":"ref31","article-title":"Follow-Your-Canvas: Higher-Resolution Video Outpainting with Extensive Content Generation","author":"Chen","year":"2024","journal-title":"arXiv preprint"},{"key":"ref32","article-title":"COVE: Unleashing the Diffusion Feature Correspondence for Consistent Video Editing","author":"Wang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref33","article-title":"InstantSwap: Fast Customized Concept Swapping across Sharp Shape Differences","author":"Zhu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref34","article-title":"See Through Their Minds: Learning Transferable Neural Representation from Cross-Subject fMRI","author":"Liu","year":"2024","journal-title":"arXiv [cs.CV]"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32304"}],"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\/10890233.pdf?arnumber=10890233","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:02Z","timestamp":1774416302000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890233\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890233","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}