{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,16]],"date-time":"2026-07-16T14:08:35Z","timestamp":1784210915680,"version":"3.55.0"},"reference-count":63,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2023YFC2705700"],"award-info":[{"award-number":["2023YFC2705700"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2048,623B2076,62225113"],"award-info":[{"award-number":["U23B2048,623B2076,62225113"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001381","name":"National Research Foundation, Singapore","doi-asserted-by":"publisher","award":["RF-P2024-001"],"award-info":[{"award-number":["RF-P2024-001"]}],"id":[{"id":"10.13039\/501100001381","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01475","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15896-15906","source":"Crossref","is-referenced-by-count":2,"title":["Rethink Sparse Signals for Pose-Guided Text-to-Image Generation"],"prefix":"10.1109","author":[{"given":"Wenjie","family":"Xuan","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juhua","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01762"},{"key":"ref2","article-title":"Ediff-i: Text-to-image diffusion models with an ensemble of expert denoisers","author":"Balaji","year":"2022","journal-title":"arXiv preprint"},{"key":"ref3","article-title":"Zoedepth: Zero-shot transfer by combining relative and metric depth","author":"Farooq Bhat","year":"2023","journal-title":"arXiv preprint"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref5","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","volume-title":"In 41st International Conference on Machine Learning","author":"Chang"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00451"},{"key":"ref7","volume-title":"Openmmlab pose estimation toolbox and benchmark","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_6"},{"key":"ref9","article-title":"An image is worth one word: Personalizing text-toimage generation using textual inversion","author":"Gal","year":"2022","journal-title":"arXiv preprint"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02081"},{"key":"ref11","article-title":"Prompt-to-prompt image editing with cross-attention control","volume-title":"The 11th International Conference on Learning Representations","author":"Hertz"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.595"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref14","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","volume":"1","author":"Hu"},{"key":"ref15","first-page":"13753","article-title":"Composer: Creative and controllable image synthesis with composable conditions","volume-title":"In Proceedings of the 40th International Conference on Machine Learning","author":"Huang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2098"},{"key":"ref17","article-title":"Spac-net: Synthetic poseaware animal controlnet for enhanced pose estimation","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/wacv61041.2025.00077"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00067"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01465"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02073"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1303"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00708"},{"key":"ref24","article-title":"Dispose: Disentangling pose guidance for controllable human image animation","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","first-page":"129","article-title":"Controlnet++: Improving conditional controls with efficient consistency feedback","volume-title":"In European Conference on Computer Vision","author":"Li"},{"key":"ref26","article-title":"Ecnet: Effective controllable text-to-image diffusion models","volume":"1","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02156"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV66043.2025.00107"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4095"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref31","article-title":"Hyperhuman: Hyper-realistic human generation with latent structural diffusion","volume-title":"In The 12th International Conference on Learning Representations","author":"Liu"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73195-2_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680693"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00513"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00713"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28226"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687611"},{"key":"ref39","article-title":"Controlnext: Powerful and efficient control for image and video generation","author":"Peng","year":"2024","journal-title":"arXiv preprint"},{"key":"ref40","article-title":"Learn, imagine and create: Text-to-image generation from prior knowledge","volume":"32","author":"Qiao","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00160"},{"key":"ref42","article-title":"Unicontrol: A unified diffusion model for controllable visual generation in the wild","volume-title":"Proceedings of the 37th International Conference on Neural Information Processing Systems","volume":"1","author":"Qin"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.48"},{"key":"ref45","first-page":"1","year":"2022","journal-title":"Stable Diffusion"},{"key":"ref46","article-title":"Advancing pose-guided image synthesis with progressive conditional diffusion models","volume-title":"The 12th International Conference on Learning Representations","author":"Shen"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-023-1438-4"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.310"},{"issue":"86","key":"ref50","first-page":"2579","article-title":"Visualizing data using t -sne","volume":"9","author":"der Maaten","year":"2008","journal-title":"Journal of Machine Learning Research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2795"},{"key":"ref52","article-title":"Animatezoo: Zero-shot video generation of cross-species animation via subject alignment","author":"Xu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3330016"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680692"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33032"},{"key":"ref57","article-title":"Ap-10k: A benchmark for animal pose estimation in the wild","volume-title":"In 35th Conference on Neural Information Processing Systems Datasets and Benchmarks Track","author":"Yu"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00789"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref60","first-page":"1","article-title":"Uni-controlnet: All-in-one control to text-to-image diffusion models","volume":"36","author":"Zhao","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2170"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_10"},{"key":"ref63","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\/11445518.pdf?arnumber=11445518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:09Z","timestamp":1777613529000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":63,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01475","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}