{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,14]],"date-time":"2026-11-14T08:24:01Z","timestamp":1794644641133,"version":"4.9.1"},"reference-count":30,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,6,30]],"date-time":"2025-06-30T00:00:00Z","timestamp":1751241600000},"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":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11209788","type":"proceedings-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T17:57:42Z","timestamp":1761847062000},"page":"1-6","source":"Crossref","is-referenced-by-count":3,"title":["STP4D: Spatio-Temporal-Prompt Consistent Modeling for Text-To-4D Gaussian Splatting"],"prefix":"10.1109","author":[{"given":"Yunze","family":"Deng","sequence":"first","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haijun","family":"Xiong","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Feng","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinggang","family":"Wang","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wenyu","family":"Liu","sequence":"additional","affiliation":[{"name":"Huazhong University of Science and Technology,School of Electronic Information and Communications,Wuhan,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","author":"Liu","year":"2024","journal-title":"A comprehensive survey on 3d content generation"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01922"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00404"},{"key":"ref4","author":"Liang","year":"2024","journal-title":"Diffusion4d: Fast spatial-temporal consistent 4d generation via video diffusion models"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3746284"},{"key":"ref6","author":"Yi","year":"2023","journal-title":"Gaussiandreamer: Fast generation from text to 3d gaussian splatting with point cloud priors"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00764"},{"key":"ref8","article-title":"Prolificdreamer: High-fidelity and diverse text-to-3d generation with variational score distillation","volume":"36","author":"Wang","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","author":"Singer","year":"2023","journal-title":"Text-to-4d dynamic scene generation"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3261988"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3361474"},{"key":"ref13","author":"Song","year":"2020","journal-title":"Denoising diffusion implicit models"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01920"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657463"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref17","first-page":"1212","article-title":"Probability distillation: A caveat and alternatives","volume-title":"Uncertainty in Artificial Intelligence","author":"Huang","year":"2020"},{"key":"ref18","author":"Poole","year":"2022","journal-title":"Dream-fusion: Text-to-3d using 2d diffusion"},{"key":"ref19","author":"Zhao","year":"2023","journal-title":"Animate124: Animating one image to 4d dynamic scene"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00819"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00697"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72764-1_10"},{"key":"ref23","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01201"},{"key":"ref25","article-title":"Condaformer: Disassembled transformer with local structure enhancement for 3d point cloud understanding","volume":"36","author":"Duan","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref26","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref28","first-page":"109","article-title":"As-rigid-as-possible surface modeling","volume-title":"Symposium on Geometry processing","volume":"4","author":"Sorkine"},{"key":"ref29","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1504\/IJAIP.2020.107011"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","location":"Nantes, France","start":{"date-parts":[[2025,6,30]]},"end":{"date-parts":[[2025,7,4]]}},"container-title":["2025 IEEE International Conference on Multimedia and Expo (ICME)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11208895\/11208897\/11209788.pdf?arnumber=11209788","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:32:18Z","timestamp":1761888738000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11209788\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":30,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11209788","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}