{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T17:01:46Z","timestamp":1780765306462,"version":"3.54.1"},"reference-count":22,"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\/icassp49660.2025.10887583","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T17:15:19Z","timestamp":1741799719000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["DreamVideo: High-Fidelity Image-to-Video Generation with Image Retention and Text Guidance"],"prefix":"10.1109","author":[{"given":"Cong","family":"Wang","sequence":"first","affiliation":[{"name":"Sun Yat-Sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxi","family":"Gu","sequence":"additional","affiliation":[{"name":"Huawei,Noah’ark Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Panwen","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong at Shenzhen,School of Science and Engineering,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[{"name":"Huawei,Noah’ark Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University at Zhuhai,School of Intelligent Engineering,Zhuhai,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Huawei,Noah’ark Lab,China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-Sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01769"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_19"},{"key":"ref3","author":"Yin","year":"2023","journal-title":"Dragnuwa: Fine-grained control in video generation by integrating text, image, and trajectory"},{"key":"ref4","author":"Chen","year":"2023","journal-title":"Videocrafter1: Open diffusion models for high-quality video generation"},{"key":"ref5","volume-title":"Video-composer: Compositional video synthesis with motion controllability","author":"Wang","year":"2023"},{"key":"ref6","volume-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023"},{"key":"ref7","volume":"abs\/2311.15127","author":"Blattmann","year":"2023","journal-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets"},{"key":"ref8","author":"Soomro","year":"2012","journal-title":"UCF101: A dataset of 101 human actions classes from videos in the wild"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref11","article-title":"Auto-encoding variational bayes","volume-title":"2nd International Conference on Learning Representations, ICLR 2014, Banff, AB, Canada, April 14-16, 2014, Conference Track Proceedings","author":"Kingma"},{"key":"ref12","author":"Ho","year":"2022","journal-title":"Classifier-free diffusion guidance"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01764"},{"key":"ref14","author":"Gu","year":"2023","journal-title":"Reuse and diffuse: Iterative denoising for text-to-video generation"},{"key":"ref15","article-title":"pexelvideos","year":"2022"},{"key":"ref16","author":"Singer","year":"2022","journal-title":"Make-a-video: Text-to-video generation without text-video data"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref18","article-title":"FVD: A new metric for video generation","volume-title":"Deep Generative Models for Highly Structured Data, ICLR 2019 Workshop","author":"Unterthiner"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref21","author":"Hong","year":"2022","journal-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"}],"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\/10887583.pdf?arnumber=10887583","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:07Z","timestamp":1774416367000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10887583\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10887583","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}