{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T07:11:38Z","timestamp":1761894698938,"version":"build-2065373602"},"reference-count":36,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1109\/icme59968.2025.11210223","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":0,"title":["UniVG: Towards UNIfied-modal Video Generation"],"prefix":"10.1109","author":[{"given":"Ludan","family":"Ruan","sequence":"first","affiliation":[{"name":"Baidu Inc.,Beijing,China"}]},{"given":"Lei","family":"Tian","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Beijing,China"}]},{"given":"Chuanwei","family":"Huang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Beijing,China"}]},{"given":"Xu","family":"Zhang","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Beijing,China"}]},{"given":"Xinyan","family":"Xiao","sequence":"additional","affiliation":[{"name":"Baidu Inc.,Beijing,China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref2","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref3","article-title":"Improved techniques for training score-based generative models","author":"Song","year":"2020","journal-title":"NeurIPS"},{"key":"ref4","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref5","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2022","journal-title":"ICML"},{"article-title":"Hierarchical text-conditional image generation with clip latents","year":"2022","author":"Ramesh","key":"ref6"},{"key":"ref7","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","author":"Saharia","year":"2022","journal-title":"NeurIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02349-y"},{"key":"ref10","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"article-title":"Imagen video: High definition video generation with diffusion models","year":"2022","author":"Ho","key":"ref11"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_12"},{"article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","year":"2023","author":"Blattmann","key":"ref13"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02096"},{"article-title":"Modelscope text-to-video technical report","year":"2023","author":"Wang","key":"ref16"},{"key":"ref17","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2022","journal-title":"ICLR"},{"article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","year":"2022","author":"He","key":"ref18"},{"article-title":"Videocrafter1: Open diffusion models for high-quality video generation","year":"2023","author":"Chen","key":"ref19"},{"article-title":"Videogen: A reference-guided latent diffusion approach for high definition text-to-video generation","year":"2023","author":"Li","key":"ref20"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02271-9"},{"article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","year":"2023","author":"Zhang","key":"ref22"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00845"},{"article-title":"Magicvideo: Efficient video generation with latent diffusion models","year":"2022","author":"Zhou","key":"ref24"},{"key":"ref25","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2022","journal-title":"ICLR"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00037"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00684"},{"key":"ref30","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"ICLR"},{"key":"ref31","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford","key":"ref32"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"article-title":"Godiva: Generating open-domain videos from natural descriptions","year":"2021","author":"Wu","key":"ref34"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00331"},{"article-title":"Internvid: A large-scale video-text dataset for multimodal understanding and generation","year":"2023","author":"Wang","key":"ref36"},{"article-title":"Latent-shift: Latent diffusion with temporal shift for efficient text-to-video generation","year":"2023","author":"An","key":"ref37"},{"article-title":"SDXL: improving latent diffusion models for high-resolution image synthesis","year":"2023","author":"Podell","key":"ref38"}],"event":{"name":"2025 IEEE International Conference on Multimedia and Expo (ICME)","start":{"date-parts":[[2025,6,30]]},"location":"Nantes, France","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\/11210223.pdf?arnumber=11210223","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T05:33:55Z","timestamp":1761888835000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11210223\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":36,"URL":"https:\/\/doi.org\/10.1109\/icme59968.2025.11210223","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]}}}