{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:02:55Z","timestamp":1777888975854,"version":"3.51.4"},"reference-count":37,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01668","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"17951-17960","source":"Crossref","is-referenced-by-count":0,"title":["VideoVAE+: Large Motion Video Autoencoding with Cross-Modal Video VAE"],"prefix":"10.1109","author":[{"given":"Yazhou","family":"Xing","sequence":"first","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Fei","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingqing","family":"He","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingye","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxin","family":"Xie","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Chi","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qifeng","family":"Chen","sequence":"additional","affiliation":[{"name":"The Hong Kong University of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","year":"2023","journal-title":"Stable diffusion 3.5 large"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref3","article-title":"Vidu: a highly consistent, dynamic and skilled text-to-video generator with diffusion models","author":"Bao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arXiv preprint"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02161"},{"key":"ref6","author":"Brooks","year":"2024","journal-title":"Video generation models as world simulators"},{"key":"ref7","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"Chen","year":"2023","journal-title":"arXiv preprint"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icme59968.2025.11210036"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref11","author":"Chi","year":"2024","journal-title":"Mmtrail: A multimodal trailer video dataset with language and music descriptions"},{"issue":"70","key":"ref12","first-page":"1","article-title":"Scaling instructionfinetuned language models","volume":"25","author":"Won Chung","year":"2024","journal-title":"Journal of Machine Learning Research"},{"key":"ref13","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","volume-title":"The Twelfth International Conference on Learning Representations","author":"Guo"},{"key":"ref14","article-title":"Latent video diffusion models for high-fidelity video generation with arbitrary lengths","author":"He","year":"2022","journal-title":"arXiv preprint"},{"key":"ref15","author":"He","year":"2023","journal-title":"Latent video diffusion models for high-fidelity long video generation"},{"key":"ref16","first-page":"1","article-title":"Auto-encoding variational bayes","volume":"1050","author":"Kingma","year":"2014","journal-title":"stat"},{"key":"ref17","year":"2024","journal-title":"Open-sora-plan"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01656"},{"key":"ref19","article-title":"Latte: Latent diffusion transformer for video generation","author":"Ma","year":"2024","journal-title":"arXiv preprint"},{"key":"ref20","year":"2024","journal-title":"Cosmos tokenizer: A suite of image and video neural tokenizers"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/tip.2022.3227503"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/s00530-014-0446-1"},{"key":"ref24","article-title":"Vidtok: A versatile and open-source video tokenizer","author":"Tang","year":"2024","journal-title":"arXiv preprint"},{"key":"ref25","year":"2024","journal-title":"Movie gen: A cast of media foundation models"},{"key":"ref26","author":"Unterthiner","year":"2019","journal-title":"Fvd: A new metric for video generation"},{"key":"ref27","author":"Zhang","year":"2024","journal-title":"Hunyuanvideo: A systematic framework for large video generative models"},{"key":"ref28","article-title":"Improved video vae for latent video diffusion model","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72952-2_23"},{"key":"ref30","author":"Xu","year":"2024","journal-title":"Easyanimate: A high-performance long video generation method based on transformer architecture"},{"key":"ref31","author":"Yang","year":"2024","journal-title":"Cogvideox: Text-to-video diffusion models with an expert transformer"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref33","article-title":"Language model beats diffusion-tokenizer is key to visual generation","volume-title":"International Conference on Learning Representations","author":"Yu"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref35","article-title":"Cv-vae: A compatible video vae for latent generative video models","author":"Zhao","year":"2024","journal-title":"arXiv preprint"},{"key":"ref36","author":"Zheng","year":"2024","journal-title":"Open-sora: Democratizing efficient video production for all"},{"key":"ref37","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"}],"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\/11449026.pdf?arnumber=11449026","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:04:08Z","timestamp":1777611848000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449026\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":37,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01668","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}