{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:26:08Z","timestamp":1774419968197,"version":"3.50.1"},"reference-count":32,"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\/icassp49660.2025.10890195","type":"proceedings-article","created":{"date-parts":[[2025,3,12]],"date-time":"2025-03-12T13:52:43Z","timestamp":1741787563000},"page":"1-5","source":"Crossref","is-referenced-by-count":0,"title":["Do Less and Achieve More: Free Condition Video Outpainting with Diffusion Model"],"prefix":"10.1109","author":[{"given":"Haofan","family":"Huang","sequence":"first","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinlin","family":"Guo","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yening","family":"Lv","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sizhe","family":"Shan","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Zhang","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuehai","family":"Wang","sequence":"additional","affiliation":[{"name":"Zhejiang University,College of Information Science and Electronic Engineering,Hangzhou,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01008"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01114"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00090"},{"key":"ref5","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3054477"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01517"},{"key":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref10","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref12","article-title":"Elucidating the design space of diffusion-based generative models","author":"Karras","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref14","article-title":"Denoising diffusion implicit models","volume-title":"International Conference on Learning Representations","author":"Song"},{"key":"ref15","first-page":"16 784","article-title":"Glide: Towards photo-realistic image generation and editing with text-guided diffusion models","volume-title":"International Conference on Machine Learning","author":"Nichol"},{"key":"ref16","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS 2021 Workshop on Deep Generative Models and Downstream Applications","author":"Ho"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref18","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":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00084"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612478"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72784-9_9"},{"key":"ref22","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref23","first-page":"19 730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"International conference on machine learning","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.85"},{"key":"ref26","article-title":"Youtube-vos: A large-scale video object segmentation benchmark","author":"Xu","year":"2018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00175"},{"key":"ref28","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref31","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref32","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"ICML","author":"Li"}],"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\/10890195.pdf?arnumber=10890195","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:25:41Z","timestamp":1774416341000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10890195\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":32,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10890195","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}