{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T06:29:11Z","timestamp":1774420151205,"version":"3.50.1"},"reference-count":38,"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"}],"funder":[{"DOI":"10.13039\/501100002402","name":"Sun Yat-sen University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002402","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,4,6]]},"DOI":"10.1109\/icassp49660.2025.10889997","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":0,"title":["EasyControl: Adding Control to Video Diffusion for Controllable Video Generation and Interpolation"],"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":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaxi","family":"Gu","sequence":"additional","affiliation":[{"name":"Noah’ark Lab Huawei,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Panwen","family":"Hu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong at Shenzhen,School of Science and Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiao","family":"Dong","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University at Zhuhai,School of Intelligent Engineering,Zhuhai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuanfan","family":"Guo","sequence":"additional","affiliation":[{"name":"Noah’ark Lab Huawei,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hang","family":"Xu","sequence":"additional","affiliation":[{"name":"Noah’ark Lab Huawei,Shanghai,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaodan","family":"Liang","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University at Shenzhen,School of Intelligent Engineering,Shenzhen,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho"},{"key":"ref2","article-title":"Videocomposer: Compositional video synthesis with motion controllability","volume-title":"NeurIPS","author":"W"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3556544"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"ref5","first-page":"250","article-title":"FILM: frame interpolation for large motion","volume-title":"ECCV","volume":"13667","author":"T"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-01144-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref8","first-page":"624","article-title":"Real-time intermediate flow estimation for video frame interpolation","volume-title":"ECCV","volume":"13674","author":"H"},{"key":"ref9","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"B","year":"2023","journal-title":"CoRR"},{"key":"ref10","article-title":"Videocrafter1: Open diffusion models for high-quality video generation","author":"C","year":"2024"},{"key":"ref11","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Z","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_12"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925972"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00675"},{"key":"ref16","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2023"},{"key":"ref17","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023"},{"key":"ref18","article-title":"Modelscope text-to-video technical report","author":"W","year":"2023","journal-title":"CoRR"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27912"},{"key":"ref20","article-title":"U-net: Convolutional networks for biomedical image segmentation","volume-title":"MICCAI","author":"R"},{"key":"ref21","first-page":"563","article-title":"An edge-based approach to motion detection","volume-title":"ICCS","volume":"3991","author":"S"},{"key":"ref22","first-page":"1395","article-title":"Holistically-nested edge detection","volume-title":"ICCV","author":"X"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3019967"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3132703"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72646-0_22"},{"key":"ref26","article-title":"Reuse and diffuse: Iterative de-noising for text-to-video generation","author":"Gu","year":"2023"},{"key":"ref27","article-title":"pexelvideos","year":"2022"},{"key":"ref28","article-title":"UCF101: A dataset of 101 human actions classes from videos in the wild","author":"Soomro","year":"2012"},{"key":"ref29","first-page":"5288","article-title":"MSR-VTT: A large video description dataset for bridging video and language","volume-title":"CVPR","author":"X"},{"key":"ref30","article-title":"The 2017 DAVIS challenge on video object segmentation","author":"P","year":"2017","journal-title":"CoRR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"ref32","article-title":"FVD: A new metric for video generation","volume-title":"ICLR","author":"U"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.502"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01333-y"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00984"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3298645"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2003.819861"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"}],"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\/10889997.pdf?arnumber=10889997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T05:26:41Z","timestamp":1774416401000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10889997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,6]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/icassp49660.2025.10889997","relation":{},"subject":[],"published":{"date-parts":[[2025,4,6]]}}}