{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:06:47Z","timestamp":1777889207424,"version":"3.51.4"},"reference-count":61,"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\/iccv51701.2025.01577","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"16981-16990","source":"Crossref","is-referenced-by-count":0,"title":["Versatile Transition Generation with Image-to-Video Diffusion"],"prefix":"10.1109","author":[{"given":"Zuhao","family":"Yang","sequence":"first","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiahui","family":"Zhang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yingchen","family":"Yu","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[{"name":"Nanyang Technological University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Song","family":"Bai","sequence":"additional","affiliation":[{"name":"ByteDance Inc."}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.47577\/technium.v9i.8699"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/142920.134003"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5121\/sipij.2011.2420"},{"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","article-title":"Linear combinations of latents in generative models: subspaces and beyond","volume-title":"ICLR","author":"Bodin","year":"2025"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00698"},{"key":"ref8","article-title":"Seine: Short-to-long video diffusion model for generative transition and prediction","volume-title":"ICLR","author":"Chen","year":"2023"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185578"},{"key":"ref10","article-title":"Infinite-resolution integral noise warping for diffusion models","volume-title":"ICLR","author":"Deng","year":"2025"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3556544"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73229-4_22"},{"key":"ref13","article-title":"Tc-bench: Benchmarking temporal compositionality in text-to-video and image-to-video generation","volume-title":"ACL","author":"Feng","year":"2025"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14027"},{"key":"ref15","article-title":"Generative adversarial nets","volume-title":"NeurIPS","author":"Goodfellow","year":"2014"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3101"},{"key":"ref17","article-title":"Classifier-free diffusion guidance","volume-title":"NeurIPS Workshop","author":"Ho","year":"2021"},{"key":"ref18","article-title":"Denoising diffusion probabilistic models","volume-title":"NeurIPS","author":"Ho","year":"2020"},{"key":"ref19","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref20","article-title":"Lora: Low-rank adaptation of large language models","volume-title":"ICLR","author":"Hu","year":"2022"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00701"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00201"},{"key":"ref24","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009","journal-title":"Toronto, ON, Canada"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00945"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2629494"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01809"},{"key":"ref28","article-title":"Fixing weight decay regularization in adam","author":"Loshchilov","year":"2018","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011161132514"},{"key":"ref30","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","volume-title":"ICML","author":"Nichol","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00548"},{"key":"ref32","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"TMLR"},{"key":"ref33","article-title":"Geodesics, Splines, and Embeddings in Spaces of Images","volume-title":"PhD thesis, Universit\u00e4ts-und Landesbibliothek Bonn","author":"Rajkovi\u0107","year":"2023"},{"key":"ref34","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_15"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume-title":"NeurIPS","author":"Saharia","year":"2022"},{"key":"ref39","article-title":"Laion-5b: An open large-scale dataset for training next generation image-text models","volume-title":"NeurIPS","author":"Schuhmann","year":"2022"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2010.5540159"},{"key":"ref41","article-title":"Make-a-video: Text-to-video generation without text-video data","volume-title":"ICLR","author":"Singer","year":"2023"},{"key":"ref42","article-title":"Denoising diffusion implicit models","volume-title":"ICLR","author":"Song","year":"2021"},{"key":"ref43","article-title":"Score-based generative modeling through stochastic differential equations","volume-title":"ICLR","author":"Song","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00753"},{"key":"ref45","article-title":"Interpolating between images with diffusion models","volume-title":"ICMLW","author":"Wang","year":"2023"},{"key":"ref46","article-title":"Generative inbetweening: Adapting image-to-video models for keyframe interpolation","volume-title":"ICLR","author":"Wang","year":"2025"},{"key":"ref47","article-title":"Lavie: High-quality video generation with cascaded latent diffusion models","author":"Wang","year":"2024","journal-title":"IJCV"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657518"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s003710050148"},{"key":"ref50","article-title":"Dynamicrafter: Animating open-domain images with video diffusion priors","volume-title":"ECCV","author":"Xing","year":"2024"},{"key":"ref51","article-title":"Realworld denoising via diffusion model","author":"Yang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref52","article-title":"Impus: Image morphing with perceptually-uniform sampling using diffusion models","volume-title":"ICLR","author":"Yang","year":"2024"},{"key":"ref53","article-title":"Representation alignment for generation: Training diffusion transformers is easier than you think","volume-title":"ICLR","author":"Yu","year":"2025"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00845"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00550"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00756"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3547337"},{"key":"ref58","article-title":"I2vgen-xl: High-quality image-to-video synthesis via cascaded diffusion models","author":"Zhang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref59","article-title":"Identifying and solving conditional image leakage in image-to-video diffusion model","volume-title":"NeurIPS","author":"Zhao","year":"2024"},{"key":"ref60","article-title":"Magicvideo: Efficient video generation with latent diffusion models","author":"Zhou","year":"2022","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.24001\/ijaems.3.2.15"}],"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\/11445507.pdf?arnumber=11445507","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:08:04Z","timestamp":1777612084000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445507\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01577","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}