{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:10:21Z","timestamp":1778051421951,"version":"3.51.4"},"reference-count":70,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"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":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00386","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"3961-3971","source":"Crossref","is-referenced-by-count":0,"title":["Mobile-Oriented Video Diffusion: Enabling Text-to-Video Generation on Mobile Devices Without Retraining, Compression, or Pruning"],"prefix":"10.1109","author":[{"given":"Bosung","family":"Kim","sequence":"first","affiliation":[{"name":"Ulsan National Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kyuhwan","family":"Lee","sequence":"additional","affiliation":[{"name":"Ulsan National Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Isu","family":"Jeong","sequence":"additional","affiliation":[{"name":"Ulsan National Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jungmin","family":"Cheon","sequence":"additional","affiliation":[{"name":"Ulsan National Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeojin","family":"Lee","sequence":"additional","affiliation":[{"name":"Ulsan National Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Seulki","family":"Lee","sequence":"additional","affiliation":[{"name":"Ulsan National Institute of Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","article-title":"iphone 15 pro\u2014technical specifications","year":"2023"},{"key":"ref2","article-title":"Swift","year":"2024"},{"key":"ref3","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023"},{"key":"ref4","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022"},{"key":"ref5","article-title":"Token merging: Your ViT but faster","volume-title":"International Conference on Learning Representations","author":"Bolya"},{"key":"ref6","article-title":"Edgefusion: On-device text-to-image generation","author":"Castells","year":"2024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1263"},{"key":"ref8","article-title":"Neural ordinary differential equations","volume":"31","author":"Chen","year":"2018","journal-title":"Advances in neural information processing systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01265"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00490"},{"key":"ref11","article-title":"Squeezing large-scale diffusion models for mobile","author":"Choi","year":"2023"},{"key":"ref12","article-title":"Tutorial on variational autoencoders","author":"Doersch","year":"2016"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3293763"},{"key":"ref15","article-title":"Efficient time series processing for transformers and state-space models through token merging","author":"G\u00f6tz","year":"2024"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref18","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref19","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref20","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"issue":"47","key":"ref21","first-page":"1","article-title":"Cascaded diffusion models for high fidelity image generation","volume":"23","author":"Ho","year":"2022","journal-title":"Journal of Machine Learning Research"},{"key":"ref22","first-page":"1587","article-title":"Toward controlled generation of text","volume-title":"International conference on machine learning","author":"Hu"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref24","article-title":"Pyramidal flow matching for efficient video generative modeling","author":"Jin","year":"2024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"ref26","article-title":"Hunyuanvideo: A systematic framework for large video generative models","author":"Kong","year":"2024"},{"key":"ref27","article-title":"Flux","year":"2024"},{"key":"ref28","article-title":"xformers: A modular and hackable transformer modelling library","author":"Lefaudeux","year":"2022"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref30","article-title":"Snapfusion: Text-to-image diffusion model on mobile devices within two seconds","volume":"36","author":"Li","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref31","article-title":"Animatediff-lightning: Cross-model diffusion distillation","author":"Lin","year":"2024"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2021.3049196"},{"key":"ref33","article-title":"Flow straight and fast: Learning to generate and transfer data with rectified flow","author":"Liu","year":"2022"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00672"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2021.03.091"},{"key":"ref37","volume-title":"Generative models for video analysis and 3D range data applications","author":"Orriols","year":"2004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"issue":"140","key":"ref39","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/72.248452"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/BF01446807"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6421-8_2"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00467"},{"key":"ref47","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/356887.356892"},{"key":"ref50","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2022.2035253"},{"key":"ref52","article-title":"Vidgen-1m: A large-scale dataset for text-to-video generation","author":"Tan","year":"2024"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681050"},{"key":"ref54","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3681758.3698013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-demos.6"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755081"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.00237"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01808"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3626235"},{"key":"ref62","article-title":"Cogvideox: Text-to-video diffusion models with an expert transformer","author":"Yang","year":"2024"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02180"},{"key":"ref64","article-title":"Fast video generation with sliding tile attention","author":"Zhang","year":"2025"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1563-3"},{"key":"ref66","article-title":"Vidit-q: Efficient and accurate quantization of diffusion transformers for image and video generation","author":"Zhao","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_13"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2423"},{"key":"ref69","article-title":"Open-sora: Democratizing efficient video production for all","author":"Zheng","year":"2024"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73007-8_20"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492472.pdf?arnumber=11492472","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:10:13Z","timestamp":1778047813000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492472\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":70,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00386","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}