{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:19:00Z","timestamp":1778048340777,"version":"3.51.4"},"reference-count":58,"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\/wacv61042.2026.00817","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"8468-8478","source":"Crossref","is-referenced-by-count":0,"title":["SmoothDiffusion-VE: Real-time Generative Video Editing Using Adaptive Feature Cache"],"prefix":"10.1109","author":[{"given":"Mustafa","family":"Munir","sequence":"first","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sophia","family":"Zalewski","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shiqiu","family":"Liu","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"David","family":"Tarjan","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sushmitha","family":"Belede","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anjul","family":"Patney","sequence":"additional","affiliation":[{"name":"NVIDIA Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Radu","family":"Marculescu","sequence":"additional","affiliation":[{"name":"The University of Texas at Austin"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00484"},{"key":"ref2","article-title":"Token merging: Your vit but faster","author":"Bolya","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02121"},{"key":"ref6","article-title":"Control-a-video: Controllable text-to-video generation with diffusion models","author":"Chen","year":"2023"},{"key":"ref7","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02060"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-45103-X_50"},{"key":"ref10","article-title":"An image is worth one word: Personalizing text-to-image generation using textual inversion","author":"Gal","year":"2022"},{"key":"ref11","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72986-7_23"},{"key":"ref14","article-title":"Lora+: Efficient low rank adaptation of large models","author":"Hayou","year":"2024"},{"key":"ref15","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref17","article-title":"Self forcing: Bridging the traintest gap in autoregressive video diffusion","author":"Huang","year":"2025"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_36"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00976"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.01150"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.5555\/2999134.2999257"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_11"},{"key":"ref24","article-title":"xformers: A modular and hackable transformer modelling library","author":"Lefaudeux","year":"2022"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01006"},{"key":"ref26","article-title":"Looking backward: Streaming video-to-video translation with feature banks","author":"Liang","year":"2024"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00784"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01765"},{"key":"ref29","article-title":"Autoregressive adversarial post-training for real-time interactive video generation","author":"Lin","year":"2025"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"ref31","article-title":"Diffusion hyperfeatures: Searching through time and space for semantic correspondence","volume":"36","author":"Luo","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00101"},{"key":"ref33","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2021"},{"key":"ref34","volume-title":"Rtx sdk for video super resolution","year":"2024"},{"issue":"285-296","key":"ref35","first-page":"23","article-title":"A threshold selection method from gray-level histograms","volume":"11","author":"Otsu","year":"1975","journal-title":"Automatica"},{"key":"ref36","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref37","article-title":"The 2017 davis challenge on video object segmentation","author":"Pont-Tuset","year":"2017"},{"key":"ref38","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref39","first-page":"1060","article-title":"Generative adversarial text to image synthesis","volume-title":"International conference on machine learning","author":"Reed"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687625"},{"key":"ref44","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref45","article-title":"Sdxs: Real-time one-step latent diffusion models with image conditions","author":"Song","year":"2024"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01602"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58536-5_24"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00786"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0907"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00809"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/83.366472"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00632"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00595"}],"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\/11492368.pdf?arnumber=11492368","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T05:56:09Z","timestamp":1778046969000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492368\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":58,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00817","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}