{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T07:11:47Z","timestamp":1778051507848,"version":"3.51.4"},"reference-count":92,"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\/wacv61042.2026.00709","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"7344-7354","source":"Crossref","is-referenced-by-count":0,"title":["Zero-Shot Audio-Visual Editing via Cross-Modal Delta Denoising"],"prefix":"10.1109","author":[{"given":"Yan-Bo","family":"Lin","sequence":"first","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhengyuan","family":"Yang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Linjie","family":"Li","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfeng","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chung-Ching","family":"Lin","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gedas","family":"Bertasius","sequence":"additional","affiliation":[{"name":"UNC Chapel Hill"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lijuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Microsoft"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_41"},{"key":"ref3","article-title":"Sonicdiffusion: Audio-driven image generation and editing with pretrained diffusion models","author":"Biner","year":"2024"},{"key":"ref4","article-title":"Videoldm: Text-to-video generation with latent diffusion models","author":"Blattmann","year":"2023","journal-title":"ICLR"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref7","article-title":"Semantically consistent video-to-audio generation using multimodal language large model","author":"Chen","year":"2024"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.52202\/079017-2700"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01749"},{"key":"ref11","article-title":"Slicedit: Zero-shot video editing with text-to-image diffusion models using spatio-temporal slices","author":"Cohen","year":"2024","journal-title":"ICML"},{"key":"ref12","article-title":"Diffusion models beat gans on image synthesis","author":"Dhariwal","year":"2021","journal-title":"NeurIPS"},{"key":"ref13","article-title":"Scaling rectified flow transformers for high-resolution image synthesis","author":"Esser","year":"2024","journal-title":"ICML"},{"key":"ref14","article-title":"Fast timing-conditioned latent audio diffusion","author":"Evans","year":"2024","journal-title":"ICML"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73254-6_14"},{"key":"ref16","article-title":"Tokenflow: Consistent diffusion features for consistent video editing","author":"Geyer","year":"2023","journal-title":"ICLR"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00221"},{"key":"ref19","article-title":"Prompt-to-prompt image editing with cross attention control","author":"Hertz","year":"2023","journal-title":"ICLR"},{"key":"ref20","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Imagen video: High definition video generation with diffusion models","author":"Ho","year":"2022"},{"key":"ref22","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022"},{"key":"ref23","article-title":"Video diffusion models","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref24","article-title":"Cogvideo: Large-scale pretraining for text-to-video generation via transformers","author":"Hong","year":"2023","journal-title":"ICLR"},{"key":"ref25","article-title":"Noise2music: Textconditioned music generation with diffusion models","author":"Huang","year":"2023"},{"key":"ref26","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","author":"Huang","year":"2023","journal-title":"ICML"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ijcnn64981.2025.11228639"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73404-5_21"},{"key":"ref29","article-title":"Ground-a-video: Zero-shot grounded video editing using text-to-image diffusion models","author":"Jeong","year":"2024","journal-title":"ICLR"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00719"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10887821"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00622"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480546"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01462"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00246"},{"key":"ref36","article-title":"A versatile diffusion transformer with mixture of noise levels for audiovisual generation","author":"Kim","year":"2024","journal-title":"NeurIPS"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01410"},{"key":"ref38","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_3"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01376"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CAI59869.2024.00146"},{"key":"ref42","article-title":"Muvi: Video-to-music generation with semantic alignment and rhythmic synchronization","author":"Li","year":"2024"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00715"},{"key":"ref44","article-title":"Language-guided joint audio-visual editing via one-shot adaptation","author":"Liang","year":"2024","journal-title":"ACCV"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00120"},{"key":"ref46","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"ICML"},{"key":"ref47","article-title":"Medic: Zero-shot music editing with disentangled inversion control","author":"Liu","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00821"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2121"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref53","article-title":"Zero-shot unsupervised and text-based audio editing using ddpm inversion","author":"Manor","year":"2024","journal-title":"ICML"},{"key":"ref54","article-title":"Sdedit: Guided image synthesis and editing with stochastic differential equations","author":"Meng","year":"2022","journal-title":"ICLR"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00878"},{"key":"ref56","article-title":"Improved denoising diffusion probabilistic models","author":"Nichol","year":"2021","journal-title":"ICML"},{"key":"ref57","article-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73021-4_15"},{"key":"ref59","article-title":"Movie gen: A cast of media foundation models","author":"Polyak","year":"2024"},{"key":"ref60","article-title":"Dreamfusion: Text-to-3d using 2d diffusion","author":"Poole","year":"2023","journal-title":"ICLR"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01460"},{"key":"ref62","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref63","article-title":"Hierarchical text-conditional image generation with clip latents","author":"Ramesh","year":"2022"},{"key":"ref64","article-title":"Zero-shot text-to-image generation","author":"Ramesh","year":"2021","journal-title":"ICML"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref66","article-title":"Mmdiffusion: Learning multi-modal diffusion models for joint audio and video generation. 2023 ieee","author":"Ruan","year":"2022","journal-title":"CVPR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530757"},{"key":"ref69","article-title":"Mo\u00fbsai: Text-to-music generation with long-context latent diffusion","author":"Schneider","year":"2023"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00847"},{"key":"ref71","article-title":"Make-a-video: Text-to-video generation without text-video data","author":"Singer","year":"2023","journal-title":"ICLR"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73116-7_26"},{"key":"ref73","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2021","journal-title":"ICLR"},{"key":"ref74","article-title":"Audeo: Audio generation for a silent performance video","author":"Su","year":"2020","journal-title":"NeurIPS"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02589"},{"key":"ref76","article-title":"Any-to-any generation via composable diffusion","author":"Tang","year":"2024","journal-title":"NeurIPS"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01750"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00191"},{"key":"ref79","article-title":"Av-dit: Efficient audio-visual diffusion transformer for joint audio and video generation","author":"Wang","year":"2024"},{"key":"ref80","article-title":"Zero-shot video editing using off-the-shelf image diffusion models","author":"Wang","year":"2023"},{"key":"ref81","article-title":"Frieren: Efficient video-to-audio generation network with rectified flow matching","author":"Wang","year":"2024","journal-title":"NeurIPS"},{"key":"ref82","article-title":"Audit: Audio editing by following instructions with latent diffusion models","author":"Wang","year":"2023","journal-title":"NeurIPS"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19787-1_41"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00701"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618160"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28486"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctt5hjpwg.11"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01406"},{"key":"ref90","article-title":"Audio-synchronized visual animation","author":"Zhang","year":"2024","journal-title":"ECCV"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref92","article-title":"Controlvideo: Training-free controllable text-to-video generation","author":"Zhang","year":"2024","journal-title":"ICLR"}],"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\/11492028.pdf?arnumber=11492028","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:14:56Z","timestamp":1778048096000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492028\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":92,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00709","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}