{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:24:03Z","timestamp":1777890243826,"version":"3.51.4"},"reference-count":54,"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\/iccv51701.2025.01477","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"15917-15926","source":"Crossref","is-referenced-by-count":0,"title":["CAFA: A Controllable Automatic Foley Artist"],"prefix":"10.1109","author":[{"given":"Roi","family":"Benita","sequence":"first","affiliation":[{"name":"Technion"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael","family":"Finkelson","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tavi","family":"Halperin","sequence":"additional","affiliation":[{"name":"Lightricks"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gleb","family":"Sterkin","sequence":"additional","affiliation":[{"name":"Lightricks"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yossi","family":"Adi","sequence":"additional","affiliation":[{"name":"Hebrew University of Jerusalem"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.4324\/9780203766880"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053174"},{"key":"ref3","article-title":"Contrastive localized languageimage pre-training","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.3009820"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.01749"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01749"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52734.2025.02691"},{"key":"ref8","article-title":"Fast timing-conditioned latent audio diffusion","volume-title":"Forty-first International Conference on Machine Learning","author":"Evans"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888461"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612348"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref12","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref13","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/0004-3702(81)90024-2"},{"key":"ref15","first-page":"13916","article-title":"Make-an-audio: Text-to-audio generation with prompt-enhanced diffusion models","volume-title":"International Conference on Machine Learning","author":"Huang"},{"key":"ref16","article-title":"Tangoflux: Super fast and faithful text to audio generation with flow matching and clap-ranked preference optimization","author":"Hung","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.5244\/C.35.336"},{"key":"ref18","article-title":"Sparse in space and time: Audio-visual synchronisation with trainable selectors","author":"Iashin","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448489"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i17.33934"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2019-2219"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3030497"},{"key":"ref23","article-title":"Audiogen: Textually guided audio generation","author":"Kreuk","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1214\/aoms\/1177729694"},{"key":"ref25","article-title":"Audioldm: Text-to-audio generation with latent diffusion models","author":"Liu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2024.3399607"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3213"},{"key":"ref28","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint arXiv"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-025-1562-4"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2121"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681688"},{"key":"ref32","article-title":"Representation learning with contrastive predictive coding","author":"van den Oord","year":"2018","journal-title":"arXiv preprint arXiv"},{"key":"ref33","first-page":"12493","article-title":"Keeping your eye on the ball: Trajectory attention in video transformers","volume":"34","author":"Patrick","year":"2021","journal-title":"Advances in neural information processing systems"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref35","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","author":"Radford"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.52202\/075280-2338"},{"issue":"140","key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref40","article-title":"Progressive distillation for fast sampling of diffusion models","author":"Salimans","year":"2022","journal-title":"arXiv preprint arXiv"},{"key":"ref41","article-title":"Improved techniques for training gans","author":"Salimans","year":"2016","journal-title":"ArXiv"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096023"},{"key":"ref43","article-title":"Denoising diffusion implicit models","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref44","article-title":"Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arXiv preprint arXiv"},{"key":"ref45","article-title":"Temporally aligned audio for video with autoregression","author":"Viertola","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i14.29475"},{"key":"ref47","first-page":"128118","article-title":"Frieren: Efficient video-to-audio generation network with rectified flow matching","volume":"37","author":"Wang","year":"2025","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095969"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00683"},{"key":"ref50","article-title":"Video-to-audio generation with hidden alignment","author":"Xu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3268730"},{"key":"ref52","article-title":"Ipadapter: Text compatible image prompt adapter for text-toimage diffusion models","author":"Ye","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-025-02649-3"}],"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\/11445691.pdf?arnumber=11445691","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:32:36Z","timestamp":1777613556000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445691\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":54,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01477","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}