{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:22:24Z","timestamp":1777890144863,"version":"3.51.4"},"reference-count":53,"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\/iccv51701.2025.01137","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12232-12241","source":"Crossref","is-referenced-by-count":0,"title":["How Would it Sound? Material-Controlled Multimodal Acoustic Profile Generation for Indoor Scenes"],"prefix":"10.1109","author":[{"given":"Mahnoor Fatima","family":"Saad","sequence":"first","affiliation":[{"name":"University of Utah"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziad","family":"Al-Halah","sequence":"additional","affiliation":[{"name":"University of Utah"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1121\/1.382599"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2011.76"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982431"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref5","article-title":"SoundSpaces: AudioVisual Navigaton in 3D Environments","volume-title":"Proceedings of the European Conference on Computer Vision (ECCV)","author":"Chen","year":"2020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01829"},{"key":"ref8","article-title":"SoundSpaces 2.0: A Simulation Platform for Visual-Acoustic Learning","author":"Chen","year":"2022","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00620"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/IROS58592.2024.10802636"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00725"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414399"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1121\/1.3021297"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2017.2744799"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/PROC.1978.10837"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/VR.2019.8798247"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1406.3269"},{"key":"ref19","article-title":"Deep neural networks for cross-modal estimations of acoustic reverberation characteristics from two-dimensional images","author":"Kon","year":"2018","journal-title":"Audio Engineering Society Convention 144. Audio Engineering Society"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1250\/ast.41.675"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201391"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1629"},{"key":"ref23","author":"Liang","year":"2023","journal-title":"Neural Acoustic Context Field: Rendering Realistic Room Impulse Response With Neural Fields"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-79214-4"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0229"},{"key":"ref26","article-title":"Few-Shot Audio-Visual Learning of Environment Acoustics","volume-title":"Conference on Neural Information Processing Systems (NeurIPS)","author":"Majumder","year":"2022"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.apacoust.2011.05.012"},{"key":"ref28","article-title":"AV-SAM: Segment Anything Model Meets Audio-Visual Localization and Segmentation","author":"Mo","year":"2023","journal-title":"arXiv preprint"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2009.28"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/VR58804.2024.00048"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-230"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU51503.2021.9688304"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747846"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10094770"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02565"},{"key":"ref36","article-title":"Reproducing real world acoustics in virtual reality using spherical cameras","volume-title":"International Conference on Immersive and Interactive Audio. Audio Engineering Society","author":"Remaggi","year":"2019"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.2943779"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2666150"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2666150"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00035"},{"key":"ref42","article-title":"Self-Supervised Visual Acoustic Matching","volume":"36","author":"Somayazulu","year":"2024","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref43","article-title":"INRAS: Implicit Neural Representation for Audio Scenes","author":"Su","year":"2022","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref44","article-title":"Habitat 2.0: Training Home Assistants to Rearrange their Habitat","author":"Szot","year":"2021","journal-title":"Advances in Neural Information Processing Systems (NeurIPS)"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2973058"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530731"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1121\/1.2164987"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1201\/9781482266016"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1121\/1.398336"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.3390\/app11031150"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16403"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01710"}],"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\/11444579.pdf?arnumber=11444579","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:29:47Z","timestamp":1777613387000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11444579\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01137","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}