{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:28:35Z","timestamp":1766068115639,"version":"3.32.0"},"reference-count":47,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,14]],"date-time":"2024-10-14T00:00:00Z","timestamp":1728864000000},"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":[[2024,10,14]]},"DOI":"10.1109\/iros58592.2024.10802429","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"557-564","source":"Crossref","is-referenced-by-count":1,"title":["Disentangled Acoustic Fields For Multimodal Physical Scene Understanding"],"prefix":"10.1109","author":[{"given":"Jie","family":"Yin","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Andrew","family":"Luo","sequence":"additional","affiliation":[{"name":"Carnegie Mellon University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yilun","family":"Du","sequence":"additional","affiliation":[{"name":"Massachusetts Institute of Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Anoop","family":"Cherian","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories(MERL)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tim K.","family":"Marks","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories(MERL)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jonathan","family":"Le Roux","sequence":"additional","affiliation":[{"name":"Mitsubishi Electric Research Laboratories(MERL)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuang","family":"Gan","sequence":"additional","affiliation":[{"name":"MIT-IBM AI Lab and UMass Amherst"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Learning neural acoustic fields","year":"2022","author":"Luo","key":"ref1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01593"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00025"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01852"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"ref6","article-title":"Scene representation networks: Continuous 3d-structure-aware neural scene representations","volume":"32","author":"Sitzmann","year":"2019","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1111\/cgf.14505"},{"key":"ref8","first-page":"8320","article-title":"Learning signal-agnostic manifolds of neural fields","volume":"34","author":"Du","year":"2021","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2021.3138527"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610070"},{"key":"ref11","first-page":"2536","article-title":"Inverting audio-visual simulation for shape and material perception","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops","author":"Zhang"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1083-5"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11633-021-1293-0"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_3"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_38"},{"article-title":"Structure from silence: Learning scene structure from ambient sound","year":"2021","author":"Chen","key":"ref19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_44"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.264"},{"key":"ref24","first-page":"3325","article-title":"Audeo: Audio generation for a silent performance video","volume":"33","author":"Su","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126723"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref30","first-page":"103","article-title":"Audio-visual embodied navigation","volume":"97","author":"Chen","year":"2019","journal-title":"environment"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"article-title":"Learning to set waypoints for audio-visual navigation","year":"2020","author":"Chen","key":"ref33"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01027"},{"article-title":"Three-dworld: A platform for interactive multi-modal physical simulation","year":"2020","author":"Gan","key":"ref35"},{"year":"2018","key":"ref36","article-title":"Google resonance audio"},{"article-title":"Auto-encoding variational bayes","year":"2013","author":"Kingma","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TSSC.1968.300136"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01034"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00152"},{"key":"ref42","article-title":"Dcase 2020 task 3: A single stage fully convolutional neural network for sound source localization and detection","author":"Patel","year":"2020","journal-title":"DCASE2020 Challenge"},{"key":"ref43","first-page":"4160","article-title":"Sounddet: Polyphonic moving sound event detection and localization from raw waveform","volume-title":"International Conference on Machine Learning","author":"He"},{"article-title":"On evaluation of embodied navigation agents","year":"2018","author":"Anderson","key":"ref44"},{"key":"ref45","first-page":"15 084","article-title":"Decision transformer: Reinforcement learning via sequence modeling","volume":"34","author":"Chen","year":"2021","journal-title":"Advances in neural information processing systems"},{"article-title":"Proximal policy optimization algorithms","year":"2017","author":"Schulman","key":"ref46"},{"key":"ref47","first-page":"4247","article-title":"Object goal navigation using goal-oriented semantic exploration","volume":"33","author":"Chaplot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2024,10,14]]},"location":"Abu Dhabi, United Arab Emirates","end":{"date-parts":[[2024,10,18]]}},"container-title":["2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/10801246\/10801290\/10802429.pdf?arnumber=10802429","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:22:33Z","timestamp":1735197753000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802429\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":47,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802429","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}