{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,7]],"date-time":"2026-11-07T18:38:56Z","timestamp":1794076736814,"version":"4.8.0"},"reference-count":48,"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\/iros58592.2024.10802636","type":"proceedings-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:17:39Z","timestamp":1735154259000},"page":"8595-8602","source":"Crossref","is-referenced-by-count":7,"title":["Sim2Real Transfer for Audio-Visual Navigation with Frequency-Adaptive Acoustic Field Prediction"],"prefix":"10.1109","author":[{"given":"Changan","family":"Chen","sequence":"first","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jordi","family":"Ramos","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Anshul","family":"Tomar","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Kristen","family":"Grauman","sequence":"additional","affiliation":[{"name":"University of Texas at Austin"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TRO.2016.2624754"},{"key":"ref2","article-title":"Retrospectives on the embodied AI workshop","author":"Deitke","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref6","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"},{"key":"ref7","article-title":"Objectnav revisited: On evaluation of embodied agents navigating to objects","author":"Batra","year":"2020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01832"},{"key":"ref9","article-title":"Learning to set waypoints for audio-visual navigation","author":"Chen","year":"2021","journal-title":"ICLR"},{"key":"ref10","article-title":"Learning to explore using active neural SLAM","author":"Chaplot","year":"2020","journal-title":"ICLR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58539-6_2"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197008"},{"key":"ref13","article-title":"Sim-to-real transfer for vision-and-language navigation","author":"Anderson","year":"2020","journal-title":"CoRL"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2020.3013848"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA48891.2023.10160461"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01526"},{"key":"ref18","article-title":"Soundspaces 2.0: A simulation platform for visual-acoustic learning","author":"Chen","year":"2023","journal-title":"NeurIPS"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1121\/1.4926438"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-012-9365-8"},{"key":"ref21","article-title":"Dd-ppo: Learning near-perfect pointgoal navigators from 2.5 billion frames","author":"Wijmans","year":"2020","journal-title":"ICLR"},{"key":"ref22","article-title":"ThreeDWorld: A platform for interactive multi-modal physical simulation","author":"Gan","year":"2021","journal-title":"NeurIPS Datasets and Benchmarks Track"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1002\/047134608x.w8266"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2017.07.011"},{"key":"ref25","article-title":"Active audition for humanoid","author":"Nakadai","year":"2000","journal-title":"AAAI"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s10846-008-9297-3"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1142\/S0219878906001003"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICHR.2009.5379586"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1177\/0278364914548050"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.3390\/s140609522"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s10514-013-9323-6"},{"key":"ref32","article-title":"Dereverberation for reverberation-robust microphone arrayss","author":"Yoshioka","year":"2013","journal-title":"EUSIPCO"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA46639.2022.9812193"},{"key":"ref34","article-title":"The cone of silence: Speech separation by localization","author":"Jenrungrot","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00945"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00081"},{"key":"ref37","article-title":"AI2-THOR: An Interactive 3D Environment for Visual AI","author":"Kolve","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LARS-SBR-WRE48964.2019.00060"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/21.179842"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3004555"},{"key":"ref42","article-title":"The replica dataset: A digital replica of indoor spaces","author":"Straub","year":"2019"},{"key":"ref43","article-title":"Catch me if you hear me: Audio-visual navigation in complex unmapped environments with moving sounds","author":"Younes","year":"2021","journal-title":"RAL"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/2980179.2982431"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1137\/S0036144598347059"},{"key":"ref47","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2015","journal-title":"ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/2041-210X.14196"}],"event":{"name":"2024 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","location":"Abu Dhabi, United Arab Emirates","start":{"date-parts":[[2024,10,14]]},"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\/10802636.pdf?arnumber=10802636","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,26]],"date-time":"2024-12-26T07:01:42Z","timestamp":1735196502000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10802636\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,14]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/iros58592.2024.10802636","relation":{},"subject":[],"published":{"date-parts":[[2024,10,14]]}}}