{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,20]],"date-time":"2026-10-20T16:53:16Z","timestamp":1792515196346,"version":"4.5.0"},"reference-count":45,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icra40945.2020.9197008","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T21:25:46Z","timestamp":1600205146000},"page":"9701-9707","source":"Crossref","is-referenced-by-count":101,"title":["Look, Listen, and Act: Towards Audio-Visual Embodied Navigation"],"prefix":"10.1109","author":[{"given":"Chuang","family":"Gan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yiwei","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiajun","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boqing","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Joshua B.","family":"Tenenbaum","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","article-title":"Ai2-thor: An interactive 3d environment for visual ai","author":"kolve","year":"2017"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.95"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref32","article-title":"The sound of pixels","author":"zhao","year":"2018","journal-title":"ECCV"},{"key":"ref31","article-title":"Learning to separate object sounds by watching unlabeled video","author":"gao","year":"2018","journal-title":"ECCV"},{"key":"ref30","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"ECCV"},{"key":"ref37","author":"van trees","year":"2004","journal-title":"Optimum Array Processing Part IV of Detection Estimation and Modulation Theory"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2018.8461268"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00715"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682467"},{"key":"ref10","article-title":"Visual semantic navigation using scene priors","author":"yang","year":"2019","journal-title":"ICLRE"},{"key":"ref40","article-title":"Efficient encoding and decoding of binaural sound with resonance audio","author":"gorzel","year":"2019","journal-title":"AES"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793565"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793500"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2019.8793493"},{"key":"ref14","article-title":"Semi-parametric topological memory for navigation","author":"savinov","year":"2018","journal-title":"ICLRE"},{"key":"ref15","article-title":"Speaker-follower models for vision-and-language navigation","author":"fried","year":"2018","journal-title":"NeurIPS"},{"key":"ref16","article-title":"Interactive grounded language acquisition and generalization in a 2d world","author":"yu","year":"2018","journal-title":"ICLRE"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v30i1.10364","article-title":"Listen, attend, and walk: Neural mapping of navigational instructions to action sequences","author":"mei","year":"2016","journal-title":"AAAI"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00387"},{"key":"ref19","article-title":"Audio-visual embodied navigation","author":"chen","year":"2019"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2017.7989381"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref3","author":"thrun","year":"2005","journal-title":"Probabilistic Robotics"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2017.XIII.034"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.769"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.329"},{"key":"ref7","article-title":"Learning to navigate in complex environments","author":"mirowski","year":"2017","journal-title":"ICLRE"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0000943"},{"key":"ref9","article-title":"Training agent for first-person shooter game with actor-critic curriculum learning","author":"wu","year":"2017","journal-title":"ICLRE"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/264746a0"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00943"},{"key":"ref45","article-title":"Asynchronous methods for deep reinforcement learning","author":"mnih","year":"2016","journal-title":"ICML"},{"key":"ref22","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher iii","year":"2001","journal-title":"NeurIPS"},{"key":"ref21","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","author":"hershey","year":"2000","journal-title":"NeurIPS"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383344"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D16-1147"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.274"},{"key":"ref44","article-title":"On evaluation of embodied navigation agents","author":"anderson","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-74567-6_19"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2012.2228476"}],"event":{"name":"2020 IEEE International Conference on Robotics and Automation (ICRA)","location":"Paris, France","start":{"date-parts":[[2020,5,31]]},"end":{"date-parts":[[2020,8,31]]}},"container-title":["2020 IEEE International Conference on Robotics and Automation (ICRA)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9187508\/9196508\/09197008.pdf?arnumber=9197008","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,18]],"date-time":"2022-11-18T13:58:19Z","timestamp":1668779899000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9197008\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":45,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9197008","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}