{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,13]],"date-time":"2026-10-13T17:35:37Z","timestamp":1791912937208,"version":"4.3.4"},"reference-count":22,"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\/icra40945.2020.9196934","type":"proceedings-article","created":{"date-parts":[[2020,9,15]],"date-time":"2020-09-15T17:25:46Z","timestamp":1600190746000},"page":"1581-1587","source":"Crossref","is-referenced-by-count":52,"title":["BatVision: Learning to See 3D Spatial Layout with Two Ears"],"prefix":"10.1109","author":[{"given":"Jesper Haahr","family":"Christensen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sascha","family":"Hornauer","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Stella X.","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00458"},{"key":"ref11","article-title":"Audio-visual model distillation using acoustic images","author":"prez","year":"2019"},{"key":"ref12","doi-asserted-by":"crossref","first-page":"112:1","DOI":"10.1145\/3197517.3201357","article-title":"Looking to listen at the cocktail party: A speaker-independent audio-visual model for speech separation","volume":"37","author":"ephrat","year":"2018","journal-title":"ACM Trans Graph"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2015.95"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ISSPIT.2006.270883"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00694"},{"key":"ref18","first-page":"892","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"aytar","year":"2016","journal-title":"Advances in Neural IInformation Processing Systems"},{"key":"ref19","first-page":"234","article-title":"U-net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Med Image Comput Comput Assist Interv"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TBME.2015.2393371"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1121\/1.4940668"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0054076"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pcbi.1006406"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1121\/1.428283"},{"key":"ref7","article-title":"3d sparse imaging in biosonar scene analysis","author":"fontaine","year":"2009"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1121\/1.1377294"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1177\/0278364910380474"},{"key":"ref9","article-title":"Audio-visual event localization in the wild","author":"tian","year":"2019","journal-title":"Proc CVPR Workshop Sight and Sound"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"ref21","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2014","journal-title":"International Conference on Learning Representations"}],"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\/09196934.pdf?arnumber=9196934","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:19:13Z","timestamp":1656361153000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9196934\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icra40945.2020.9196934","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}