{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,18]],"date-time":"2025-12-18T14:20:52Z","timestamp":1766067652359,"version":"3.37.3"},"reference-count":77,"publisher":"IEEE","license":[{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,10,23]],"date-time":"2022-10-23T00:00:00Z","timestamp":1666483200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/100000183","name":"Army Research Office (DURIP)","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000183","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100000001","name":"National Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100000001","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022,10,23]]},"DOI":"10.1109\/iros47612.2022.9981549","type":"proceedings-article","created":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:38:15Z","timestamp":1672083495000},"page":"9239-9246","source":"Crossref","is-referenced-by-count":3,"title":["Audio-Visual Depth and Material Estimation for Robot Navigation"],"prefix":"10.1109","author":[{"given":"Justin","family":"Wilson","sequence":"first","affiliation":[{"name":"University of North Carolina at Chapel Hill,Department of Computer Science,United States"}]},{"given":"Nicholas","family":"Rewkowski","sequence":"additional","affiliation":[{"name":"University of Maryland at College Park,Department of Computer Science,United States"}]},{"given":"Ming C.","family":"Lin","sequence":"additional","affiliation":[{"name":"University of Maryland at College Park,Department of Computer Science,United States"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Temporal convolutional networks for action segmentation and detection","volume":"abs\/1611.05267","author":"Lea","year":"2016","journal-title":"CoRR"},{"key":"ref2","article-title":"SemanticPaint: A Framework for the Interactive Segmentation of 3D Scenes","author":"Golodetz","year":"2015","journal-title":"Department of Engineering Science, University of Oxford, Tech. Rep. TVG-2015\u20131"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.40"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.28"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298801"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.261"},{"key":"ref7","article-title":"The replica dataset: A digital replica of indoor spaces","volume":"abs\/1906.05797","author":"Straub","year":"2019","journal-title":"ArXiv"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/2185520.2185596"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201319"},{"key":"ref10","article-title":"Stereodrnet: Dilated residual stereo net","volume":"abs\/l904.02251","author":"Chabra","year":"2019","journal-title":"CoRR"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.141"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2421636.2421637"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2017.2666150"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2020.2973058"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3432195"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01267-0_34"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS40897.2019.8968118"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197528"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2015.2391858"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2016.2518421"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1145\/1015706.1015710"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/1179352.1141983"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964933"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IoTDI.2018.00031"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1121\/1.5133944"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00694"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00076"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3210240.3210325"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00817"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/2733373.2806390"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2655045"},{"key":"ref33","article-title":"Bat-g net: Bat-inspired high-resolution 3d image reconstruction using ultrasonic echoes","author":"Hwang","year":"2019","journal-title":"NeurIPS"},{"issue":"01","key":"ref34","article-title":"Sound classification in hearing aids inspired by auditory scene analysis","volume":"18","author":"Michael","year":"2005","journal-title":"EURASIP Journal on Advances in Signal Processing"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-8655(03)00147-8"},{"volume-title":"Physical audio signal processing","year":"2020","author":"Smith","key":"ref36"},{"volume-title":"Multimodal residual learning for visual qa","year":"2016","author":"Kim","key":"ref37"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6320"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i05.6294"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2622271"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351010"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref44","first-page":"535","article-title":"Algorithms for non-negative matrix factorization","volume-title":"Proceedings of the 13th International Conference on Neural Information Processing Systems, ser. NIPSOO","author":"Lee"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298939"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/2508363.2508369"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00375"},{"key":"ref48","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00890","article-title":"Where is my mirror?","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Yang","year":"2019"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130894"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3012001"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/1476589.1476686"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2723883"},{"volume-title":"What is ultrasound motion detection?","key":"ref53"},{"volume-title":"How ultrasound sensing makes nest displays more accessible","year":"2019","author":"Udall","key":"ref54"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA.2011.5979561"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2016.7759617"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.15607\/RSS.2012.VIII.035"},{"volume-title":"Spectrogram, cepstrum and melfrequency analysis","year":"2011","author":"Prahallad","key":"ref58"},{"volume-title":"Architectural Acoustics","year":"1988","author":"Egan","key":"ref59"},{"volume-title":"Architectural Acoustics","year":"2014","author":"Long","key":"ref60"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1016\/b978-0-12-396487-8.00012-4"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CISP.2008.415"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1121\/1.1907816"},{"key":"ref64","article-title":"Comparison of time-frequency representations for environmental sound classification using convolutional neural networks","volume":"abs\/1706.07156","author":"Huzaifah","year":"2017","journal-title":"CoRR"},{"key":"ref65","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-21945-5","volume-title":"Fundamentals of Music Processing: Audio, Analysis, Algorithms, Applications","author":"MIler","year":"2015"},{"key":"ref66","article-title":"Very deep convolutional networks for large-scale image recognition","volume":"abs\/1409.1556","author":"Simonyan","year":"2015","journal-title":"CoRR"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.202"},{"volume-title":"TensorFlow: Large-scale machine learning on heterogeneous systems","year":"2015","author":"Abadi","key":"ref68"},{"volume-title":"Keras","year":"2015","author":"Chollet","key":"ref69"},{"key":"ref70","article-title":"Adam: A method for stochastic optimization","volume":"abs\/1412.6980","author":"Kingma","year":"2015","journal-title":"CoRR"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-7908-2604-3_16"},{"key":"ref73","article-title":"Soundnet: Learning sound representations from unlabeled video","author":"Aytar","year":"2016","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref74","article-title":"A very simple way to simulate the timbre of flutter echoes in spatial audio","volume-title":"EAA Spatial Audio Signal Processing Symposium","author":"Halmrast","year":"2019"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2013.15"},{"volume-title":"Agisoft metashape standard","year":"2020","key":"ref76"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853678"}],"event":{"name":"2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)","start":{"date-parts":[[2022,10,23]]},"location":"Kyoto, Japan","end":{"date-parts":[[2022,10,27]]}},"container-title":["2022 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9981026\/9981028\/09981549.pdf?arnumber=9981549","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T05:30:58Z","timestamp":1706765458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9981549\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,10,23]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/iros47612.2022.9981549","relation":{},"subject":[],"published":{"date-parts":[[2022,10,23]]}}}