{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T20:20:58Z","timestamp":1740169258169,"version":"3.37.3"},"reference-count":35,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Johns Hopkins Institute for Assured Autonomy"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2021]]},"DOI":"10.1109\/access.2021.3115082","type":"journal-article","created":{"date-parts":[[2021,9,23]],"date-time":"2021-09-23T22:01:13Z","timestamp":1632434473000},"page":"131574-131582","source":"Crossref","is-referenced-by-count":1,"title":["Object Permanence Through Audio-Visual Representations"],"prefix":"10.1109","volume":"9","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9953-7347","authenticated-orcid":false,"given":"Fanjun","family":"Bu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6838-3701","authenticated-orcid":false,"given":"Chien-Ming","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"article-title":"Dataset: Audio-visual representations of object drops","year":"2020","author":"bu","key":"ref33"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.23919\/EUSIPCO.2018.8553182"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.33682\/xb0q-a335"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2902489"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.proeng.2010.11.050"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA40945.2020.9197434"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.110"},{"key":"ref12","first-page":"1525","article-title":"Motion planning with worker’s trajectory prediction for assembly task partner robot","author":"tanaka","year":"2012","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1177\/0278364920917446"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2018.00196"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2013.6696982"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ROBIO.2010.5723394"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/IROS.2011.6095044"},{"key":"ref18","article-title":"Bounce and learn: Modeling scene dynamics with real-world bounces","author":"purushwalkam","year":"2019","journal-title":"arXiv 1904 06827"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00881"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-32192-9_8"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TSMCB.2004.823327"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2953020"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2007.4354063"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2015.7346157"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2057890"},{"key":"ref5","first-page":"928","article-title":"Coupling perception and simulation: Steps towards conversational robotics","author":"mavridis","year":"2003","journal-title":"Proc IEEE\/RSJ Int Conf Intell Robots Syst (IROS)"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2018.8761015"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/DEVLRN.2016.7846812"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1177\/0278364907087172"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00240"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1037\/11494-000"},{"key":"ref20","first-page":"892","article-title":"SoundNet: Learning sound representations from unlabeled video","volume":"29","author":"aytar","year":"2016","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_48"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01216-8_16"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/RO-MAN46459.2019.8956321"},{"key":"ref25","first-page":"10045","article-title":"AVOT: Audio-visual object tracking of multiple objects for robotics","author":"wilson","year":"2020","journal-title":"Proc IEEE Int Conf Robot Autom (ICRA)"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/9312710\/09547333.pdf?arnumber=9547333","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,12,17]],"date-time":"2021-12-17T19:55:43Z","timestamp":1639770943000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9547333\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/access.2021.3115082","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2021]]}}}