{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T16:08:38Z","timestamp":1726762118441},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"6","license":[{"start":{"date-parts":[[2023,6,1]],"date-time":"2023-06-01T00:00:00Z","timestamp":1685577600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,6,1]]},"DOI":"10.1109\/tpami.2020.3025105","type":"journal-article","created":{"date-parts":[[2020,9,18]],"date-time":"2020-09-18T20:37:13Z","timestamp":1600461433000},"page":"6783-6793","source":"Crossref","is-referenced-by-count":8,"title":["EgoCom: A Multi-Person Multi-Modal Egocentric Communications Dataset"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"http:\/\/orcid.org\/0000-0002-2423-1300","authenticated-orcid":false,"given":"Curtis G.","family":"Northcutt","sequence":"first","affiliation":[{"name":"Department of Electrical and Computer Science, Massachusetts Institute of Technology, Cambridge, MA, USA"}]},{"ORCID":"http:\/\/orcid.org\/0000-0002-9711-4447","authenticated-orcid":false,"given":"Shengxin","family":"Zha","sequence":"additional","affiliation":[{"name":"Facebook AI, Menlo Park, CA, USA"}]},{"given":"Steven","family":"Lovegrove","sequence":"additional","affiliation":[{"name":"Facebook Reality Labs (Oculus Research), Redmond, WA, USA"}]},{"given":"Richard","family":"Newcombe","sequence":"additional","affiliation":[{"name":"Facebook Reality Labs (Oculus Research), Redmond, WA, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2614300"},{"key":"ref12","first-page":"619","article-title":"In the eye of beholder: Joint learning of gaze and actions in first person video","author":"li","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.106"},{"key":"ref14","first-page":"iv-4072","article-title":"An overview of automatic speaker recognition technology","author":"reynolds","year":"2002","journal-title":"Proc IEEE Int Conf Acoust Speech Signal Process"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462105"},{"key":"ref11","first-page":"753","article-title":"Scaling egocentric vision: The epic-kitchens dataset","author":"damen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/2556288.2557092"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref16","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/THMS.2016.2623480"},{"key":"ref18","article-title":"The MNIST database of handwritten digits","author":"lecun","year":"1998"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639034"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/321796.321811"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00675"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390177"},{"key":"ref48","article-title":"Advances in pre-training distributed word representations","author":"mikolov","year":"2018","journal-title":"Proc Int Conf Lang Resour Eval"},{"key":"ref47","first-page":"2616","article-title":"Voxceleb: A large-scale speaker identification dataset","author":"nagrani","year":"2017","journal-title":"Proc 18th Annu Conf Int Speech Commun Assoc"},{"key":"ref42","first-page":"631","article-title":"Audio-visual scene analysis with self-supervised multisensory features","author":"owens","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995444"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298625"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ASRU.2009.5372931"},{"key":"ref49","first-page":"2825","article-title":"Scikit-learn: Machine learning in python","volume":"12","author":"pedregosa","year":"2011","journal-title":"J Mach Learn Res"},{"key":"ref8","first-page":"35","article-title":"Learning to separate object sounds by watching unlabeled video","author":"gao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3197517.3201357"},{"key":"ref9","first-page":"435","article-title":"Objects that sound","author":"arandjelovic","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1196\/annals.1382.016"},{"key":"ref3","article-title":"Toward natural turn-taking in a virtual human negotiation agent","author":"devault","year":"2015","journal-title":"Proc AAAI Spring Symp Turn-Taking Coordination Hum -Mach Interact"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2009.2031510"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1162\/0899766054322964"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.350"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2798607"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00812"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref36","first-page":"860","article-title":"Latent mixture of discriminative experts for multimodal prediction modeling","author":"ozkan","year":"2010","journal-title":"Proc 23rd Int Conf Comput Linguistics"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2013.438"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6247805"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01113"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.288"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462227"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/S0021-9924(97)00085-3"},{"key":"ref39","first-page":"1346","article-title":"Discovering important people and objects for egocentric video summarization","author":"lee","year":"2012","journal-title":"Proc IEEE Conf Comput Vis Pattern Recognit"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-85483-8_18"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00633"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298698"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.367"},{"key":"ref25","article-title":"AVA-ActiveSpeaker: An audio-visual dataset for active speaker detection","author":"roth","year":"2019"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1561\/1500000074"},{"key":"ref22","article-title":"The kinetics human action video dataset","author":"kay","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4613-8997-2_14"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10120646\/09200754.pdf?arnumber=9200754","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,12]],"date-time":"2023-06-12T18:10:58Z","timestamp":1686593458000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9200754\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,6,1]]},"references-count":52,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2020.3025105","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,6,1]]}}}