{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,4]],"date-time":"2025-11-04T11:12:00Z","timestamp":1762254720345,"version":"3.28.0"},"reference-count":35,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T00:00:00Z","timestamp":1693180800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000038","name":"Natural Sciences and Engineering Research Council of Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100000038","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100020487","name":"Nature","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100020487","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100013020","name":"Compute Canada","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100013020","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/100011047","name":"AGE-WELL","doi-asserted-by":"publisher","id":[{"id":"10.13039\/100011047","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,8,28]]},"DOI":"10.1109\/ro-man57019.2023.10309338","type":"proceedings-article","created":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T14:07:48Z","timestamp":1699884468000},"page":"1302-1307","source":"Crossref","is-referenced-by-count":1,"title":["Attempting to Aggregate Perceptual Constructs From Deep Neural Networks for Video and Audio Interaction Representation"],"prefix":"10.1109","author":[{"given":"Marc-Antoine","family":"Maheux","sequence":"first","affiliation":[{"name":"Interdisciplinary Institute for Technological Innovation (3IT), Université de Sherbrooke, 3000 Bd de l’Université,Department of Electrical Engineering and Computer Engineering,Sherbrooke,Canada"}]},{"given":"Guillaume","family":"Auclair","sequence":"additional","affiliation":[{"name":"Interdisciplinary Institute for Technological Innovation (3IT), Université de Sherbrooke, 3000 Bd de l’Université,Department of Electrical Engineering and Computer Engineering,Sherbrooke,Canada"}]},{"given":"Philippe","family":"Warren","sequence":"additional","affiliation":[{"name":"Interdisciplinary Institute for Technological Innovation (3IT), Université de Sherbrooke, 3000 Bd de l’Université,Department of Electrical Engineering and Computer Engineering,Sherbrooke,Canada"}]},{"given":"Dominic","family":"L\u00e9tourneau","sequence":"additional","affiliation":[{"name":"Interdisciplinary Institute for Technological Innovation (3IT), Université de Sherbrooke, 3000 Bd de l’Université,Department of Electrical Engineering and Computer Engineering,Sherbrooke,Canada"}]},{"given":"Fran\u00e7ois","family":"Michaud","sequence":"additional","affiliation":[{"name":"Interdisciplinary Institute for Technological Innovation (3IT), Université de Sherbrooke, 3000 Bd de l’Université,Department of Electrical Engineering and Computer Engineering,Sherbrooke,Canada"}]}],"member":"263","reference":[{"key":"ref35","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der maaten","year":"2008","journal-title":"J Machine Learning Research"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2013.2270402"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/0377-0427(87)90125-7"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/1922649.1922653"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2966819"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2016.00524"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.2307\/2346830"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/MRA.2022.3210587"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2018.2822810"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2019.2924623"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11370-021-00394-3"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/01691864.2019.1599728"},{"key":"ref17","article-title":"YOLOv4: Optimal speed and accuracy of object detection","author":"bochkovskiy","year":"2020","journal-title":"arXiv 2004 10934"},{"key":"ref16","first-page":"21","article-title":"SSD: Single shot multibox detector","author":"liu","year":"2016","journal-title":"Proc Euro Conf Computer Vision"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"ref24","first-page":"472","article-title":"Simple baselines for human pose estimation and tracking","author":"xiao","year":"2018","journal-title":"Proc Euro Conf Computer Vision"},{"key":"ref23","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Euro Conf Computer Vision"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00020"},{"key":"ref25","article-title":"OpenFace: A general-purpose face recognition library with mobile applications","author":"amos","year":"2016","journal-title":"CMU School of Computer Science Technical Report CMU-CS"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2017.06.121"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01283"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/HRI53351.2022.9889346"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.robot.2019.01.002"},{"key":"ref27","article-title":"Labeled faces in the wild: Updates and new reporting procedures","author":"huang","year":"2014","journal-title":"Tech Rep UM-CS-2014-003 University of Massachusetts Amherst"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3133208"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICAL.2009.5262649"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/s20071928"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.4028\/www.scientific.net\/AMM.55-57.1017"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3005338.3005342"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2020.2983406"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/2508037.2508045"},{"key":"ref5","first-page":"89","article-title":"Scene interpretation for self-aware cognitive robots","volume":"ss 14 6","author":"ozturk","year":"2014","journal-title":"AAAI Spring Symposium - Technical Report"}],"event":{"name":"2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)","start":{"date-parts":[[2023,8,28]]},"location":"Busan, Korea, Republic of","end":{"date-parts":[[2023,8,31]]}},"container-title":["2023 32nd IEEE International Conference on Robot and Human Interactive Communication (RO-MAN)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10309296\/10309265\/10309338.pdf?arnumber=10309338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,29]],"date-time":"2023-11-29T10:56:10Z","timestamp":1701255370000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10309338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,8,28]]},"references-count":35,"URL":"https:\/\/doi.org\/10.1109\/ro-man57019.2023.10309338","relation":{},"subject":[],"published":{"date-parts":[[2023,8,28]]}}}