{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,12]],"date-time":"2026-03-12T14:22:36Z","timestamp":1773325356100,"version":"3.50.1"},"reference-count":38,"publisher":"IEEE","license":[{"start":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T00:00:00Z","timestamp":1694390400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,11]],"date-time":"2023-09-11T00:00:00Z","timestamp":1694390400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2023,9,11]]},"DOI":"10.1109\/secon58729.2023.10287518","type":"proceedings-article","created":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T17:57:08Z","timestamp":1698083828000},"page":"528-536","source":"Crossref","is-referenced-by-count":2,"title":["E-Talk: Accelerating Active Speaker Detection with Audio-Visual Fusion and Edge-Cloud Computing"],"prefix":"10.1109","author":[{"given":"Xiaojing","family":"Yu","sequence":"first","affiliation":[{"name":"University of Science and Technology of China,Department of Computer Science,Anhui,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lan","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Department of Computer Science,Anhui,China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiang-Yang","family":"Li","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China,Department of Computer Science,Anhui,China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3387514.3405874"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_18"},{"key":"ref12","first-page":"119","article-title":"Ekya: Continuous learning of video analytics models on edge compute servers","author":"bhardwaj","year":"2022","journal-title":"7th USENIX Symposium on Networked System Design and Implementation (NSDI)"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1064"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3478095"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_28"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2019.02.010"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00864"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3061800"},{"key":"ref30","article-title":"An introduction to the kalman filter","author":"welch","year":"1995"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2019.00018"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1400"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM42981.2021.9488704"},{"key":"ref32","first-page":"192","article-title":"S3fd: Single shot scale-invariant face detector","author":"zhang","year":"2017","journal-title":"Proceedings of the IEEE International Conference on Computer Vision"},{"key":"ref2","first-page":"1193","article-title":"How to design a three-stage architecture for audio-visual active speaker detection in the wild","author":"k\u00f6p\u00fckl\u00fc","year":"2021","journal-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01029"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2337"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.533"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00238"},{"key":"ref18","first-page":"12 465","article-title":"Active speakers in context","author":"alc\u00e1zar","year":"2020","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-2650"},{"key":"ref23","first-page":"709","article-title":"A survey on speaker recognition with various feature extraction and classification techniques","volume":"3","author":"ramgire","year":"2016","journal-title":"International Research Journal of Engineering and Technology"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1037\/a0027127"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3233\/IDA-2007-11508"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2021.3075336"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01943"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16235"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.04.018"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2009.4959741"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.603"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/INFOCOM48880.2022.9796817"},{"key":"ref7","author":"team","year":"2018","journal-title":"Resolution usage statistics"},{"key":"ref9","first-page":"3531","article-title":"An effective genetic algorithm to improve wireless sensor network lifetime for large-scale surveillance applications","author":"lai","year":"2007","journal-title":"IEEE Congress on Evolutionary Computation"},{"key":"ref4","first-page":"251","article-title":"Out of time: automated lip sync in the wild","author":"chung","year":"2016","journal-title":"ACCV International Workshops Taipei Taiwan November 20-24 2016 Revised Selected Papers Part II 13"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2016.2535357"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475587"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01842"}],"event":{"name":"2023 20th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)","location":"Madrid, Spain","start":{"date-parts":[[2023,9,11]]},"end":{"date-parts":[[2023,9,14]]}},"container-title":["2023 20th Annual IEEE International Conference on Sensing, Communication, and Networking (SECON)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10287388\/10287413\/10287518.pdf?arnumber=10287518","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,13]],"date-time":"2023-11-13T19:04:35Z","timestamp":1699902275000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10287518\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,11]]},"references-count":38,"URL":"https:\/\/doi.org\/10.1109\/secon58729.2023.10287518","relation":{},"subject":[],"published":{"date-parts":[[2023,9,11]]}}}