{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T20:35:39Z","timestamp":1730234139166,"version":"3.28.0"},"reference-count":10,"publisher":"IEEE","license":[{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,6]],"date-time":"2024-01-06T00:00:00Z","timestamp":1704499200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024,1,6]]},"DOI":"10.1109\/icce59016.2024.10444380","type":"proceedings-article","created":{"date-parts":[[2024,2,28]],"date-time":"2024-02-28T18:47:20Z","timestamp":1709146040000},"page":"1-2","source":"Crossref","is-referenced-by-count":0,"title":["Multimodal active speaker detection using cross-attention and contextual information"],"prefix":"10.1109","author":[{"given":"Bogdan","family":"Mocanu","sequence":"first","affiliation":[{"name":"Institut Polytechnique de Paris,Télécom SudParis, Laboratoire SAMOVAR,Evry,France"}]},{"given":"Ruxandra","family":"Tapu","sequence":"additional","affiliation":[{"name":"Institut Polytechnique de Paris,Télécom SudParis, Laboratoire SAMOVAR,Evry,France"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9413776"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2889052"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413725"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2000.871073"},{"key":"ref6","article-title":"Facesync: A linear operator for measuring synchronization of video facial images and audio tracks","volume":"13","author":"Slaney","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref7","first-page":"3927","article-title":"Is someone speaking? exploring long-term temporal features for audio-visual active speaker detection","author":"Tao","year":"2021","journal-title":"ACM ICM"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00123"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02196"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"}],"event":{"name":"2024 IEEE International Conference on Consumer Electronics (ICCE)","start":{"date-parts":[[2024,1,6]]},"location":"Las Vegas, NV, USA","end":{"date-parts":[[2024,1,8]]}},"container-title":["2024 IEEE International Conference on Consumer Electronics (ICCE)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/10444098\/10444131\/10444380.pdf?arnumber=10444380","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,1]],"date-time":"2024-03-01T05:38:11Z","timestamp":1709271491000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10444380\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,6]]},"references-count":10,"URL":"https:\/\/doi.org\/10.1109\/icce59016.2024.10444380","relation":{},"subject":[],"published":{"date-parts":[[2024,1,6]]}}}