{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T10:14:23Z","timestamp":1740132863922,"version":"3.37.3"},"reference-count":51,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tmm.2022.3229975","type":"journal-article","created":{"date-parts":[[2022,12,16]],"date-time":"2022-12-16T18:41:11Z","timestamp":1671216071000},"page":"7825-7836","source":"Crossref","is-referenced-by-count":2,"title":["Cross Modal Video Representations for Weakly Supervised Active Speaker Localization"],"prefix":"10.1109","volume":"25","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1697-3897","authenticated-orcid":false,"given":"Rahul","family":"Sharma","sequence":"first","affiliation":[{"name":"Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2845-1079","authenticated-orcid":false,"given":"Krishna","family":"Somandepalli","sequence":"additional","affiliation":[{"name":"USC, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1052-6204","authenticated-orcid":false,"given":"Shrikanth","family":"Narayanan","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, University of Southern California, Los Angeles, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3242969.3243026"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/2993148.2993172"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2020.102437"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413581"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00357"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9053900"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477688"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00097"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00238"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-30642-7_5"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_39"},{"key":"ref48","first-page":"1","article-title":"Multi-task learning for audio-visual active speaker detection","author":"zhang","year":"0","journal-title":"Proc ActivityNet Large-Scale Activity Recognit Challenge"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952261"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.324"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9052974"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682847"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19836-6_8"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_35"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_39"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803248"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.brainres.2012.05.015"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.plrev.2010.04.006"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.73"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01061"},{"key":"ref35","first-page":"772","article-title":"Learning joint statistical models for audio-visual fusion and segregation","author":"fisher iii","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2007.383344"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01032"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00182"},{"key":"ref31","first-page":"265","article-title":"Maas: Multi-modal assignation for active speaker detection","author":"le\u00f3n-alc\u00e1zar","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01248"},{"key":"ref33","first-page":"814","article-title":"Audio vision: Using audio-visual synchrony to locate sounds","volume":"12","author":"hershey","year":"2000","journal-title":"Advances in neural information processing systems"},{"key":"ref32","first-page":"208","article-title":"Self-supervised learning of audio-visual objects from video","author":"afouras","year":"0","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.neubiorev.2011.04.015"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2020.3047978"},{"key":"ref39","first-page":"190","article-title":"Training and analysing deep recurrent neural networks","author":"hermans","year":"0","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.5244\/C.20.92"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00230"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58523-5_13"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.311"},{"key":"ref22","first-page":"9834","article-title":"C-MIDN: Coupled multiple instance detection network with segmentation guidance for weakly supervised object detection","author":"gao","year":"0","journal-title":"Proc IEEE\/CVF Int Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.326"},{"key":"ref28","first-page":"1","article-title":"Multi-task learning for audio-visual active speaker detection","author":"zhang","year":"0","journal-title":"Proc ActivityNet Large-Scale Activity Recognit Challenge"},{"key":"ref27","first-page":"87","article-title":"Who's speaking? audio-supervised classification of active speakers in video","author":"chakravarty","year":"0","journal-title":"Proc Int Conf Multimodal Interact"},{"article-title":"Naver at activitynet challenge 2019–task B active speaker detection (AVA)","year":"2019","author":"chung","key":"ref29"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6046\/10016790\/09991097.pdf?arnumber=9991097","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,13]],"date-time":"2023-12-13T19:46:58Z","timestamp":1702496818000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9991097\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":51,"URL":"https:\/\/doi.org\/10.1109\/tmm.2022.3229975","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"type":"print","value":"1520-9210"},{"type":"electronic","value":"1941-0077"}],"subject":[],"published":{"date-parts":[[2023]]}}}