{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:35:51Z","timestamp":1774366551963,"version":"3.50.1"},"reference-count":22,"publisher":"IEEE","license":[{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2020,5,1]],"date-time":"2020-05-01T00:00:00Z","timestamp":1588291200000},"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":[[2020,5]]},"DOI":"10.1109\/icassp40776.2020.9052916","type":"proceedings-article","created":{"date-parts":[[2020,4,9]],"date-time":"2020-04-09T16:21:13Z","timestamp":1586449273000},"page":"4482-4486","source":"Crossref","is-referenced-by-count":31,"title":["Multitask Learning and Multistage Fusion for Dimensional Audiovisual Emotion Recognition"],"prefix":"10.1109","author":[{"given":"Bagus Tris","family":"Atmaja","sequence":"first","affiliation":[]},{"given":"Masato","family":"Akagi","sequence":"additional","affiliation":[]}],"member":"263","reference":[{"key":"ref10","first-page":"65","article-title":"Multi-modal Multicultural Dimensional Continues Emotion Recognition in Dyadic Interactions","author":"zhao","year":"2018"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/APSIPAASC47483.2019.9023098"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2944808"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/2502081.2502224"},{"key":"ref15","first-page":"3370","article-title":"openXBOW - Introducing the Passau Open-Source Crossmodal Bag-of-Words Toolkit","volume":"18","author":"schmitt","year":"0","journal-title":"The Journal of Machine Learning Research"},{"key":"ref16","doi-asserted-by":"crossref","first-page":"3512","DOI":"10.21437\/Interspeech.2017-434","article-title":"Snore sound classification using image-based deep spectrum features","author":"amiriparian","year":"2017","journal-title":"InterSpeech"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/FG.2018.00019"},{"key":"ref18","first-page":"2014","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"0"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref4","doi-asserted-by":"crossref","first-page":"1103","DOI":"10.21437\/Interspeech.2017-1494","article-title":"Jointly predicting arousal, valence and dominance with multi-task learning","author":"parthasarathy","year":"2017","journal-title":"InterSpeech"},{"key":"ref3","article-title":"AVEC 2019 workshop and challenge: State-of-mind, depression with AI, and crosscultural affect recognition","author":"ringeval","year":"2019","journal-title":"Proc of the 2019 on Audio\/Visual Emotion Challenge and Workshop"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3133944.3133949"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-9280.2007.02024.x"},{"key":"ref1","first-page":"1161","article-title":"Three dimensions of emotion","volume":"9","author":"russel","year":"0","journal-title":"J Pers Soc Psychol"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2018.07.041"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.2307\/2532051"},{"key":"ref22","first-page":"2015","article-title":"Keras","author":"chollet","year":"0"},{"key":"ref21","first-page":"2825","article-title":"Scikit-learn: Machine learning in Python","volume":"12","author":"pedregosa","year":"0","journal-title":"Journal of Machine Learning Research"}],"event":{"name":"ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","location":"Barcelona, Spain","start":{"date-parts":[[2020,5,4]]},"end":{"date-parts":[[2020,5,8]]}},"container-title":["ICASSP 2020 - 2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/9040208\/9052899\/09052916.pdf?arnumber=9052916","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,6,27]],"date-time":"2022-06-27T20:11:49Z","timestamp":1656360709000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9052916\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,5]]},"references-count":22,"URL":"https:\/\/doi.org\/10.1109\/icassp40776.2020.9052916","relation":{},"subject":[],"published":{"date-parts":[[2020,5]]}}}