{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T19:06:38Z","timestamp":1772823998347,"version":"3.50.1"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,9,1]],"date-time":"2022-09-01T00:00:00Z","timestamp":1661990400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100004733","name":"University of Macau","doi-asserted-by":"publisher","award":["MYRG2018-00035-FST"],"award-info":[{"award-number":["MYRG2018-00035-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004733","name":"University of Macau","doi-asserted-by":"publisher","award":["MYRG2019-00086-FST"],"award-info":[{"award-number":["MYRG2019-00086-FST"]}],"id":[{"id":"10.13039\/501100004733","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Development Fund, Macau","award":["0034\/2019\/AMJ"],"award-info":[{"award-number":["0034\/2019\/AMJ"]}]},{"name":"Science and Technology Development Fund, Macau","award":["0087\/2020\/A2"],"award-info":[{"award-number":["0087\/2020\/A2"]}]},{"name":"Science and Technology Development Fund, Macau","award":["0049\/2021\/A"],"award-info":[{"award-number":["0049\/2021\/A"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2022,9]]},"DOI":"10.1109\/tcsvt.2022.3163445","type":"journal-article","created":{"date-parts":[[2022,3,30]],"date-time":"2022-03-30T19:56:39Z","timestamp":1648670199000},"page":"6472-6485","source":"Crossref","is-referenced-by-count":21,"title":["Temporal Relation Inference Network for Multimodal Speech Emotion Recognition"],"prefix":"10.1109","volume":"32","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1919-3258","authenticated-orcid":false,"given":"Guan-Nan","family":"Dong","sequence":"first","affiliation":[{"name":"Department of Computer and Information Science, University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1788-3746","authenticated-orcid":false,"given":"Chi-Man","family":"Pun","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1470-6998","authenticated-orcid":false,"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"Department of Computer and Information Science, University of Macau, Macau, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3007327"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.2980792"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2019.2918739"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2004.826773"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2003.1202279"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/S0167-6393(03)00099-2"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ITAIC.2019.8785867"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2013.6638116"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3351039"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2014.2324759"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240714"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/MASSP.1986.1165342"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/2647868.2654984"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2017.2719043"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/2133366.2133372"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123353"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2019.2925934"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2018.8639583"},{"key":"ref19","article-title":"Multimodal speech emotion recognition and ambiguity resolution","author":"Sahu","year":"2019","journal-title":"arXiv:1904.06022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2015.2444731"},{"key":"ref21","first-page":"2949","article-title":"Multimodal learning with deep Boltzmann machines","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7953112"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.389"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2858255"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2020.3026543"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3023632"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683163"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1242"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-3007"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2014.2360798"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3076364"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2020.3006331"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-2466"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683483"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2684799"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.21437\/interspeech.2017-200"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2016.0055"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN.2016.7727636"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2015.07.005"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2015.04.012"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2019.2960635"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.3014889"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.9"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2013.34"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref47","first-page":"1","article-title":"Efficient estimation of word representations in vector space","volume-title":"Proc. 1st Int. Conf. Learn. Represent., (ICLR) Workshop Track","author":"Mikolov"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref49","first-page":"1","article-title":"Attention is all you need","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Vaswani"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref51","article-title":"MELD: A multimodal multi-party dataset for emotion recognition in conversations","author":"Poria","year":"2018","journal-title":"arXiv:1810.02508"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/752"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1778"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414635"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3068598"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428327"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/76\/9875133\/09745163.pdf?arnumber=9745163","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,1,18]],"date-time":"2024-01-18T00:39:24Z","timestamp":1705538364000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9745163\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,9]]},"references-count":61,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2022.3163445","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,9]]}}}