{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:32:47Z","timestamp":1783823567136,"version":"3.55.0"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"3","license":[{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,7,1]],"date-time":"2025-07-01T00:00:00Z","timestamp":1751328000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100003399","name":"Science and Technology Commission of Shanghai Municipality","doi-asserted-by":"publisher","award":["22511105901"],"award-info":[{"award-number":["22511105901"]}],"id":[{"id":"10.13039\/501100003399","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["32471151"],"award-info":[{"award-number":["32471151"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key R&D Program"},{"name":"Health and Aging Population Technology Response","award":["2024YFC3606802"],"award-info":[{"award-number":["2024YFC3606802"]}]},{"name":"Beijing Key Laboratory of Behavior and Mental Health, Peking University"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2025,7]]},"DOI":"10.1109\/taffc.2025.3558222","type":"journal-article","created":{"date-parts":[[2025,4,4]],"date-time":"2025-04-04T16:08:12Z","timestamp":1743782892000},"page":"2261-2273","source":"Crossref","is-referenced-by-count":13,"title":["Towards Speaker-Unknown Emotion Recognition in Conversation via Progressive Contrastive Deep Supervision"],"prefix":"10.1109","volume":"16","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9732-9600","authenticated-orcid":false,"given":"Siyuan","family":"Shen","sequence":"first","affiliation":[{"name":"Research and Development Department, Baidu Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5289-5761","authenticated-orcid":false,"given":"Feng","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Psychology, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5227-5765","authenticated-orcid":false,"given":"Hanyang","family":"Wang","sequence":"additional","affiliation":[{"name":"AI Research Center, Midea Group Inc., Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4768-5946","authenticated-orcid":false,"given":"Aimin","family":"Zhou","sequence":"additional","affiliation":[{"name":"Institute of AI Education, East China Normal University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i09.7098"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3057270"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.440"},{"issue":"2","key":"ref4","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1109\/TAFFC.2023.3298405","article-title":"Text-based fine-grained emotion prediction","volume":"15","author":"Singh","year":"2024","journal-title":"IEEE Trans. Affect. Comput."},{"key":"ref5","doi-asserted-by":"crossref","first-page":"1","DOI":"10.4018\/IJSWIS.339187","article-title":"Affective prompt-tuning-based language model for semantic-based emotional text generation","volume":"20","author":"Gu","year":"2024","journal-title":"Int. J. Semantic Web Inf. Syst."},{"key":"ref6","first-page":"13789","article-title":"DialogXL: All-in-one XLNet for multi-party conversation emotion recognition","volume-title":"Proc. AAAI Conf. Artif. Intell.","author":"Shen"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.125"},{"key":"ref8","first-page":"2470","article-title":"COSMIC: Commonsense knowledge for emotion identification in conversations","volume-title":"Proc. Int. Conf. Findings Assoc. Comput. Linguistics","author":"Ghosal"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556601"},{"key":"ref10","first-page":"5415","article-title":"Modeling both context- and speaker-sensitive dependence for emotion detection in multi-speaker conversations","volume-title":"Proc. Int. Joint Conf. Artif. Intell.","author":"Zhang"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1280"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.547"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i15.17625"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i10.21348"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.123"},{"key":"ref18","article-title":"Multi-task learning framework for extracting emotion cause span and entailment in conversations","author":"Bhat","year":"2022"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.937"},{"key":"ref20","article-title":"HCAM \u2013 Hierarchical cross attention model for multi-modal emotion recognition","author":"Dutta","year":"2024"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.597"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747460"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054580"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2016-692"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19809-0_1"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2021.101317"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"ref30","first-page":"397","article-title":"HiGRU: Hierarchical gated recurrent units for utterance-level emotion recognition","volume-title":"Proc. 2019 Conf. North Amer. Chapter Assoc. Comput. Linguistics: Hum. Lang. Technol.","author":"Jiao"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.01.116"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/a16010008"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854514"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-573"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428217"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2010.8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2021.03.004"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2010.2064307"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6854363"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461375"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472652"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8461958"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/SLT.2016.7846260"},{"key":"ref44","article-title":"Bayesian speaker verification with, heavy tailed priors","volume-title":"Proc. Speaker Lang. Recognit. Workshop","author":"Kenny"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2010.2081790"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TASL.2013.2264673"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462628"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1388"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1893"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683892"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-2899"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952154"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2023-293"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref56","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"ref59","article-title":"Representation learning with contrastive predictive coding","author":"Oord","year":"2018"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01549"},{"key":"ref62","first-page":"18661","article-title":"Supervised contrastive learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Khosla"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.347"},{"key":"ref64","first-page":"562","article-title":"Deeply-supervised nets","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Lee"},{"key":"ref65","article-title":"Training deeper convolutional networks with deep supervision","author":"Wang","year":"2015"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.49"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2863285"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-00934-2_10"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00941"},{"key":"ref70","first-page":"3484","article-title":"Beyond object recognition: Visual sentiment analysis with deep coupled adjective and noun neural networks","volume-title":"Proc. 25th Int. Joint Conf. Artif. Intell.","author":"Wang"},{"key":"ref71","article-title":"Multi-task learning with deep neural networks: A survey","author":"Crawshaw","year":"2020"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2022.3145287"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1131-1"},{"key":"ref74","first-page":"9929","article-title":"Understanding contrastive representation learning through alignment and uniformity on the hypersphere","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Wang"},{"key":"ref75","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1022"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00252"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/5165369\/11152495\/10949847.pdf?arnumber=10949847","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,8]],"date-time":"2025-09-08T17:46:43Z","timestamp":1757353603000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10949847\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7]]},"references-count":77,"journal-issue":{"issue":"3"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2025.3558222","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7]]}}}