{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:27:29Z","timestamp":1784388449028,"version":"3.55.0"},"reference-count":87,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62206136"],"award-info":[{"award-number":["62206136"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Key Laboratory of Human Digital Twin","award":["2022B121201 0004"],"award-info":[{"award-number":["2022B121201 0004"]}]},{"name":"Inner Mongolia Science and Technology Achievement Transfer and Transformation Demonstration Zone"},{"name":"University Collaborative Innovation Base"},{"name":"University Entrepreneurship Training Base","award":["21300-231510"],"award-info":[{"award-number":["21300-231510"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62201572"],"award-info":[{"award-number":["62201572"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Internal Project Fund from Shenzhen Research Institute of Big Data","award":["T00120220002"],"award-info":[{"award-number":["T00120220002"]}]},{"name":"Shenzhen Science and Technology Research Fund Fundamental Research Key Project","award":["JCYJ20220818103001002"],"award-info":[{"award-number":["JCYJ20220818103001002"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Affective Comput."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/taffc.2024.3378570","type":"journal-article","created":{"date-parts":[[2024,3,18]],"date-time":"2024-03-18T19:05:52Z","timestamp":1710788752000},"page":"1856-1873","source":"Crossref","is-referenced-by-count":80,"title":["Contrastive Learning Based Modality-Invariant Feature Acquisition for Robust Multimodal Emotion Recognition With Missing Modalities"],"prefix":"10.1109","volume":"15","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4524-7413","authenticated-orcid":false,"given":"Rui","family":"Liu","sequence":"first","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1412-2883","authenticated-orcid":false,"given":"Haolin","family":"Zuo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Inner Mongolia University, Hohhot, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"additional","affiliation":[{"name":"Institute of Automation, Chinese Academy of Sciences, Bejing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6478-8699","authenticated-orcid":false,"given":"Bj\u00f6rn W.","family":"Schuller","sequence":"additional","affiliation":[{"name":"GLAM–the Group on Language, Audio, & Music, Imperial College London, London, U.K."}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9158-9401","authenticated-orcid":false,"given":"Haizhou","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen Research Institute of Big Data, School of Data Science, The Chinese University of Hong Kong, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3092735"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413690"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2022-534"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/IALP54817.2021.9675192"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1236"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i17.29833"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.203"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413909"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475585"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2023.3274829"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3037734"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref15","first-page":"17612","article-title":"Mind the gap: Understanding the modality gap in multi-modal contrastive representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liang"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475465"},{"key":"ref18","article-title":"Domain and modality gaps for LiDAR-based person detection on mobile robots","author":"Jia","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.215"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.202"},{"key":"ref21","first-page":"24206","article-title":"VATT: Transformers for multimodal self-supervised learning from raw video, audio and text","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Akbari"},{"key":"ref22","article-title":"Learning in audio-visual context: A review, analysis, and new perspective","author":"Wei","year":"2022"},{"key":"ref23","article-title":"Multimodal analogical reasoning over knowledge graphs","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095836"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tnnls.2023.3327962"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3126782"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3316458"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.acl-long.421"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-acl.130"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.21437\/Odyssey.2022-57"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746598"},{"key":"ref32","article-title":"RoBERTa: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.acl-long.412"},{"key":"ref35","article-title":"CMI-Net: A unified framework for physiological time series classification with incomplete modalities","author":"Shen","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3325770"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.findings-emnlp.900"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1152"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICDM.2018.00174"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3219963"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/1390156.1390294"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.528"},{"key":"ref44","article-title":"Variational autoencoder with arbitrary conditioning","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Ivanov"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240528"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ITSC.2014.6957805"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/490"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5795"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8682773"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3216993"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"issue":"11","key":"ref53","first-page":"2579","article-title":"Visualizing data using T-SNE","volume":"9","author":"Van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/SLT48900.2021.9383618"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.86"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.427"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"ref61","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref62","first-page":"4348","article-title":"Understanding multimodal contrastive learning and incorporating unpaired data","volume-title":"Proc. Int. Conf. Artif. Intell. Statist.","author":"Nakada"},{"key":"ref63","article-title":"Long short-term memory based recurrent neural network architectures for large vocabulary speech recognition","author":"Sak","year":"2004"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/d14-1181"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/978-0-387-84858-7"},{"key":"ref66","volume-title":"Neural Networks and Deep Learning","volume":"25","author":"Nielsen","year":"2015"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2016.2515617"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/MIS.2016.94"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413579"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0024"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.113723"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09068-1"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4899-7687-1_953"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1145\/1873951.1874246"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/n19-1423"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"ref80","volume-title":"What the Face Reveals: Basic and Applied Studies of Spontaneous Expression Using the Facial Action Coding System (FACS)","author":"Rosenberg","year":"2020"},{"key":"ref81","article-title":"Rectifier nonlinearities improve neural network acoustic models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Maas"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556630"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859836"},{"key":"ref84","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref85","article-title":"Deep transformer models for time series forecasting: The influenza prevalence case","author":"Wu","year":"2020"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.76"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3348762"}],"container-title":["IEEE Transactions on Affective Computing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/5165369\/10768431\/10474146.pdf?arnumber=10474146","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,27]],"date-time":"2024-11-27T19:38:10Z","timestamp":1732736290000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10474146\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":87,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/taffc.2024.3378570","relation":{},"ISSN":["1949-3045","2371-9850"],"issn-type":[{"value":"1949-3045","type":"electronic"},{"value":"2371-9850","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}