{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T16:11:48Z","timestamp":1781799108732,"version":"3.54.5"},"reference-count":100,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Excellent Youth Program of the State Key Laboratory of Multimodal Artificial Intelligence Systems","award":["MAIS2024311"],"award-info":[{"award-number":["MAIS2024311"]}]},{"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"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62322120"],"award-info":[{"award-number":["62322120"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61831022"],"award-info":[{"award-number":["61831022"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62276259"],"award-info":[{"award-number":["62276259"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21B2010"],"award-info":[{"award-number":["U21B2010"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tpami.2026.3653457","type":"journal-article","created":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:30Z","timestamp":1768255230000},"page":"5793-5810","source":"Crossref","is-referenced-by-count":4,"title":["MERBench: A Unified Evaluation Benchmark for Multimodal Emotion Recognition"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-9477-0599","authenticated-orcid":false,"given":"Zheng","family":"Lian","sequence":"first","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7944-3458","authenticated-orcid":false,"given":"Licai","family":"Sun","sequence":"additional","affiliation":[{"name":"University of Oulu, Oulu, Finland"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong","family":"Ren","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Gu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyang","family":"Sun","sequence":"additional","affiliation":[{"name":"School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lan","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1529-1552","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9344-6428","authenticated-orcid":false,"given":"Jianhua","family":"Tao","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/1140.001.0001"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.011"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/MCI.2018.2840738"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/taffc.2023.3274829"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3049898"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3141237"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1145\/3423327.3423672"},{"key":"ref9","first-page":"1","article-title":"Investigation of multimodal features, classifiers and fusion methods for emotion recognition","volume-title":"Proc. Nat. Conf. Man- Mach. Speech Commun.","author":"Lian"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s10579-008-9076-6"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3234553"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.391"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.11.007"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2983669"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D17-1115"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1050"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3536221.3556630"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1037\/13784-000"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1080\/026999398379574"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0732"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1186\/s40537-016-0043-6"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3395035.3425202"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3037734"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CSCITA.2014.6839284"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2009-103"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2010-739"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2016.7472669"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3207050"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2019-1873"},{"key":"ref33","first-page":"12449","article-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Baevski"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3122291"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-020-1647-3"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref37","article-title":"RoBERTa: A robustly optimized BERT pretraining approach","author":"Liu","year":"2019"},{"key":"ref38","first-page":"5754","article-title":"XLNet: Generalized autoregressive pretraining for language understanding","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref39","first-page":"1","article-title":"DeBERTa: Decoding-enhanced BERT with disentangled attention","volume-title":"Proc. 8th Int. Conf. Learn. Representations","author":"He"},{"key":"ref40","first-page":"1","article-title":"ALBERT: A lite BERT for self-supervised learning of language representations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Lan"},{"key":"ref41","first-page":"1","article-title":"ELECTRA: Pre-training text encoders as discriminators rather than generators","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Clark"},{"key":"ref42","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023"},{"key":"ref43","article-title":"The RefinedWeb dataset for falcon LLM: Outperforming curated corpora with web data, and web data only","author":"Penedo","year":"2023"},{"key":"ref44","article-title":"BLOOM: A 176B-parameter open-access multilingual language model","author":"Workshop"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/34.908962"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2981446"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3093397"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-42051-1_16"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.277"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2992393"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3577925"},{"key":"ref55","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref56","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1209"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413678"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"ref62","first-page":"1","article-title":"Learning factorized multimodal representations","volume-title":"Proc. 7th Int. Conf. Learn. Representations","author":"Tsai"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1656"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1016\/0005-7916(94)90063-9"},{"key":"ref65","article-title":"MUSAN: A music, speech, and noise corpus","author":"Snyder","year":"2015"},{"key":"ref66","first-page":"1","article-title":"A baseline for detecting misclassified and out-of-distribution examples in neural networks","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00945"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2016.7477553"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2021-1983"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0195-2"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2024.105171"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2457417"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2017.7952132"},{"key":"ref74","first-page":"1298","article-title":"Data2Vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSTSP.2022.3188113"},{"key":"ref76","first-page":"28492","article-title":"Robust speech recognition via large-scale weak supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref77","article-title":"OPT: Open pre-trained transformer language models","author":"Zhang","year":"2022"},{"key":"ref78","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref79","article-title":"StableLM alpha v2 models","author":"Tow","year":"2023"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1410"},{"key":"ref81","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"key":"ref82","article-title":"PERT: Pre-training BERT with permuted language model","author":"Cui","year":"2022"},{"key":"ref83","article-title":"LERT: A linguistically-motivated pre-trained language model","author":"Cui","year":"2022"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-long.26"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.58"},{"key":"ref86","article-title":"Baichuan 2: Open large-scale language models","author":"Yang","year":"2023"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/FG47880.2020.00126"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P17-1081"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-1193"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"ref92","first-page":"1597","article-title":"EmotionLines: An emotion corpus of multi-party conversations","volume-title":"Proc. 11th Int. Conf. Lang. Resour. Eval.","author":"Hsu"},{"key":"ref93","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612365"},{"key":"ref96","article-title":"GPT-4V with emotion: A zero-shot benchmark for multimodal emotion understanding","author":"Lian","year":"2023"},{"key":"ref97","article-title":"Explainable multimodal emotion reasoning","author":"Lian","year":"2023"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1016\/j.tics.2020.11.004"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3411290"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11474534\/11347465.pdf?arnumber=11347465","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,6]],"date-time":"2026-04-06T19:56:26Z","timestamp":1775505386000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11347465\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":100,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3653457","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}