{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:21:38Z","timestamp":1776889298467,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":63,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Shanghai Municipal Science and Technology Major Project","award":["2021SHZDZX"],"award-info":[{"award-number":["2021SHZDZX"]}]},{"name":"Shanghai Pujiang Program","award":["22PJ1408600"],"award-info":[{"award-number":["22PJ1408600"]}]},{"name":"National Natural Science Foundation of China","award":["61976135"],"award-info":[{"award-number":["61976135"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3613797","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:30Z","timestamp":1698391650000},"page":"5975-5984","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Multimodal Adaptive Emotion Transformer with Flexible Modality Inputs on A Novel Dataset with Continuous Labels"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-3759-5100","authenticated-orcid":false,"given":"Wei-Bang","family":"Jiang","sequence":"first","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9693-7839","authenticated-orcid":false,"given":"Xuan-Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9474-6369","authenticated-orcid":false,"given":"Wei-Long","family":"Zheng","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8359-0058","authenticated-orcid":false,"given":"Bao-Liang","family":"Lu","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University, Shanghai, China"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.specom.2019.12.001"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2714671"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1109\/EMBC46164.2021.9629837"},{"key":"e_1_3_2_1_4_1","volume-title":"Kriti Aggarwal, Subhojit Som, and Furu Wei.","author":"Bao Hangbo","year":"2021","unstructured":"Hangbo Bao, Wenhui Wang, Li Dong, Qiang Liu, Owais Khan Mohammed, Kriti Aggarwal, Subhojit Som, and Furu Wei. 2021. Vlmo: Unified vision-language pre-training with mixture-of-modality-experts. arXiv preprint arXiv:2111.02358 (2021)."},{"key":"e_1_3_2_1_5_1","first-page":"1","article-title":"EEG-based emotion recognition","volume":"56","author":"Bos Danny Oude","year":"2006","unstructured":"Danny Oude Bos et al. 2006. EEG-based emotion recognition. The Influence of Visual and Auditory Stimuli 56, 3 (2006), 1--17.","journal-title":"The Influence of Visual and Auditory Stimuli"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1111\/j.1469-8986.2008.00654.x"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2021.10.005"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548367"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIT.1967.1053964"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuron.2013.10.017"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/NER.2013.6695876"},{"key":"e_1_3_2_1_12_1","first-page":"488","article-title":"Automatic emotion recognition using facial expression: a review","volume":"3","author":"Dubey Monika","year":"2016","unstructured":"Monika Dubey and Lokesh Singh. 2016. Automatic emotion recognition using facial expression: a review. International Research Journal of Engineering and Technology (IRJET) 3, 2 (2016), 488--492.","journal-title":"International Research Journal of Engineering and Technology (IRJET)"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0030377"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2010.09.020"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/0191-8869(85)90026-1"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1016\/j"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.5555\/2946645.2946704"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3389\/fnins.2013.00267"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1007\/s40815-018-0567-3"},{"key":"e_1_3_2_1_20_1","volume-title":"Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415","author":"Hendrycks Dan","year":"2016","unstructured":"Dan Hendrycks and Kevin Gimpel. 2016. Gaussian error linear units (gelus). arXiv preprint arXiv:1606.08415 (2016)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2017.2781732"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.neuroimage.2021.118819"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1080\/02533839.2013.799946"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475583"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669637"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/JBHI.2017.2688239"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2019.2936124"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2008.26"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.15"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12559-017-9533-x"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCDS.2021.3071170"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46672-9_58"},{"key":"e_1_3_2_1_35_1","volume-title":"Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101","author":"Loshchilov Ilya","year":"2017","unstructured":"Ilya Loshchilov and Frank Hutter. 2017. Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1080\/02699930802204677"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICECA49313.2020.9297483"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.procs.2020.07.101"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ECBIOS51820.2021.9510858"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-50726-8_23"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.954607"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2022.103547"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1037\/h0077714"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/bhv086"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.3390\/e21070646"},{"key":"e_1_3_2_1_46_1","volume-title":"Bernd Bender, and Myriam N Bechtoldt.","author":"Schreckenbach Teresa","year":"2018","unstructured":"Teresa Schreckenbach, Falk Ochsendorf, Jasmina Sterz, Miriam R\u00fcsseler, Wolf Otto Bechstein, Bernd Bender, and Myriam N Bechtoldt. 2018. Emotion recognition and extraversion of medical students interact to predict their empathic communication perceived by simulated patients. BMC medical education 18, 1 (2018), 1--10."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2019.8803460"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/IEMBS.2010.5627125"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2015.2436926"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.25"},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/T-AFFC.2011.37"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2018.2817622"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1007\/s12193-015-0203-6"},{"key":"e_1_3_2_1_54_1","volume-title":"Attention is all you need. Advances in Neural Information Processing Systems 30","author":"Vaswani Ashish","year":"2017","unstructured":"Ashish Vaswani, Noam Shazeer, Niki Parmar, Jakob Uszkoreit, Llion Jones, Aidan N Gomez, ?ukasz Kaiser, and Illia Polosukhin. 2017. Attention is all you need. Advances in Neural Information Processing Systems 30 (2017)."},{"key":"e_1_3_2_1_55_1","volume-title":"Emotion Recognition with Pre-Trained Transformers Using Multimodal Signals. In 2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE, 1--8.","author":"Vazquez-Rodriguez Juan","year":"2022","unstructured":"Juan Vazquez-Rodriguez, Gr\u00e9goire Lefebvre, Julien Cumin, and James L Crowley. 2022. Emotion Recognition with Pre-Trained Transformers Using Multimodal Signals. In 2022 10th International Conference on Affective Computing and Intelligent Interaction (ACII). IEEE, 1--8."},{"key":"e_1_3_2_1_56_1","doi-asserted-by":"publisher","DOI":"10.1109\/BIBM52615.2021.9669556"},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/JSEN.2022.3144317"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.1038\/s41398-022-02064-z"},{"key":"e_1_3_2_1_59_1","volume-title":"Free Lunch for Domain Adversarial Training: Environment Label Smoothing. In International Conference on Learning Representations.","author":"Zhang YiFan","year":"2023","unstructured":"YiFan Zhang, Xue Wang, Jian Liang, Zhang Zhang, Liang Wang, Rong Jin, and Tieniu Tan. 2023. Free Lunch for Domain Adversarial Training: Environment Label Smoothing. In International Conference on Learning Representations."},{"key":"e_1_3_2_1_60_1","doi-asserted-by":"publisher","DOI":"10.1109\/NER.2019.8717055"},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2018.2797176"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAMD.2015.2431497"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2020.2994159"}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","location":"Ottawa ON Canada","acronym":"MM '23","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613797","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3613797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:06:29Z","timestamp":1755821189000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3613797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":63,"alternative-id":["10.1145\/3581783.3613797","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3613797","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}