{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,5]],"date-time":"2026-07-05T00:17:44Z","timestamp":1783210664864,"version":"3.54.6"},"reference-count":52,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T00:00:00Z","timestamp":1790812800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4254091"],"award-info":[{"award-number":["4254091"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2026,10]]},"DOI":"10.1016\/j.neucom.2026.134368","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T15:12:58Z","timestamp":1782573178000},"page":"134368","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":0,"special_numbering":"C","title":["Milmer: a framework for multiple instance learning based multimodal emotion recognition"],"prefix":"10.1016","volume":"699","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9953-4956","authenticated-orcid":false,"given":"Zaitian","family":"Wang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5422-0920","authenticated-orcid":false,"given":"Yu","family":"Liang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7095-6986","authenticated-orcid":false,"given":"Xiyuan","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianhao","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6650-2850","authenticated-orcid":false,"given":"Kaixin","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiakai","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3215-222X","authenticated-orcid":false,"given":"Chenlong","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weili","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Niu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaoyang","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.neucom.2026.134368_bib0005","series-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","first-page":"10012","article-title":"Swin transformer: hierarchical vision transformer using shifted windows","author":"Liu","year":"2021"},{"issue":"1","key":"10.1016\/j.neucom.2026.134368_bib0010","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","article-title":"Deap: a database for emotion analysis; using physiological signals","volume":"3","author":"Koelstra","year":"2011","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"5","key":"10.1016\/j.neucom.2026.134368_bib0015","doi-asserted-by":"crossref","first-page":"105","DOI":"10.3390\/fi11050105","article-title":"Combining facial expressions and electroencephalography to enhance emotion recognition","volume":"11","author":"Huang","year":"2019","journal-title":"Future Internet"},{"key":"10.1016\/j.neucom.2026.134368_bib0020","author":"Khaireddin"},{"key":"10.1016\/j.neucom.2026.134368_bib0025","doi-asserted-by":"crossref","first-page":"3793","DOI":"10.1109\/TMM.2020.3032037","article-title":"C-GCN: correlation based graph convolutional network for audio-video emotion recognition","volume":"23","author":"Nie","year":"2020","journal-title":"IEEE Trans. Multimed."},{"issue":"4","key":"10.1016\/j.neucom.2026.134368_bib0030","doi-asserted-by":"crossref","first-page":"1374","DOI":"10.1109\/TCDS.2024.3357618","article-title":"Husformer: a multi-modal transformer for multi-modal human state recognition","volume":"16","author":"Wang","year":"2024","journal-title":"IEEE Trans. Cogn. Dev. Syst."},{"issue":"3","key":"10.1016\/j.neucom.2026.134368_bib0035","doi-asserted-by":"crossref","DOI":"10.1088\/1741-2552\/ad4743","article-title":"FetchEEG: a hybrid approach combining feature extraction and temporal-channel joint attention for EEG-based emotion classification","volume":"21","author":"Liang","year":"2024","journal-title":"J. Neural Eng."},{"issue":"7","key":"10.1016\/j.neucom.2026.134368_bib0040","doi-asserted-by":"crossref","first-page":"2074","DOI":"10.3390\/s18072074","article-title":"A review of emotion recognition using physiological signals","volume":"18","author":"Shu","year":"2018","journal-title":"Sensors"},{"issue":"23","key":"10.1016\/j.neucom.2026.134368_bib0045","doi-asserted-by":"crossref","DOI":"10.3390\/app132312832","article-title":"A fusion framework for confusion analysis in learning based on EEG signals","volume":"13","author":"Zhang","year":"2023","journal-title":"Appl. Sci."},{"key":"10.1016\/j.neucom.2026.134368_bib0050","doi-asserted-by":"crossref","first-page":"103","DOI":"10.1016\/j.inffus.2020.01.011","article-title":"Emotion recognition using multi-modal data and machine learning techniques: a tutorial and review","volume":"59","author":"Zhang","year":"2020","journal-title":"Inf. Fusion"},{"issue":"1","key":"10.1016\/j.neucom.2026.134368_bib0055","article-title":"Fusion of facial expressions and EEG for multimodal emotion recognition","volume":"2017","author":"Huang","year":"2017","journal-title":"Comput. Intell. Neurosci."},{"key":"10.1016\/j.neucom.2026.134368_bib0060","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104121","article-title":"Deep learning model for simultaneous recognition of quantitative and qualitative emotion using visual and bio-sensing data","volume":"248","author":"Hosseini","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.neucom.2026.134368_bib0065","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2023.126866","article-title":"A review of multimodal emotion recognition from datasets, preprocessing, features, and fusion methods","author":"Pan","year":"2023","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2026.134368_bib0070","series-title":"International Conference on Machine Learning","first-page":"5583","article-title":"Vilt: vision-and-language transformer without convolution or region supervision","author":"Kim","year":"2021"},{"key":"10.1016\/j.neucom.2026.134368_bib0075","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.130185","article-title":"Stress assessment with EEG and machine learning in affective VR environments","volume":"638","author":"Marcolin","year":"2025","journal-title":"Neurocomputing"},{"issue":"11","key":"10.1016\/j.neucom.2026.134368_bib0080","doi-asserted-by":"crossref","first-page":"5391","DOI":"10.1002\/hbm.23730","article-title":"Deep learning with convolutional neural networks for EEG decoding and visualization","volume":"38","author":"Schirrmeister","year":"2017","journal-title":"Hum. Brain Mapp."},{"issue":"3","key":"10.1016\/j.neucom.2026.134368_bib0085","doi-asserted-by":"crossref","first-page":"417","DOI":"10.1109\/TAFFC.2017.2712143","article-title":"Identifying stable patterns over time for emotion recognition from EEG","volume":"10","author":"Zheng","year":"2017","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"5","key":"10.1016\/j.neucom.2026.134368_bib0090","doi-asserted-by":"crossref","first-page":"4359","DOI":"10.1109\/JSEN.2022.3144317","article-title":"Transformers for EEG-based emotion recognition: a hierarchical spatial information learning model","volume":"22","author":"Wang","year":"2022","journal-title":"IEEE Sens. J."},{"issue":"3","key":"10.1016\/j.neucom.2026.134368_bib0095","doi-asserted-by":"crossref","first-page":"1290","DOI":"10.1109\/TAFFC.2020.2994159","article-title":"EEG-based emotion recognition using regularized graph neural networks","volume":"13","author":"Zhong","year":"2020","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134368_bib0100","doi-asserted-by":"crossref","DOI":"10.1016\/j.compbiomed.2023.107450","article-title":"Emotion recognition in EEG signals using deep learning methods: a review","author":"Jafari","year":"2023","journal-title":"Comput. Biol. Med."},{"key":"10.1016\/j.neucom.2026.134368_bib0105","author":"Breuer"},{"key":"10.1016\/j.neucom.2026.134368_bib0110","series-title":"Proceedings of the 18th ACM International Conference on Multimodal Interaction","first-page":"445","article-title":"Video-based emotion recognition using CNN-RNN and C3D hybrid networks","author":"Fan","year":"2016"},{"key":"10.1016\/j.neucom.2026.134368_bib0115","series-title":"2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","first-page":"6837","article-title":"End-to-end continuous emotion recognition from video using 3D ConvLSTM networks","author":"Huang","year":"2018"},{"key":"10.1016\/j.neucom.2026.134368_bib0120","series-title":"Proceedings of the 29th ACM International Conference on Multimedia","first-page":"1553","article-title":"Former-dfer: dynamic facial expression recognition transformer","author":"Zhao","year":"2021"},{"key":"10.1016\/j.neucom.2026.134368_bib0125","doi-asserted-by":"crossref","first-page":"35","DOI":"10.1016\/j.ins.2021.08.043","article-title":"Facial expression recognition with grid-wise attention and visual transformer","volume":"580","author":"Huang","year":"2021","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.134368_bib0130","doi-asserted-by":"crossref","first-page":"593","DOI":"10.1016\/j.ins.2021.10.005","article-title":"A survey on facial emotion recognition techniques: a state-of-the-art literature review","volume":"582","author":"Canal","year":"2022","journal-title":"Inf. Sci."},{"key":"10.1016\/j.neucom.2026.134368_bib0135","doi-asserted-by":"crossref","first-page":"24587","DOI":"10.1109\/ACCESS.2025.3538642","article-title":"Multimodal emotion recognition: emotion classification through the integration of EEG and facial expressions","volume":"13","author":"Guler","year":"2025","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.134368_bib0140","doi-asserted-by":"crossref","DOI":"10.1016\/j.bspc.2021.103029","article-title":"A multimodal emotion recognition method based on facial expressions and electroencephalography","volume":"70","author":"Tan","year":"2021","journal-title":"Biomed. Signal Process. Control"},{"issue":"5","key":"10.1016\/j.neucom.2026.134368_bib0145","doi-asserted-by":"crossref","first-page":"977","DOI":"10.3390\/diagnostics13050977","article-title":"A bimodal emotion recognition approach through the fusion of electroencephalography and facial sequences","volume":"13","author":"Muhammad","year":"2023","journal-title":"Diagnostics"},{"key":"10.1016\/j.neucom.2026.134368_bib0150","author":"Liu"},{"issue":"1","key":"10.1016\/j.neucom.2026.134368_bib0155","first-page":"96","article-title":"Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing","volume":"13","author":"Jung","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134368_bib0160","series-title":"International Conference on Machine Learning","first-page":"2127","article-title":"Attention-based deep multiple instance learning","author":"Ilse","year":"2018"},{"issue":"4","key":"10.1016\/j.neucom.2026.134368_bib0165","doi-asserted-by":"crossref","first-page":"3231","DOI":"10.1109\/TAFFC.2025.3581388","article-title":"EmotionMIL: an end-to-end multiple instance learning framework for emotion recognition from EEG signals","volume":"16","author":"Xiao","year":"2025","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134368_bib0170","series-title":"2016 IEEE International Conference on Image Processing (ICIP)","first-page":"634","article-title":"Multi-scale blocks based image emotion classification using multiple instance learning","author":"Rao","year":"2016"},{"issue":"1","key":"10.1016\/j.neucom.2026.134368_bib0175","doi-asserted-by":"crossref","first-page":"389","DOI":"10.1109\/TAFFC.2019.2954118","article-title":"Multiple instance learning for emotion recognition using physiological signals","volume":"13","author":"Romeo","year":"2019","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.neucom.2026.134368_bib0180","article-title":"Attention is all you need","volume":"30","author":"Vaswani","year":"2017","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.neucom.2026.134368_bib0185","series-title":"International Conference on Machine Learning","first-page":"19730","article-title":"Blip-2: bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023"},{"key":"10.1016\/j.neucom.2026.134368_bib0190","first-page":"267","article-title":"MEG and EEG data analysis with MNE-Python","volume":"7","author":"Gramfort","year":"2013","journal-title":"Front. Neuroinformatics"},{"key":"10.1016\/j.neucom.2026.134368_bib0195","author":"Loshchilov"},{"key":"10.1016\/j.neucom.2026.134368_bib0200","author":"Bazarevsky"},{"issue":"6","key":"10.1016\/j.neucom.2026.134368_bib0205","doi-asserted-by":"crossref","first-page":"2266","DOI":"10.1109\/JSEN.2018.2883497","article-title":"Cross-subject emotion recognition using flexible analytic wavelet transform from EEG signals","volume":"19","author":"Gupta","year":"2018","journal-title":"IEEE Sens. J."},{"issue":"5","key":"10.1016\/j.neucom.2026.134368_bib0210","doi-asserted-by":"crossref","first-page":"1383","DOI":"10.3390\/s18051383","article-title":"Electroencephalography based fusion two-dimensional (2D)-convolution neural networks (CNN) model for emotion recognition system","volume":"18","author":"Kwon","year":"2018","journal-title":"Sensors"},{"key":"10.1016\/j.neucom.2026.134368_bib0215","series-title":"2021 International Symposium of Asian Control Association on Intelligent Robotics and Industrial Automation (IRIA)","first-page":"304","article-title":"EEG-based emotion recognition using genetic algorithm optimized multi-layer perceptron","author":"Marjit","year":"2021"},{"key":"10.1016\/j.neucom.2026.134368_bib0220","doi-asserted-by":"crossref","first-page":"168865","DOI":"10.1109\/ACCESS.2020.3023871","article-title":"Cross-subject multimodal emotion recognition based on hybrid fusion","volume":"8","author":"Cimtay","year":"2020","journal-title":"IEEE Access"},{"issue":"10","key":"10.1016\/j.neucom.2026.134368_bib0225","doi-asserted-by":"crossref","first-page":"997","DOI":"10.3390\/bioengineering11100997","article-title":"Emotion recognition using EEG signals and audiovisual features with contrastive learning","volume":"11","author":"Lee","year":"2024","journal-title":"Bioengineering"},{"issue":"4","key":"10.1016\/j.neucom.2026.134368_bib0230","doi-asserted-by":"crossref","first-page":"3177","DOI":"10.1109\/TAFFC.2023.3253859","article-title":"Recognizing, fast and slow: complex emotion recognition with facial expression detection and remote physiological measurement","volume":"14","author":"Wu","year":"2023","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"8","key":"10.1016\/j.neucom.2026.134368_bib0235","article-title":"EEG-based emotion recognition using 3D convolutional neural networks","volume":"9","author":"Salama","year":"2018","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"4","key":"10.1016\/j.neucom.2026.134368_bib0240","doi-asserted-by":"crossref","first-page":"2426","DOI":"10.1109\/TSMC.2024.3523342","article-title":"Design and analysis of a closed-loop emotion regulation system based on multimodal affective computing and emotional Markov chain","volume":"55","author":"Wang","year":"2025","journal-title":"IEEE Trans. Syst. Man Cybern. Syst."},{"issue":"1","key":"10.1016\/j.neucom.2026.134368_bib0245","article-title":"Expression EEG multimodal emotion recognition method based on the bidirectional LSTM and attention mechanism","volume":"2021","author":"Zhao","year":"2021","journal-title":"Computational and Mathematical Methods in Medicine"},{"issue":"7","key":"10.1016\/j.neucom.2026.134368_bib0250","doi-asserted-by":"crossref","first-page":"10901","DOI":"10.1007\/s11042-022-13711-4","article-title":"Multi-modal emotion identification fusing facial expression and EEG","volume":"82","author":"Wu","year":"2023","journal-title":"Multimed. Tools Appl."},{"key":"10.1016\/j.neucom.2026.134368_bib0255","doi-asserted-by":"crossref","first-page":"33061","DOI":"10.1109\/ACCESS.2023.3263670","article-title":"Multimodal emotion recognition from EEG signals and facial expressions","volume":"11","author":"Wang","year":"2023","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2026.134368_bib0260","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","article-title":"Return of frustratingly easy domain adaptation","volume":"vol. 30","author":"Sun","year":"2016"}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017662?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231226017662?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T23:52:00Z","timestamp":1783209120000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231226017662"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,10]]},"references-count":52,"alternative-id":["S0925231226017662"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134368","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2026,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Milmer: a framework for multiple instance learning based multimodal emotion recognition","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2026.134368","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier B.V. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"134368"}}