{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T18:51:11Z","timestamp":1780512671169,"version":"3.54.1"},"reference-count":59,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["No.U2133218"],"award-info":[{"award-number":["No.U2133218"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"The National Key Research and Development Program of China","award":["No.2018YFB0204304"],"award-info":[{"award-number":["No.2018YFB0204304"]}]},{"name":"The Fundamental Research Funds for the Central Universities of China","award":["No.FRF-MP-19-007 and No. FRF-TP-20-065A1Z"],"award-info":[{"award-number":["No.FRF-MP-19-007 and No. FRF-TP-20-065A1Z"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s10489-024-05329-w","type":"journal-article","created":{"date-parts":[[2024,2,21]],"date-time":"2024-02-21T06:03:16Z","timestamp":1708495396000},"page":"3040-3057","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":8,"title":["A multimodal fusion-based deep learning framework combined with local-global contextual TCNs for continuous emotion recognition from videos"],"prefix":"10.1007","volume":"54","author":[{"given":"Congbao","family":"Shi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanyuan","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0975-2316","authenticated-orcid":false,"given":"Baolin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,21]]},"reference":[{"issue":"104","key":"5329_CR1","doi-asserted-by":"publisher","first-page":"445","DOI":"10.1016\/j.bspc.2022.104445","volume":"81","author":"YH Bhosale","year":"2023","unstructured":"Bhosale YH, Patnaik KS (2023) Puldi-covid: Chronic obstructive pulmonary (lung) diseases with covid-19 classification using ensemble deep convolutional neural network from chest x-ray images to minimize severity and mortality rates. Biomed Signal Process Control 81(104):445. https:\/\/doi.org\/10.1016\/j.bspc.2022.104445","journal-title":"Biomed Signal Process Control"},{"issue":"108","key":"5329_CR2","doi-asserted-by":"publisher","first-page":"485","DOI":"10.1016\/j.asoc.2022.108485","volume":"118","author":"J Zhang","year":"2022","unstructured":"Zhang J, Feng W, Yuan T et al (2022) Scstcf: spatial-channel selection and temporal regularized correlation filters for visual tracking. Appl Soft Comput 118(108):485. https:\/\/doi.org\/10.1016\/j.asoc.2022.108485","journal-title":"Appl Soft Comput"},{"issue":"3","key":"5329_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3388790","volume":"53","author":"S Zepf","year":"2020","unstructured":"Zepf S, Hernandez J, Schmitt A et al (2020) Driver emotion recognition for intelligent vehicles: A survey. ACM Computing Surveys (CSUR) 53(3):1\u201330. https:\/\/doi.org\/10.1145\/3388790","journal-title":"ACM Computing Surveys (CSUR)"},{"key":"5329_CR4","doi-asserted-by":"publisher","first-page":"212","DOI":"10.1016\/j.neucom.2020.01.034","volume":"388","author":"Z Fei","year":"2020","unstructured":"Fei Z, Yang E, Li DDU et al (2020) Deep convolution network based emotion analysis towards mental health care. Neurocomputing 388:212\u2013227. https:\/\/doi.org\/10.1016\/j.neucom.2020.01.034","journal-title":"Neurocomputing"},{"key":"5329_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2020\/4065207","volume":"2020","author":"W Wang","year":"2020","unstructured":"Wang W, Xu K, Niu H et al (2020) Emotion recognition of students based on facial expressions in online education based on the perspective of computer simulation. Complexity 2020:1\u20139. https:\/\/doi.org\/10.1155\/2020\/4065207","journal-title":"Complexity"},{"key":"5329_CR6","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1016\/j.inffus.2020.01.011","volume":"59","author":"J Zhang","year":"2020","unstructured":"Zhang J, Yin Z, Chen P et al (2020) Emotion recognition using multi-modal data and machine learning techniques: A tutorial and review. Information Fusion 59:103\u2013126. https:\/\/doi.org\/10.1016\/j.inffus.2020.01.011","journal-title":"Information Fusion"},{"key":"5329_CR7","doi-asserted-by":"publisher","first-page":"56","DOI":"10.1016\/j.specom.2019.12.001","volume":"116","author":"MB Ak\u00e7ay","year":"2020","unstructured":"Ak\u00e7ay MB, O\u011fuz K (2020) Speech emotion recognition: Emotional models, databases, features, preprocessing methods, supporting modalities, and classifiers. Speech Commun 116:56\u201376. https:\/\/doi.org\/10.1016\/j.specom.2019.12.001","journal-title":"Speech Commun"},{"key":"5329_CR8","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.inffus.2019.06.019","volume":"53","author":"Y Jiang","year":"2020","unstructured":"Jiang Y, Li W, Hossain MS et al (2020) A snapshot research and implementation of multimodal information fusion for data-driven emotion recognition. Information Fusion 53:209\u2013221. https:\/\/doi.org\/10.1016\/j.inffus.2019.06.019","journal-title":"Information Fusion"},{"issue":"3","key":"5329_CR9","doi-asserted-by":"publisher","first-page":"417","DOI":"10.3390\/electronics11030417","volume":"11","author":"X Li","year":"2022","unstructured":"Li X, Lu G, Yan J et al (2022) A multi-scale multi-task learning model for continuous dimensional emotion recognition from audio. Electronics 11(3):417. https:\/\/doi.org\/10.3390\/electronics11030417","journal-title":"Electronics"},{"issue":"3","key":"5329_CR10","doi-asserted-by":"publisher","first-page":"595","DOI":"10.1109\/TAFFC.2020.3014171","volume":"12","author":"D Kollias","year":"2020","unstructured":"Kollias D, Zafeiriou S (2020) Exploiting multi-cnn features in cnn-rnn based dimensional emotion recognition on the omg in-the-wild dataset. IEEE Trans Affect Comput 12(3):595\u2013606. https:\/\/doi.org\/10.1109\/TAFFC.2020.3014171","journal-title":"IEEE Trans Affect Comput"},{"issue":"2","key":"5329_CR11","doi-asserted-by":"publisher","first-page":"524","DOI":"10.1109\/TAFFC.2018.2890471","volume":"12","author":"PV Rouast","year":"2019","unstructured":"Rouast PV, Adam MT, Chiong R (2019) Deep learning for human affect recognition: Insights and new developments. IEEE Trans Affect Comput 12(2):524\u2013543. https:\/\/doi.org\/10.1109\/TAFFC.2018.2890471","journal-title":"IEEE Trans Affect Comput"},{"key":"5329_CR12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2022.03.009","author":"Y Wang","year":"2022","unstructured":"Wang Y, Song W, Tao W et al (2022) A systematic review on affective computing: Emotion models, databases, and recent advances. Information Fusion. https:\/\/doi.org\/10.1016\/j.inffus.2022.03.009","journal-title":"Information Fusion"},{"key":"5329_CR13","doi-asserted-by":"publisher","unstructured":"Zhao J, Li R, Chen S et\u00a0al (2018) Multi-modal multi-cultural dimensional continues emotion recognition in dyadic interactions. In: Proceedings of the 2018 on audio\/visual emotion challenge and workshop, pp 65\u201372. https:\/\/doi.org\/10.1145\/3266302.3266313","DOI":"10.1145\/3266302.3266313"},{"key":"5329_CR14","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.neucom.2020.01.048","volume":"391","author":"M Hao","year":"2020","unstructured":"Hao M, Cao WH, Liu ZT et al (2020) Visual-audio emotion recognition based on multi-task and ensemble learning with multiple features. Neurocomputing 391:42\u201351. https:\/\/doi.org\/10.1016\/j.neucom.2020.01.048","journal-title":"Neurocomputing"},{"key":"5329_CR15","doi-asserted-by":"publisher","unstructured":"Li C, Bao Z, Li L et\u00a0al (2020) Exploring temporal representations by leveraging attention-based bidirectional lstm-rnns for multi-modal emotion recognition. Inform Process & Manag 57(3):102,185. https:\/\/doi.org\/10.1016\/j.ipm.2019.102185","DOI":"10.1016\/j.ipm.2019.102185"},{"key":"5329_CR16","unstructured":"Vaswani A, Shazeer N, Parmar N et al (2017) Attention is all you need. Adv Neural Inf Process Syst 30:5998\u20136008"},{"key":"5329_CR17","doi-asserted-by":"publisher","unstructured":"Jiang J, Chen Z, Lin H et\u00a0al (2020) Divide and conquer: Question-guided spatio-temporal contextual attention for video question answering. In: Proceedings of the AAAI conference on artificial intelligence, pp 11,101\u201311,108, https:\/\/doi.org\/10.1609\/aaai.v34i07.6766","DOI":"10.1609\/aaai.v34i07.6766"},{"key":"5329_CR18","doi-asserted-by":"publisher","first-page":"6977","DOI":"10.1109\/TIP.2020.2996086","volume":"29","author":"J Lee","year":"2020","unstructured":"Lee J, Kim S, Kim S et al (2020) Multi-modal recurrent attention networks for facial expression recognition. IEEE Trans Image Process 29:6977\u20136991. https:\/\/doi.org\/10.1109\/TIP.2020.2996086","journal-title":"IEEE Trans Image Process"},{"key":"5329_CR19","doi-asserted-by":"publisher","first-page":"4367","DOI":"10.1007\/s10489-020-02116-1","volume":"51","author":"Y Chen","year":"2021","unstructured":"Chen Y, Liu L, Phonevilay V et al (2021) Image super-resolution reconstruction based on feature map attention mechanism. Appl Intell 51:4367\u20134380. https:\/\/doi.org\/10.1007\/s10489-020-02116-1","journal-title":"Appl Intell"},{"key":"5329_CR20","doi-asserted-by":"publisher","unstructured":"Antoniadis P, Pikoulis I, Filntisis PP et\u00a0al (2021) An audiovisual and contextual approach for categorical and continuous emotion recognition in-the-wild. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3645\u20133651. https:\/\/doi.org\/10.1109\/ICCVW54120.2021.00407","DOI":"10.1109\/ICCVW54120.2021.00407"},{"key":"5329_CR21","doi-asserted-by":"publisher","first-page":"261","DOI":"10.1016\/j.neunet.2021.03.027","volume":"140","author":"Z Peng","year":"2021","unstructured":"Peng Z, Dang J, Unoki M et al (2021) Multi-resolution modulation-filtered cochleagram feature for lstm-based dimensional emotion recognition from speech. Neural Netw 140:261\u2013273. https:\/\/doi.org\/10.1016\/j.neunet.2021.03.027","journal-title":"Neural Netw"},{"key":"5329_CR22","doi-asserted-by":"publisher","unstructured":"Lee J, Kim S, Kiim S et\u00a0al (2018) Spatiotemporal attention based deep neural networks for emotion recognition. In: 2018 IEEE International conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 1513\u20131517. https:\/\/doi.org\/10.1109\/ICASSP.2018.8461920","DOI":"10.1109\/ICASSP.2018.8461920"},{"issue":"11","key":"5329_CR23","doi-asserted-by":"publisher","first-page":"5321","DOI":"10.1109\/JBHI.2021.3083525","volume":"26","author":"S Liu","year":"2021","unstructured":"Liu S, Wang X, Zhao L et al (2021) 3dcann: A spatio-temporal convolution attention neural network for eeg emotion recognition. IEEE J Biomed Health Inform 26(11):5321\u20135331. https:\/\/doi.org\/10.1109\/JBHI.2021.3083525","journal-title":"IEEE J Biomed Health Inform"},{"key":"5329_CR24","doi-asserted-by":"publisher","unstructured":"Farha YA, Gall J (2019) Ms-tcn: Multi-stage temporal convolutional network for action segmentation. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3575\u20133584. https:\/\/doi.org\/10.1109\/CVPR.2019.00369","DOI":"10.1109\/CVPR.2019.00369"},{"key":"5329_CR25","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/LSP.2021.3063609","volume":"28","author":"M Hu","year":"2021","unstructured":"Hu M, Chu Q, Wang X et al (2021) A two-stage spatiotemporal attention convolution network for continuous dimensional emotion recognition from facial video. IEEE Signal Process Lett 28:698\u2013702. https:\/\/doi.org\/10.1109\/LSP.2021.3063609","journal-title":"IEEE Signal Process Lett"},{"issue":"1","key":"5329_CR26","doi-asserted-by":"publisher","first-page":"5","DOI":"10.1109\/T-AFFC.2011.20","volume":"3","author":"G McKeown","year":"2011","unstructured":"McKeown G, Valstar M, Cowie R et al (2011) The semaine database: Annotated multimodal records of emotionally colored conversations between a person and a limited agent. IEEE Trans Affect Comput 3(1):5\u201317. https:\/\/doi.org\/10.1109\/T-AFFC.2011.20","journal-title":"IEEE Trans Affect Comput"},{"key":"5329_CR27","doi-asserted-by":"publisher","unstructured":"Ringeval F, Sonderegger A, Sauer J et\u00a0al (2013) Introducing the recola multimodal corpus of remote collaborative and affective interactions. In: 2013 10th IEEE international conference and workshops on automatic face and gesture recognition (FG), IEEE, pp 1\u20138. https:\/\/doi.org\/10.1109\/FG.2013.6553805","DOI":"10.1109\/FG.2013.6553805"},{"issue":"3","key":"5329_CR28","doi-asserted-by":"publisher","first-page":"1022","DOI":"10.1109\/TPAMI.2019.2944808","volume":"43","author":"J Kossaifi","year":"2019","unstructured":"Kossaifi J, Walecki R, Panagakis Y et al (2019) Sewa db: A rich database for audio-visual emotion and sentiment research in the wild. IEEE Trans Pattern Anal Mach Intell 43(3):1022\u20131040. https:\/\/doi.org\/10.1109\/TPAMI.2019.2944808","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"5329_CR29","doi-asserted-by":"publisher","unstructured":"Huang Z, Dang T, Cummins N et\u00a0al (2015) An investigation of annotation delay compensation and output-associative fusion for multimodal continuous emotion prediction. In: Proceedings of the 5th International Workshop on Audio\/Visual Emotion Challenge, pp 41\u201348. https:\/\/doi.org\/10.1145\/2808196.2811640","DOI":"10.1145\/2808196.2811640"},{"key":"5329_CR30","doi-asserted-by":"publisher","first-page":"1313","DOI":"10.1109\/TMM.2021.3063612","volume":"24","author":"D Nguyen","year":"2021","unstructured":"Nguyen D, Nguyen DT, Zeng R et al (2021) Deep auto-encoders with sequential learning for multimodal dimensional emotion recognition. IEEE Trans Multimedia 24:1313\u20131324. https:\/\/doi.org\/10.1109\/TMM.2021.3063612","journal-title":"IEEE Trans Multimedia"},{"key":"5329_CR31","doi-asserted-by":"publisher","unstructured":"Chen H, Deng Y, Cheng S et\u00a0al (2019) Efficient spatial temporal convolutional features for audiovisual continuous affect recognition. In: Proceedings of the 9th international on audio\/visual emotion challenge and workshop, pp 19\u201326. https:\/\/doi.org\/10.1145\/3347320.3357690","DOI":"10.1145\/3347320.3357690"},{"key":"5329_CR32","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1016\/j.neucom.2019.09.037","volume":"376","author":"E Pei","year":"2020","unstructured":"Pei E, Jiang D, Sahli H (2020) An efficient model-level fusion approach for continuous affect recognition from audiovisual signals. Neurocomputing 376:42\u201353. https:\/\/doi.org\/10.1016\/j.neucom.2019.09.037","journal-title":"Neurocomputing"},{"key":"5329_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1016\/j.patrec.2021.03.007","volume":"146","author":"L Schoneveld","year":"2021","unstructured":"Schoneveld L, Othmani A, Abdelkawy H (2021) Leveraging recent advances in deep learning for audio-visual emotion recognition. Pattern Recogn Lett 146:1\u20137. https:\/\/doi.org\/10.1016\/j.patrec.2021.03.007","journal-title":"Pattern Recogn Lett"},{"key":"5329_CR34","doi-asserted-by":"publisher","unstructured":"Mao Q, Zhu Q, Rao Q et\u00a0al (2019) Learning hierarchical emotion context for continuous dimensional emotion recognition from video sequences. IEEE Access 7:62,894\u201362,903. https:\/\/doi.org\/10.1109\/ACCESS.2019.2916211","DOI":"10.1109\/ACCESS.2019.2916211"},{"key":"5329_CR35","doi-asserted-by":"crossref","unstructured":"Deng D, Chen Z, Zhou Y et\u00a0al (2020) Mimamo net: Integrating micro-and macro-motion for video emotion recognition. In: Proceedings of the AAAI conference on artificial intelligence, pp 2621\u20132628","DOI":"10.1609\/aaai.v34i03.5646"},{"key":"5329_CR36","doi-asserted-by":"publisher","unstructured":"Singh R, Saurav S, Kumar T et\u00a0al (2023) Facial expression recognition in videos using hybrid cnn & convlstm. Int J Inform Technol pp 1\u201312. https:\/\/doi.org\/10.1007\/s41870-023-01183-0","DOI":"10.1007\/s41870-023-01183-0"},{"key":"5329_CR37","doi-asserted-by":"publisher","unstructured":"Nagrani A, Yang S, Arnab A et\u00a0al (2021) Attention bottlenecks for multimodal fusion. Adv Neural Inform Process Syst 34:14,200\u201314,213. https:\/\/doi.org\/10.48550\/arXiv.2107.00135","DOI":"10.48550\/arXiv.2107.00135"},{"key":"5329_CR38","doi-asserted-by":"crossref","unstructured":"Chen H, Deng Y, Jiang D (2021) Temporal attentive adversarial domain adaption for cross cultural affect recognition. In: Companion publication of the 2021 international conference on multimodal interaction, pp 97\u2013103","DOI":"10.1145\/3461615.3491110"},{"key":"5329_CR39","doi-asserted-by":"publisher","unstructured":"Huang J, Tao J, Liu B et\u00a0al (2020) Multimodal transformer fusion for continuous emotion recognition. In: ICASSP 2020-2020 IEEE International conference on acoustics, speech and signal processing (ICASSP), IEEE, pp 3507\u20133511, https:\/\/doi.org\/10.1109\/ICASSP40776.2020.9053762","DOI":"10.1109\/ICASSP40776.2020.9053762"},{"key":"5329_CR40","doi-asserted-by":"publisher","unstructured":"Wu S, Du Z, Li W et\u00a0al (2019) Continuous emotion recognition in videos by fusing facial expression, head pose and eye gaze. In: 2019 International conference on multimodal interaction, pp 40\u201348, https:\/\/doi.org\/10.1145\/3340555.3353739","DOI":"10.1145\/3340555.3353739"},{"key":"5329_CR41","doi-asserted-by":"publisher","first-page":"46","DOI":"10.1016\/j.inffus.2020.10.011","volume":"68","author":"P Tzirakis","year":"2021","unstructured":"Tzirakis P, Chen J, Zafeiriou S et al (2021) End-to-end multimodal affect recognition in real-world environments. Information Fusion 68:46\u201353. https:\/\/doi.org\/10.1016\/j.inffus.2020.10.011","journal-title":"Information Fusion"},{"key":"5329_CR42","doi-asserted-by":"publisher","unstructured":"Praveen RG, de\u00a0Melo WC, Ullah N et\u00a0al (2022) A joint cross-attention model for audio-visual fusion in dimensional emotion recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 2486\u20132495, https:\/\/doi.org\/10.48550\/arXiv.2203.14779","DOI":"10.48550\/arXiv.2203.14779"},{"key":"5329_CR43","unstructured":"Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. In: International conference on learning representations-workshop"},{"issue":"3","key":"5329_CR44","doi-asserted-by":"publisher","first-page":"565","DOI":"10.1109\/TAFFC.2019.2940224","volume":"12","author":"Z Du","year":"2019","unstructured":"Du Z, Wu S, Huang D et al (2019) Spatio-temporal encoder-decoder fully convolutional network for video-based dimensional emotion recognition. IEEE Trans Affect Comput 12(3):565\u2013578. https:\/\/doi.org\/10.1109\/TAFFC.2019.2940224","journal-title":"IEEE Trans Affect Comput"},{"issue":"105","key":"5329_CR45","doi-asserted-by":"publisher","first-page":"048","DOI":"10.1016\/j.compbiomed.2021.105048","volume":"141","author":"Z He","year":"2022","unstructured":"He Z, Zhong Y, Pan J (2022) An adversarial discriminative temporal convolutional network for eeg-based cross-domain emotion recognition. Comput Biol Med 141(105):048. https:\/\/doi.org\/10.1016\/j.compbiomed.2021.105048","journal-title":"Comput Biol Med"},{"issue":"2","key":"5329_CR46","doi-asserted-by":"publisher","first-page":"190","DOI":"10.1109\/TAFFC.2015.2457417","volume":"7","author":"F Eyben","year":"2015","unstructured":"Eyben F, Scherer KR, Schuller BW et al (2015) The geneva minimalistic acoustic parameter set (gemaps) for voice research and affective computing. IEEE Trans Affect Comput 7(2):190\u2013202. https:\/\/doi.org\/10.1109\/TAFFC.2015.2457417","journal-title":"IEEE Trans Affect Comput"},{"key":"5329_CR47","doi-asserted-by":"crossref","unstructured":"Ruan D, Yan Y, Lai S et\u00a0al (2021) Feature decomposition and reconstruction learning for effective facial expression recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7660\u20137669","DOI":"10.1109\/CVPR46437.2021.00757"},{"key":"5329_CR48","doi-asserted-by":"publisher","unstructured":"Verma S, Wang C, Zhu L et\u00a0al (2019) Deepcu: Integrating both common and unique latent information for multimodal sentiment analysis. In: International joint conference on artificial intelligence, international joint conferences on artificial intelligence organization. https:\/\/doi.org\/10.24963\/ijcai.2019\/503","DOI":"10.24963\/ijcai.2019\/503"},{"issue":"1","key":"5329_CR49","doi-asserted-by":"publisher","first-page":"122","DOI":"10.1109\/TMM.2019.2925966","volume":"22","author":"S Mai","year":"2019","unstructured":"Mai S, Xing S, Hu H (2019) Locally confined modality fusion network with a global perspective for multimodal human affective computing. IEEE Trans Multimed 22(1):122\u2013137. https:\/\/doi.org\/10.1109\/TMM.2019.2925966","journal-title":"IEEE Trans Multimed"},{"issue":"4","key":"5329_CR50","doi-asserted-by":"publisher","first-page":"945","DOI":"10.1109\/TCDS.2020.2976112","volume":"13","author":"Z Gao","year":"2020","unstructured":"Gao Z, Wang X, Yang Y et al (2020) A channel-fused dense convolutional network for eeg-based emotion recognition. IEEE Trans Cogn Dev Syst 13(4):945\u2013954. https:\/\/doi.org\/10.1109\/TCDS.2020.2976112","journal-title":"IEEE Trans Cogn Dev Syst"},{"key":"5329_CR51","doi-asserted-by":"publisher","unstructured":"Ringeval F, Schuller B, Valstar M et\u00a0al (2019) Avec 2019 workshop and challenge: state-of-mind, detecting depression with ai, and cross-cultural affect recognition. In: Proceedings of the 9th international on audio\/visual emotion challenge and workshop, pp 3\u201312. https:\/\/doi.org\/10.1145\/3347320.3357688","DOI":"10.1145\/3347320.3357688"},{"key":"5329_CR52","doi-asserted-by":"publisher","unstructured":"Valstar M, Gratch J, Schuller B et\u00a0al (2016) Avec 2016: Depression, mood, and emotion recognition workshop and challenge. In: Proceedings of the 6th international workshop on audio\/visual emotion challenge, pp 3\u201310. https:\/\/doi.org\/10.1145\/2988257.2988258","DOI":"10.1145\/2988257.2988258"},{"key":"5329_CR53","doi-asserted-by":"publisher","unstructured":"Zhang S, Ding Y, Wei Z et\u00a0al (2021) Continuous emotion recognition with audio-visual leader-follower attentive fusion. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 3567\u20133574, https:\/\/doi.org\/10.48550\/arXiv.2107.01175","DOI":"10.48550\/arXiv.2107.01175"},{"issue":"4","key":"5329_CR54","doi-asserted-by":"publisher","first-page":"1069","DOI":"10.1109\/TAFFC.2019.2917047","volume":"12","author":"S Khorram","year":"2019","unstructured":"Khorram S, McInnis MG, Provost EM (2019) Jointly aligning and predicting continuous emotion annotations. IEEE Trans Affect Comput 12(4):1069\u20131083. https:\/\/doi.org\/10.1109\/TAFFC.2019.2917047","journal-title":"IEEE Trans Affect Comput"},{"key":"5329_CR55","unstructured":"Liu M, Tang J (2021) Audio and video bimodal emotion recognition in social networks based on improved alexnet network and attention mechanism. J Inform Process Syst 17(4):754\u2013771"},{"issue":"1","key":"5329_CR56","doi-asserted-by":"publisher","first-page":"406","DOI":"10.1109\/TAFFC.2021.3062406","volume":"14","author":"A Shukla","year":"2023","unstructured":"Shukla A, Petridis S, Pantic M (2023) Does visual self-supervision improve learning of speech representations for emotion recognition. IEEE Trans Affect Comput 14(1):406\u2013420. https:\/\/doi.org\/10.1109\/TAFFC.2021.3062406","journal-title":"IEEE Trans Affect Comput"},{"key":"5329_CR57","unstructured":"Lucas J, Ghaleb E, Asteriadis S (2020) Deep, dimensional and multimodal emotion recognition using attention mechanisms. In: BNAIC\/BeneLearn 2020, pp 130"},{"key":"5329_CR58","doi-asserted-by":"publisher","unstructured":"Zhao J, Li R, Liang J et\u00a0al (2019) Adversarial domain adaption for multi-cultural dimensional emotion recognition in dyadic interactions. In: Proceedings of the 9th international on audio\/visual emotion challenge and workshop, pp 37\u201345. https:\/\/doi.org\/10.1145\/3347320.3357692","DOI":"10.1145\/3347320.3357692"},{"issue":"3","key":"5329_CR59","doi-asserted-by":"publisher","first-page":"1351","DOI":"10.1007\/s11053-022-10051-w","volume":"31","author":"A Abbaszadeh Shahri","year":"2022","unstructured":"Abbaszadeh Shahri A, Shan C, Larsson S (2022) A novel approach to uncertainty quantification in groundwater table modeling by automated predictive deep learning. Nat Resour Res 31(3):1351\u20131373. https:\/\/doi.org\/10.1007\/s11053-022-10051-w","journal-title":"Nat Resour Res"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05329-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-024-05329-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-024-05329-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,4,3]],"date-time":"2024-04-03T13:12:39Z","timestamp":1712149959000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-024-05329-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":59,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["5329"],"URL":"https:\/\/doi.org\/10.1007\/s10489-024-05329-w","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2]]},"assertion":[{"value":"7 February 2024","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 February 2024","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"We declare that we have no actual or potential conflict of interest including any financial, personal or other relationships with other people or organizations that can inappropriately influence our work.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}]}}