{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,2,21]],"date-time":"2025-02-21T03:17:41Z","timestamp":1740107861298,"version":"3.37.3"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"6","license":[{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T00:00:00Z","timestamp":1643846400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["B200202205"],"award-info":[{"award-number":["B200202205"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["41876097","61872199"],"award-info":[{"award-number":["41876097","61872199"]}],"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":["61501170"],"award-info":[{"award-number":["61501170"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Soft Comput"],"published-print":{"date-parts":[[2022,3]]},"DOI":"10.1007\/s00500-022-06772-y","type":"journal-article","created":{"date-parts":[[2022,2,3]],"date-time":"2022-02-03T02:02:36Z","timestamp":1643853756000},"page":"2807-2818","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Relational structure predictive neural architecture search for multimodal fusion"],"prefix":"10.1007","volume":"26","author":[{"given":"Xiao","family":"Yao","sequence":"first","affiliation":[]},{"given":"Fang","family":"Li","sequence":"additional","affiliation":[]},{"given":"Yifeng","family":"Zeng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,2,3]]},"reference":[{"key":"6772_CR1","doi-asserted-by":"crossref","unstructured":"Acharya D, Huang Z, Paudel DP, Gool LV (2018) Covariance Pooling for Facial Expression Recognition 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) IEEE","DOI":"10.1109\/CVPRW.2018.00077"},{"key":"6772_CR2","unstructured":"Andrew G, Arora R, Bilmes J, Livescu K (2013) Deep canonical correlation analysis In International Conference on Machine Learning 1247\u20131255"},{"key":"6772_CR3","unstructured":"Arevalo J, Solorio T, Montes-y G\u00f3mez M, Gonz\u00e1lez FA (2017) Gated multimodal units for information fusion ICLR Worshop"},{"key":"6772_CR4","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis T, Ahuja C, Morency LP (2018) Multimodal machine learning: A survey and taxonomy. IEEE Trans Pattern Anal Mach Intell 41(2):423\u2013443","DOI":"10.1109\/TPAMI.2018.2798607"},{"issue":"2","key":"6772_CR5","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1007\/s00521-012-1228-3","volume":"24","author":"M Bejani","year":"2014","unstructured":"Bejani M, Gharavian Davood (2014) Audiovisual emotion recognition using anova feature selection method and multi-classifier neural networks. Neural Comput Appl 24(2):399\u2013412","journal-title":"Neural Comput Appl"},{"issue":"2","key":"6772_CR6","first-page":"123","volume":"24","author":"L Breiman","year":"1996","unstructured":"Breiman L (1996) Bagging predicators. Mach Learn 24(2):123\u2013140","journal-title":"Mach Learn"},{"key":"6772_CR7","unstructured":"Chen K (2019) The research of multimodal fusing based emotion recognition"},{"key":"6772_CR8","doi-asserted-by":"crossref","unstructured":"Chen M, Wang S, Liang PP, Baltru\u0161aitis Tadas, Zadeh A, Morency LP (2018) Multimodal Sentiment Analysis with Word-Level Fusion and Reinforcement Learning In Proceedings of the 19th ACM International Conference on Multimodal Interaction ACM","DOI":"10.1145\/3136755.3136801"},{"issue":"4","key":"6772_CR9","first-page":"499","volume":"31","author":"J Cohen","year":"1988","unstructured":"Cohen J, Cohen JW, Cohen J, Cohen J, Cohen J, Cohen J et al (1988) Statistical power analysis for the behavioral science. Technometrics 31(4):499\u2013500","journal-title":"Technometrics"},{"key":"6772_CR10","doi-asserted-by":"crossref","unstructured":"Ejegwa P, Wen S, Feng Y, Zhang W, Tang N (2021) Novel Pythagorean fuzzy correlation measures via Pythagorean fuzzy deviation, variance and covariance with applications to pattern recognition and career placement. IEEE Trans Fuzzy Syst (99):1\u20131","DOI":"10.1109\/TFUZZ.2021.3063794"},{"key":"6772_CR11","doi-asserted-by":"crossref","unstructured":"Fan Y, Lu X, Li D, et al (2016) Video-based emotion recognition using CNN-RNN and C3D hybrid networks Proceedings of the 18th ACM International Conference on Multimodal Interaction 445\u2013450","DOI":"10.1145\/2993148.2997632"},{"key":"6772_CR12","first-page":"874","volume":"339","author":"Y Feng","year":"2018","unstructured":"Feng Y, Yang X, Song Q, Cao J (2018) Synchronization of memristive neural networks with mixed delays via quantized intermittent control. Appl Math Comput 339:874\u2013887","journal-title":"Appl Math Comput"},{"key":"6772_CR13","doi-asserted-by":"crossref","unstructured":"Feng Y, Zhang W, Xiong J, Li H, Rutkowski L (2020) Event-Triggering Interaction Scheme for Discrete-Time Decentralized Optimization With Nonuniform Step Sizes. IEEE Trans Cybern. https:\/\/doi.org\/10.1109\/TCYB.2019.2963330","DOI":"10.1109\/TCYB.2019.2963330"},{"key":"6772_CR14","unstructured":"Goodfellow I, Warde-Farley D, Mirza M, Courville A, Bengio Y (2013) Maxout networks. In: International conference on machine learning, Proceedings of Machine Learning Research, pp 1319\u20131327"},{"key":"6772_CR15","doi-asserted-by":"crossref","unstructured":"Guo Y, Zhang L, Hu Y, He X, Gao J (2016) Ms-celeb-1m: a dataset and benchmark for large-scale face recognition","DOI":"10.2352\/ISSN.2470-1173.2016.11.IMAWM-463"},{"issue":"8","key":"6772_CR16","doi-asserted-by":"publisher","first-page":"860","DOI":"10.3390\/rs9080860","volume":"9","author":"M Kang","year":"2017","unstructured":"Kang M, Ji K, Leng X, Lin Z (2017) Contextual region-based convolutional neural network with multilayer fusion for sar ship detection. Remote Sens 9(8):860","journal-title":"Remote Sens"},{"key":"6772_CR17","doi-asserted-by":"crossref","unstructured":"Kim DH, Song BC (2017) Multi-modal emotion recognition using semi-supervised learning and multiple neural networks in the wild In Proceedings of the 19th ACM International Conference on Multimodal Interaction 529\u2013535","DOI":"10.1145\/3136755.3143005"},{"key":"6772_CR18","doi-asserted-by":"crossref","unstructured":"Li F, Neverova N, Wolf C, Taylor G (2016) Modout: learning to fuse modalities via stochastic regularization. J Comput Vision Imag Syst 2(1)","DOI":"10.15353\/vsnl.v2i1.103"},{"key":"6772_CR19","unstructured":"Liu H, Simonyan K, Yang Y (2018) Darts: differentiable architecture search"},{"key":"6772_CR20","doi-asserted-by":"crossref","unstructured":"Liu Y, Yuan Z, Zhou W, Li H (2019) Spatial and temporal mutual promotion for video-based person re-identification Proceedings of the AAAI Conference on Artificial Intelligence 33:8786\u20138793","DOI":"10.1609\/aaai.v33i01.33018786"},{"key":"6772_CR21","doi-asserted-by":"crossref","unstructured":"Liu C, Zoph B, Shlens J, Hua W, Fei-Fei L, Yuille A, Huang J, Murphy K (2018) Progressive neural architecture search ECCV","DOI":"10.1007\/978-3-030-01246-5_2"},{"key":"6772_CR22","unstructured":"Luo R, Tan X, Wang R, Qin T, Chen E, Liu TY (2020) Semi-supervised neural architecture search"},{"key":"6772_CR23","unstructured":"Luo R, Tian F, Qin T, Liu T-Y (2018) Neural architecture optimization arXiv preprint arXiv:1808.07233"},{"issue":"2","key":"6772_CR24","doi-asserted-by":"publisher","first-page":"277","DOI":"10.1007\/s11042-009-0344-2","volume":"49","author":"M Mansoorizadeh","year":"2010","unstructured":"Mansoorizadeh M, Charkari NM (2010) Multimodal information fusion application to human emotion recognition from face and speech. Multimedia Tools Appl 49(2):277\u2013297","journal-title":"Multimedia Tools Appl"},{"key":"6772_CR25","unstructured":"Mikolov T, Sutskever I, Chen K, Corrado GS, Dean J (2013) Distributed representations of words and phrases and their compositionality. In: Advances in neural information processing systems, pp 3111\u20133119"},{"issue":"8","key":"6772_CR26","doi-asserted-by":"publisher","first-page":"1692","DOI":"10.1109\/TPAMI.2015.2461544","volume":"38","author":"N Neverova","year":"2014","unstructured":"Neverova N, Wolf C, Taylor G, Nebout F (2014) Moddrop: adaptive multi-modal gesture recognition. IEEE Transactions Pattern Anal Mach Intell 38(8):1692\u20131706","journal-title":"IEEE Transactions Pattern Anal Mach Intell"},{"key":"6772_CR27","doi-asserted-by":"crossref","unstructured":"Onasanya BO, Wen S, et al (2021) Fuzzy coefficient of impulsive intensity in a nonlinear impulsive control system. Neural Process Lett 53:4639\u20134657","DOI":"10.1007\/s11063-021-10614-7"},{"key":"6772_CR28","doi-asserted-by":"crossref","unstructured":"Ouyang X, Kawaai S, Goh EGH, Shen S, Huang DY (2017) Audio-visual emotion recognition using deep transfer learning and multiple temporal models In the 19th ACM International Conference ACM","DOI":"10.1145\/3136755.3143012"},{"key":"6772_CR29","unstructured":"P\u00e9rez-R\u00faa JM, Baccouche M, Pateux S (2018) Efficient progressive neural architecture search BMVC"},{"key":"6772_CR30","unstructured":"Pham H, Guan MY, Zoph B, Le QV, Dean J (2018) Efficient neural architecture search via parameter sharing ICML"},{"key":"6772_CR31","doi-asserted-by":"publisher","first-page":"438","DOI":"10.1007\/s10489-016-0823-x","volume":"46","author":"RR Sarvestani","year":"2017","unstructured":"Sarvestani RR, Boostani R (2017) Ff-skpcca: kernel probabilistic canonical correlation analysis. Appl Intell 46:438\u2013454","journal-title":"Appl Intell"},{"key":"6772_CR32","doi-asserted-by":"crossref","unstructured":"Schuller B, Vlasenko B, Eyben F, Rigoll G, Wendemuth A (2010) Acoustic emotion recognition: a benchmark comparison of performances IEEE Workshop on Automatic Speech Recognition & Understanding IEEE","DOI":"10.1109\/ASRU.2009.5372886"},{"key":"6772_CR33","unstructured":"Shi XJ, Chen Z, Wang H, Yeung DY, Wong WK, Woo WC (2015) Convolutional LSTM network: a machine learning approach for precipitation nowcasting. Adv Neural Inform Process Syst 802\u2013810"},{"key":"6772_CR34","unstructured":"Simonyan K, Zisserman A (2015) Two-stream convolutional networks for action recognition in videos. In: Proceedings of the Neural Information Processing Systems (NIPS)"},{"key":"6772_CR35","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"key":"6772_CR36","doi-asserted-by":"crossref","unstructured":"Snoek CG, Worring M, Smeulders AW (2005) Early versus late fusion in semantic video analysis ACMM","DOI":"10.1145\/1101149.1101236"},{"key":"6772_CR37","doi-asserted-by":"crossref","unstructured":"Vielzeuf V, Pateux S, Jurie F (2017) Temporal multimodal fusion for video emotion classification in the wild In Proceedings of the 19th ACM International Conference on Multimodal Interaction 569\u2013576","DOI":"10.1145\/3136755.3143011"},{"key":"6772_CR38","doi-asserted-by":"crossref","unstructured":"Yang X, Molchanov P, Kautz J (2016) Multilayer and Multimodal Fusion of Deep Neural Networks for Video Classification In Proceedings of the 2016 ACM on Multimedia Conference ACM 978\u2013987","DOI":"10.1145\/2964284.2964297"},{"key":"6772_CR39","doi-asserted-by":"crossref","unstructured":"Yao A, et al. (2016) HoloNet: towards robust emotion recognition in the wild Proceedings of the 18th ACM International Conference on Multimodal Interaction","DOI":"10.1145\/2993148.2997639"},{"key":"6772_CR40","doi-asserted-by":"crossref","unstructured":"Zhalehpour S, Onder O, Akhtar Z, Erdem CE (2016) BAUM-1: a spontaneous audio-visual face database of affective and mental states. IEEE Trans Affect Comput 8(3):300\u2013313","DOI":"10.1109\/TAFFC.2016.2553038"},{"issue":"10","key":"6772_CR41","doi-asserted-by":"publisher","first-page":"3030","DOI":"10.1109\/TCSVT.2017.2719043","volume":"28","author":"S Zhang","year":"2017","unstructured":"Zhang S, Zhang S, Huang T, Gao W, Tian Q (2017) Learning affective features with a hybrid deep model for audio-visual emotion recognition. IEEE Trans Circuit Syst Video Technol 28(10):3030\u20133043","journal-title":"IEEE Trans Circuit Syst Video Technol"},{"key":"6772_CR42","unstructured":"Zoph B, Le QV (2016) Neural architecture search with reinforcement learning ICLR"}],"container-title":["Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-022-06772-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00500-022-06772-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00500-022-06772-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,3,1]],"date-time":"2022-03-01T12:18:55Z","timestamp":1646137135000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00500-022-06772-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,2,3]]},"references-count":42,"journal-issue":{"issue":"6","published-print":{"date-parts":[[2022,3]]}},"alternative-id":["6772"],"URL":"https:\/\/doi.org\/10.1007\/s00500-022-06772-y","relation":{},"ISSN":["1432-7643","1433-7479"],"issn-type":[{"type":"print","value":"1432-7643"},{"type":"electronic","value":"1433-7479"}],"subject":[],"published":{"date-parts":[[2022,2,3]]},"assertion":[{"value":"10 January 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"3 February 2022","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical approval"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":4,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}