{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,27]],"date-time":"2026-07-27T10:10:24Z","timestamp":1785147024835,"version":"3.55.0"},"reference-count":67,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T00:00:00Z","timestamp":1706400000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T00:00:00Z","timestamp":1706400000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s00530-023-01244-1","type":"journal-article","created":{"date-parts":[[2024,1,28]],"date-time":"2024-01-28T05:02:43Z","timestamp":1706418163000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":12,"title":["Bag of states: a non-sequential approach to video-based engagement measurement"],"prefix":"10.1007","volume":"30","author":[{"given":"Ali","family":"Abedi","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chinchu","family":"Thomas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dinesh Babu","family":"Jayagopi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shehroz S.","family":"Khan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,28]]},"reference":[{"issue":"COVID19\u2013S4","key":"1244_CR1","first-page":"27","volume":"36","author":"K Mukhtar","year":"2020","unstructured":"Mukhtar, K., Javed, K., Arooj, M., Sethi, A.: Advantages, limitations and recommendations for online learning during covid-19 pandemic era. Pak. J. Med. Sci. 36(COVID19\u2013S4), 27 (2020)","journal-title":"Pak. J. Med. Sci."},{"issue":"3","key":"1244_CR2","first-page":"45","volume":"10","author":"DTH Dung","year":"2020","unstructured":"Dung, D.T.H.: The advantages and disadvantages of virtual learning. IOSR J. Res. Method Educ. 10(3), 45\u201348 (2020)","journal-title":"IOSR J. Res. Method Educ."},{"issue":"2","key":"1244_CR3","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1109\/TAFFC.2021.3127692","volume":"14","author":"\u00d6 S\u00fcmer","year":"2021","unstructured":"S\u00fcmer, \u00d6., Goldberg, P., D\u2019Mello, S., Gerjets, P., Trautwein, U., Kasneci, E.: Multimodal engagement analysis from facial videos in the classroom. IEEE Trans. Affect. Comput. 14(2), 1012\u20131027 (2021)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"1244_CR4","first-page":"1","volume":"11","author":"JA Gray","year":"2016","unstructured":"Gray, J.A., DiLoreto, M.: The effects of student engagement, student satisfaction, and perceived learning in online learning environments. Int. J. Educ. Leadership Prep. 11(1), 1 (2016)","journal-title":"Int. J. Educ. Leadership Prep."},{"key":"1244_CR5","volume-title":"The Challenges of Defining and Measuring Student Engagement in Science","author":"GM Sinatra","year":"2015","unstructured":"Sinatra, G.M., Heddy, B.C., Lombardi, D.: The Challenges of Defining and Measuring Student Engagement in Science. Taylor & Francis, Abingdon (2015)"},{"issue":"3\/4","key":"1244_CR6","doi-asserted-by":"crossref","first-page":"129","DOI":"10.1504\/IJLT.2009.028804","volume":"4","author":"B Woolf","year":"2009","unstructured":"Woolf, B., Burleson, W., Arroyo, I., Dragon, T., Cooper, D., Picard, R.: Affect-aware tutors: recognising and responding to student affect. Int. J. Learn. Technol. 4(3\/4), 129\u2013164 (2009)","journal-title":"Int. J. Learn. Technol."},{"issue":"2","key":"1244_CR7","doi-asserted-by":"crossref","first-page":"145","DOI":"10.1016\/j.learninstruc.2011.10.001","volume":"22","author":"S D\u2019Mello","year":"2012","unstructured":"D\u2019Mello, S., Graesser, A.: Dynamics of affective states during complex learning. Learn. Instr. 22(2), 145\u2013157 (2012)","journal-title":"Learn. Instr."},{"key":"1244_CR8","unstructured":"Fredricks, J., McColskey, W., Meli, J., Mordica, J., Montrosse, B., Mooney, K.: Measuring Student Engagement in Upper Elementary Through High School: A Description of 21 Instruments. Issues & answers. Rel 2011-no. 098. Regional Educational Laboratory Southeast (2011)"},{"key":"1244_CR9","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s41239-020-00238-7","volume":"18","author":"LM Nkomo","year":"2021","unstructured":"Nkomo, L.M., Daniel, B.K., Butson, R.J.: Synthesis of student engagement with digital technologies: a systematic review of the literature. Int. J. Educ. Technol. High. Educ. 18, 1\u201326 (2021)","journal-title":"Int. J. Educ. Technol. High. Educ."},{"issue":"2","key":"1244_CR10","doi-asserted-by":"crossref","first-page":"104","DOI":"10.1080\/00461520.2017.1281747","volume":"52","author":"S D\u2019Mello","year":"2017","unstructured":"D\u2019Mello, S., Dieterle, E., Duckworth, A.: Advanced, analytic, automated (AAA) measurement of engagement during learning. Educ. Psychol. 52(2), 104\u2013123 (2017)","journal-title":"Educ. Psychol."},{"key":"1244_CR11","doi-asserted-by":"crossref","unstructured":"Bosch, N.: Detecting student engagement: human versus machine. In: Proceedings of the 2016 Conference on User Modeling Adaptation and Personalization, pp. 317\u2013320 (2016)","DOI":"10.1145\/2930238.2930371"},{"issue":"1","key":"1244_CR12","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40561-018-0080-z","volume":"6","author":"M Dewan","year":"2019","unstructured":"Dewan, M., Murshed, M., Lin, F.: Engagement detection in online learning: a review. Smart Learn. Environ. 6(1), 1\u201320 (2019)","journal-title":"Smart Learn. Environ."},{"issue":"1","key":"1244_CR13","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s40561-022-00212-y","volume":"9","author":"SN Karimah","year":"2022","unstructured":"Karimah, S.N., Hasegawa, S.: Automatic engagement estimation in smart education\/learning settings: a systematic review of engagement definitions, datasets, and methods. Smart Learn. Environ. 9(1), 1\u201348 (2022)","journal-title":"Smart Learn. Environ."},{"key":"1244_CR14","doi-asserted-by":"crossref","DOI":"10.1155\/2012\/528781","volume":"2012","author":"A Belle","year":"2012","unstructured":"Belle, A., Hargraves, R.H., Najarian, K.: An automated optimal engagement and attention detection system using electrocardiogram. Comput. Math. Methods Med. 2012, 528781 (2012)","journal-title":"Comput. Math. Methods Med."},{"issue":"1","key":"1244_CR15","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.amjsurg.2020.06.027","volume":"221","author":"CM Pugh","year":"2021","unstructured":"Pugh, C.M., Hashimoto, D.A., Korndorffer, J.R., Jr.: The what? how? and who? of video based assessment. Am. J. Surg. 221(1), 13\u201318 (2021)","journal-title":"Am. J. Surg."},{"key":"1244_CR16","unstructured":"Khan, S.S., Abedi, A., Colella, T.: Inconsistencies in measuring student engagement in virtual learning\u2013a critical review. arXiv preprint arXiv:2208.04548 (2022)"},{"key":"1244_CR17","doi-asserted-by":"crossref","DOI":"10.1016\/j.physd.2019.132306","volume":"404","author":"A Sherstinsky","year":"2020","unstructured":"Sherstinsky, A.: Fundamentals of recurrent neural network (RNN) and long short-term memory (LSTM) network. Physica D 404, 132306 (2020)","journal-title":"Physica D"},{"key":"1244_CR18","doi-asserted-by":"crossref","first-page":"651","DOI":"10.1109\/TAFFC.2019.2945014","volume":"13","author":"X Chen","year":"2019","unstructured":"Chen, X., Niu, L., Veeraraghavan, A., Sabharwal, A.: Faceengage: robust estimation of gameplay engagement from user-contributed (youtube) videos. IEEE Trans. Affect. Comput. 13, 651\u2013665 (2019)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1244_CR19","doi-asserted-by":"crossref","unstructured":"Wu, J., Yang, B., Wang, Y., Hattori, G.: Advanced multi-instance learning method with multi-features engineering and conservative optimization for engagement intensity prediction. In: Proceedings of the 2020 International Conference on Multimodal Interaction, pp. 777\u2013783 (2020)","DOI":"10.1145\/3382507.3417959"},{"issue":"3","key":"1244_CR20","first-page":"107","volume":"11","author":"X Ma","year":"2021","unstructured":"Ma, X., Xu, M., Dong, Y., Sun, Z.: Automatic student engagement in online learning environment based on neural turing machine. Int. J. Inf. Educ. Technol. 11(3), 107\u2013111 (2021)","journal-title":"Int. J. Inf. Educ. Technol."},{"key":"1244_CR21","doi-asserted-by":"crossref","unstructured":"Copur, O., Nak\u0131p, M., Scardapane, S., Slowack, J.: Engagement detection with multi-task training in e-learning environments. In: International Conference on Image Analysis and Processing, pp. 411\u2013422. Springer (2022)","DOI":"10.1007\/978-3-031-06433-3_35"},{"key":"1244_CR22","first-page":"1","volume":"11","author":"A Abedi","year":"2023","unstructured":"Abedi, A., Khan, S.S.: Affect-driven ordinal engagement measurement from video. Multimed. Tools Appl. 11, 1\u201320 (2023)","journal-title":"Multimed. Tools Appl."},{"key":"1244_CR23","doi-asserted-by":"crossref","first-page":"3535","DOI":"10.1007\/s11760-023-02578-z","volume":"7","author":"A Abedi","year":"2023","unstructured":"Abedi, A., Khan, S.: Detecting disengagement in virtual learning as an anomaly using temporal convolutional network autoencoder. Signal Image Video Process. 7, 3535\u20133543 (2023)","journal-title":"Signal Image Video Process."},{"key":"1244_CR24","unstructured":"Bai, S., Kolter, J.Z., Koltun, V.: An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv preprint arXiv:1803.01271 (2018)"},{"key":"1244_CR25","doi-asserted-by":"crossref","unstructured":"Thomas, C., Nair, N., Jayagopi, D.B.: Predicting engagement intensity in the wild using temporal convolutional network. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, pp. 604\u2013610 (2018)","DOI":"10.1145\/3242969.3264984"},{"key":"1244_CR26","doi-asserted-by":"crossref","DOI":"10.1016\/j.caeai.2022.100079","volume":"3","author":"C Thomas","year":"2022","unstructured":"Thomas, C., Sarma, K.P., Gajula, S.S., Jayagopi, D.B.: Automatic prediction of presentation style and student engagement from videos. Comput. Educ. Artif. Intell. 3, 100079 (2022)","journal-title":"Comput. Educ. Artif. Intell."},{"key":"1244_CR27","unstructured":"Gupta, A., D\u2019Cunha, A., Awasthi, K., Balasubramanian, V.: Daisee: Towards user engagement recognition in the wild. arXiv preprint arXiv:1609.01885 (2016)"},{"key":"1244_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, H., Xiao, X., Huang, T., Liu, S., Xia, Y., Li, J.: An novel end-to-end network for automatic student engagement recognition. In: 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC), pp. 342\u2013345 (2019). IEEE","DOI":"10.1109\/ICEIEC.2019.8784507"},{"key":"1244_CR29","doi-asserted-by":"crossref","unstructured":"Abedi, A., Khan, S.S.: Improving state-of-the-art in detecting student engagement with resnet and tcn hybrid network. In: 2021 18th Conference on Robots and Vision (CRV), pp. 151\u2013157 (2021). IEEE","DOI":"10.1109\/CRV52889.2021.00028"},{"key":"1244_CR30","doi-asserted-by":"crossref","first-page":"13803","DOI":"10.1007\/s10489-022-03200-4","volume":"52","author":"NK Mehta","year":"2022","unstructured":"Mehta, N.K., Prasad, S.S., Saurav, S., Saini, R., Singh, S.: Three-dimensional densenet self-attention neural network for automatic detection of student\u2019s engagement. Appl. Intell. 52, 13803\u201313823 (2022)","journal-title":"Appl. Intell."},{"key":"1244_CR31","unstructured":"Ai, X., Sheng, V.S., Li, C.: Class-attention video transformer for engagement intensity prediction. arXiv preprint arXiv:2208.07216 (2022)"},{"key":"1244_CR32","doi-asserted-by":"crossref","unstructured":"Galke, L., Scherp, A.: Bag-of-words vs. graph vs. sequence in text classification: Questioning the necessity of text-graphs and the surprising strength of a wide mlp. In: Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Vol. 1: Long Papers), pp. 4038\u20134051 (2022)","DOI":"10.18653\/v1\/2022.acl-long.279"},{"issue":"6","key":"1244_CR33","doi-asserted-by":"crossref","first-page":"634","DOI":"10.1016\/j.bspc.2013.06.004","volume":"8","author":"J Wang","year":"2013","unstructured":"Wang, J., Liu, P., She, M.F., Nahavandi, S., Kouzani, A.: Bag-of-words representation for biomedical time series classification. Biomed. Signal Process. Control 8(6), 634\u2013644 (2013)","journal-title":"Biomed. Signal Process. Control"},{"issue":"10","key":"1244_CR34","doi-asserted-by":"crossref","first-page":"6609","DOI":"10.1007\/s10489-020-02139-8","volume":"51","author":"J Liao","year":"2021","unstructured":"Liao, J., Liang, Y., Pan, J.: Deep facial spatiotemporal network for engagement prediction in online learning. Appl. Intell. 51(10), 6609\u20136621 (2021)","journal-title":"Appl. Intell."},{"key":"1244_CR35","doi-asserted-by":"crossref","first-page":"99573","DOI":"10.1109\/ACCESS.2022.3206779","volume":"10","author":"T Selim","year":"2022","unstructured":"Selim, T., Elkabani, I., Abdou, M.A.: Students engagement level detection in online e-learning using hybrid efficientnetb7 together with tcn, lstm, and bi-lstm. IEEE Access 10, 99573\u201399583 (2022)","journal-title":"IEEE Access"},{"issue":"16","key":"1244_CR36","doi-asserted-by":"crossref","first-page":"8007","DOI":"10.3390\/app12168007","volume":"12","author":"Y Hu","year":"2022","unstructured":"Hu, Y., Jiang, Z., Zhu, K.: An optimized cnn model for engagement recognition in an e-learning environment. Appl. Sci. 12(16), 8007 (2022)","journal-title":"Appl. Sci."},{"key":"1244_CR37","doi-asserted-by":"crossref","unstructured":"Mohamad\u00a0Nezami, O., Dras, M., Hamey, L., Richards, D., Wan, S., Paris, C.: Automatic recognition of student engagement using deep learning and facial expression. In: Joint European Conference on Machine Learning and Knowledge Discovery in Databases, pp. 273\u2013289 (2019). Springer","DOI":"10.1007\/978-3-030-46133-1_17"},{"issue":"1","key":"1244_CR38","doi-asserted-by":"crossref","first-page":"86","DOI":"10.1109\/TAFFC.2014.2316163","volume":"5","author":"J Whitehill","year":"2014","unstructured":"Whitehill, J., Serpell, Z., Lin, Y.-C., Foster, A., Movellan, J.R.: The faces of engagement: automatic recognition of student engagement from facial expressions. IEEE Trans. Affect. Comput. 5(1), 86\u201398 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1244_CR39","doi-asserted-by":"crossref","unstructured":"Booth, B.M., Ali, A.M., Narayanan, S.S., Bennett, I., Farag, A.A.: Toward active and unobtrusive engagement assessment of distance learners. In: 2017 Seventh International Conference on Affective Computing and Intelligent Interaction (ACII), pp. 470\u2013476 (2017). IEEE","DOI":"10.1109\/ACII.2017.8273641"},{"key":"1244_CR40","doi-asserted-by":"crossref","unstructured":"Kaur, A., Mustafa, A., Mehta, L., Dhall, A.: Prediction and localization of student engagement in the wild. In: 2018 Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20138 (2018). IEEE","DOI":"10.1109\/DICTA.2018.8615851"},{"key":"1244_CR41","doi-asserted-by":"crossref","unstructured":"Fedotov, D., Perepelkina, O., Kazimirova, E., Konstantinova, M., Minker, W.: Multimodal approach to engagement and disengagement detection with highly imbalanced in-the-wild data. In: Proceedings of the Workshop on Modeling Cognitive Processes from Multimodal Data, pp. 1\u20139 (2018)","DOI":"10.1145\/3279810.3279842"},{"key":"1244_CR42","doi-asserted-by":"crossref","unstructured":"Cao, Z., Simon, T., Wei, S.-E., Sheikh, Y.: Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7291\u20137299 (2017)","DOI":"10.1109\/CVPR.2017.143"},{"key":"1244_CR43","doi-asserted-by":"crossref","unstructured":"Niu, X., Han, H., Zeng, J., Sun, X., Shan, S., Huang, Y., Yang, S., Chen, X.: Automatic engagement prediction with gap feature. In: Proceedings of the 20th ACM International Conference on Multimodal Interaction, pp. 599\u2013603 (2018)","DOI":"10.1145\/3242969.3264982"},{"key":"1244_CR44","doi-asserted-by":"crossref","unstructured":"Huang, T., Mei, Y., Zhang, H., Liu, S., Yang, H.: Fine-grained engagement recognition in online learning environment. In: 2019 IEEE 9th International Conference on Electronics Information and Emergency Communication (ICEIEC), pp. 338\u2013341 (2019). IEEE","DOI":"10.1109\/ICEIEC.2019.8784559"},{"issue":"2","key":"1244_CR45","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1109\/TAFFC.2015.2457413","volume":"7","author":"SK D\u2019Mello","year":"2015","unstructured":"D\u2019Mello, S.K.: On the influence of an iterative affect annotation approach on inter-observer and self-observer reliability. IEEE Trans. Affect. Comput. 7(2), 136\u2013149 (2015)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"1","key":"1244_CR46","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1186\/s13640-017-0228-8","volume":"2017","author":"J Zaletelj","year":"2017","unstructured":"Zaletelj, J., Ko\u0161ir, A.: Predicting students\u2019 attention in the classroom from kinect facial and body features. EURASIP J. Image Video Process. 2017(1), 1\u201312 (2017)","journal-title":"EURASIP J. Image Video Process."},{"key":"1244_CR47","doi-asserted-by":"crossref","unstructured":"Ma, J., Jiang, X., Xu, S., Qin, X.: Hierarchical temporal multi-instance learning for video-based student learning engagement assessment. In: IJCAI, pp. 2782\u20132789 (2021)","DOI":"10.24963\/ijcai.2021\/383"},{"issue":"2","key":"1244_CR48","doi-asserted-by":"crossref","first-page":"1696","DOI":"10.1109\/TAFFC.2021.3086118","volume":"14","author":"S Karumbaiah","year":"2021","unstructured":"Karumbaiah, S., Baker, R.B., Ocumpaugh, J., Andres, A.: A re-analysis and synthesis of data on affect dynamics in learning. IEEE Trans. Affect. Comput. 14(2), 1696\u20131710 (2021)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1244_CR49","unstructured":"D\u2019Mello, S., Graesser, A., et al.: Monitoring affective trajectories during complex learning. In: Proceedings of the Annual Meeting of the Cognitive Science Society, vol. 29 (2007)"},{"key":"1244_CR50","doi-asserted-by":"crossref","unstructured":"d Baker, R.S., Rodrigo, M., Mercedes, T., Xolocotzin, U.E.: The dynamics of affective transitions in simulation problem-solving environments. In: International Conference on Affective Computing and Intelligent Interaction, pp. 666\u2013677 (2007). Springer","DOI":"10.1007\/978-3-540-74889-2_58"},{"issue":"10","key":"1244_CR51","first-page":"2405","volume":"8","author":"G Lebanon","year":"2007","unstructured":"Lebanon, G., Mao, Y., Dillon, J.: The locally weighted bag of words framework for document representation. J. Mach. Learn. Res. 8(10), 2405\u20132441 (2007)","journal-title":"J. Mach. Learn. Res."},{"issue":"3","key":"1244_CR52","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","volume":"79","author":"JC Niebles","year":"2008","unstructured":"Niebles, J.C., Wang, H., Fei-Fei, L.: Unsupervised learning of human action categories using spatial\u2013temporal words. Int. J. Comput. Vis. 79(3), 299\u2013318 (2008)","journal-title":"Int. J. Comput. Vis."},{"key":"1244_CR53","doi-asserted-by":"crossref","unstructured":"Bettadapura, V., Schindler, G., Pl\u00f6tz, T., Essa, I.: Augmenting bag-of-words: Data-driven discovery of temporal and structural information for activity recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2619\u20132626 (2013)","DOI":"10.1109\/CVPR.2013.338"},{"issue":"21","key":"1244_CR54","doi-asserted-by":"crossref","first-page":"6380","DOI":"10.3390\/s20216380","volume":"20","author":"D Govender","year":"2020","unstructured":"Govender, D., Tapamo, J.-R.: Spatio-temporal scale coded bag-of-words. Sensors 20(21), 6380 (2020)","journal-title":"Sensors"},{"key":"1244_CR55","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2021.108263","volume":"122","author":"L Kook","year":"2022","unstructured":"Kook, L., Herzog, L., Hothorn, T., D\u00fcrr, O., Sick, B.: Deep and interpretable regression models for ordinal outcomes. Pattern Recogn. 122, 108263 (2022)","journal-title":"Pattern Recogn."},{"issue":"1","key":"1244_CR56","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1038\/s41598-020-64999-x","volume":"10","author":"C Ranti","year":"2020","unstructured":"Ranti, C., Jones, W., Klin, A., Shultz, S.: Blink rate patterns provide a reliable measure of individual engagement with scene content. Sci. Rep. 10(1), 1\u201310 (2020)","journal-title":"Sci. Rep."},{"key":"1244_CR57","doi-asserted-by":"crossref","unstructured":"Baltrusaitis, T., Zadeh, A., Lim, Y.C., Morency, L.-P.: Openface 2.0: facial behavior analysis toolkit. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 59\u201366 (2018). IEEE","DOI":"10.1109\/FG.2018.00019"},{"issue":"1","key":"1244_CR58","first-page":"53","volume":"57","author":"S Aslan","year":"2017","unstructured":"Aslan, S., Mete, S.E., Okur, E., Oktay, E., Alyuz, N., Genc, U.E., Stanhill, D., Esme, A.A.: Human expert labeling process (help): towards a reliable higher-order user state labeling process and tool to assess student engagement. Educ. Technol. 57(1), 53\u201359 (2017). http:\/\/www.jstor.org\/stable\/44430540","journal-title":"Educ. Technol."},{"key":"1244_CR59","unstructured":"Lugaresi, C., Tang, J., Nash, H., McClanahan, C., Uboweja, E., Hays, M., Zhang, F., Chang, C.-L., Yong, M.G., Lee, J., et al.: Mediapipe: a framework for building perception pipelines. arXiv preprint arXiv:1906.08172 (2019)"},{"issue":"1","key":"1244_CR60","doi-asserted-by":"crossref","first-page":"42","DOI":"10.1038\/s42256-020-00280-0","volume":"3","author":"A Toisoul","year":"2021","unstructured":"Toisoul, A., Kossaifi, J., Bulat, A., Tzimiropoulos, G., Pantic, M.: Estimation of continuous valence and arousal levels from faces in naturalistic conditions. Nat. Mach. Intell. 3(1), 42\u201350 (2021)","journal-title":"Nat. Mach. Intell."},{"issue":"1","key":"1244_CR61","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1109\/TAFFC.2017.2740923","volume":"10","author":"A Mollahosseini","year":"2017","unstructured":"Mollahosseini, A., Hasani, B., Mahoor, M.H.: Affectnet: a database for facial expression, valence, and arousal computing in the wild. IEEE Trans. Affect. Comput. 10(1), 18\u201331 (2017)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1244_CR62","first-page":"1","volume-title":"Advances in neural information processing systems","author":"A Paszke","year":"2019","unstructured":"Paszke, A., Gross, S., Massa, F., Lerer, A., Bradbury, J., Chanan, G., Killeen, T., Lin, Z., Gimelshein, N., Antiga, L., et al.: Pytorch: An imperative style, high-performance deep learning library. In: Wallach, H., Larochelle, H., Beygelzimer, A., d'Alch\u00e9-Buc, F., Fox, E., Garnett, R. (eds.) Advances in neural information processing systems, vol. 32, pp. 1\u201312. Curran Associates Inc. (2019)"},{"key":"1244_CR63","first-page":"2825","volume":"12","author":"F Pedregosa","year":"2011","unstructured":"Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Prettenhofer, P., Weiss, R., Dubourg, V., et al.: Scikit-learn: machine learning in python. J. Mach. Learn. Res. 12, 2825\u20132830 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"1244_CR64","doi-asserted-by":"crossref","first-page":"10349","DOI":"10.1109\/ACCESS.2022.3143990","volume":"10","author":"SS Khan","year":"2022","unstructured":"Khan, S.S., Mishra, P.K., Javed, N., Ye, B., Newman, K., Mihailidis, A., Iaboni, A.: Unsupervised deep learning to detect agitation from videos in people with dementia. IEEE Access 10, 10349\u201310358 (2022)","journal-title":"IEEE Access"},{"key":"1244_CR65","doi-asserted-by":"publisher","DOI":"10.1002\/9781118445112.stat04876","volume-title":"Mcnemar Test","author":"PA Lachenbruch","year":"2014","unstructured":"Lachenbruch, P.A.: Mcnemar Test. Statistics reference online, John Wiley & Sons Ltd, Wiley StatsRef (2014). https:\/\/doi.org\/10.1002\/9781118445112.stat04876"},{"issue":"03","key":"1244_CR66","doi-asserted-by":"publisher","first-page":"2621","DOI":"10.1609\/aaai.v34i03.5646","volume":"34","author":"D Deng","year":"2020","unstructured":"Deng, D., Chen, Z., Zhou, Y., Shi, B.: Mimamo net: integrating micro- and macro-motion for video emotion recognition. Proc. AAAI Conf. Artif. Intell. 34(03), 2621\u20132628 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i03.5646","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"1","key":"1244_CR67","doi-asserted-by":"crossref","first-page":"185","DOI":"10.1111\/j.1541-0420.2005.00389.x","volume":"62","author":"B Rosner","year":"2006","unstructured":"Rosner, B., Glynn, R.J., Lee, M.L.: The Wilcoxon signed rank test for paired comparisons of clustered data. Biometrics, Oxford University Press, 62(1), 185\u2013192 (2006)","journal-title":"Biometrics"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01244-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01244-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01244-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T06:22:09Z","timestamp":1707891729000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01244-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,28]]},"references-count":67,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1244"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01244-1","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,28]]},"assertion":[{"value":"9 March 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"28 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no relevant financial or non-financial interests to disclose. The authors declare no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"47"}}