{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,9]],"date-time":"2026-07-09T15:25:07Z","timestamp":1783610707150,"version":"3.55.0"},"reference-count":45,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T00:00:00Z","timestamp":1748736000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100005645","name":"B\u1ed9 Gi\u00e1o d\u1ee5c v\u00e0 \u00d0\u00e0o t\u1ea1o","doi-asserted-by":"publisher","award":["B2023-BKA-09"],"award-info":[{"award-number":["B2023-BKA-09"]}],"id":[{"id":"10.13039\/501100005645","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int. J. Mach. Learn. & Cyber."],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s13042-025-02695-w","type":"journal-article","created":{"date-parts":[[2025,6,1]],"date-time":"2025-06-01T09:09:19Z","timestamp":1748768959000},"page":"7913-7937","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A method for continuous student activity recognition from classroom videos"],"prefix":"10.1007","volume":"16","author":[{"given":"Phuong-Dung","family":"Nguyen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ngoc-Trang","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Khanh-Huyen","family":"Bui","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hong-Quan","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huu-Quynh","family":"Nguyen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Thi-Lan","family":"Le","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,6,1]]},"reference":[{"key":"2695_CR1","doi-asserted-by":"publisher","unstructured":"Alruwais N, Zakariah M (2024) 01. Student recognition and activity monitoring in e-classes using deep learning in higher education. IEEE Access\u00a0PP: 1\u20131. https:\/\/doi.org\/10.1109\/ACCESS.2024.3354981","DOI":"10.1109\/ACCESS.2024.3354981"},{"key":"2695_CR2","doi-asserted-by":"publisher","first-page":"5457","DOI":"10.1109\/TIP.2020.2984373","volume":"29","author":"P Barra","year":"2020","unstructured":"Barra P, Barra S, Bisogni C, De Marsico M, Nappi M (2020) Web-shaped model for head pose estimation: An approach for best exemplar selection. IEEE Trans Image Process 29:5457\u20135468. https:\/\/doi.org\/10.1109\/TIP.2020.2984373","journal-title":"IEEE Trans Image Process"},{"key":"2695_CR3","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2008\/246309","volume":"2008","author":"K Bernardin","year":"2008","unstructured":"Bernardin K, Stiefelhagen R (2008) Evaluating multiple object tracking performance: The clear mot metrics. EURASIP Journal on Image and Video Processing 2008:1\u201310","journal-title":"EURASIP Journal on Image and Video Processing"},{"key":"2695_CR4","doi-asserted-by":"crossref","unstructured":"Bewley A, Ge Z, Ott L, Ramos F, Upcroft B (2016) Simple online and realtime tracking. In 2016 IEEE international conference on image processing (ICIP), pp. 3464\u20133468. IEEE","DOI":"10.1109\/ICIP.2016.7533003"},{"key":"2695_CR5","doi-asserted-by":"crossref","unstructured":"B\u00fchler B, Hou R, Bozkir E, Goldberg P, Gerjets P, Trautwein U, Kasneci E (2023) Automated hand-raising detection in classroom videos: A view-invariant and occlusion-robust machine learning approach. In International Conference on Artificial Intelligence in Education, pp. 102\u2013113. Springer","DOI":"10.1007\/978-3-031-36272-9_9"},{"key":"2695_CR6","doi-asserted-by":"crossref","unstructured":"Cao J, Pang J, Weng X, Khirodkar R, Kitani K (2023). Observation-centric sort: Rethinking sort for robust multi-object tracking. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp. 9686\u20139696","DOI":"10.1109\/CVPR52729.2023.00934"},{"key":"2695_CR7","doi-asserted-by":"crossref","unstructured":"Carion N, Massa F, Synnaeve G, Usunier N, Kirillov A, Zagoruyko S (2020) End-to-end object detection with transformers. In European conference on computer vision, pp. 213\u2013229. Springer","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"2695_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2022.108075","volume":"101","author":"B Che","year":"2022","unstructured":"Che B, Li X, Sun Y, Yang F, Liu P, Lu W (2022) A database of students\u2019 spontaneous actions in the real classroom environment. Comput Electr Eng 101:108075","journal-title":"Comput Electr Eng"},{"issue":"14","key":"2695_CR9","doi-asserted-by":"publisher","first-page":"4632","DOI":"10.3390\/s24144632","volume":"24","author":"J Chen","year":"2024","unstructured":"Chen J, Wang M, Wang L, Huang F (2024) Student motivation analysis based on raising-hand videos. Sensors 24(14):4632","journal-title":"Sensors"},{"key":"2695_CR10","doi-asserted-by":"publisher","first-page":"8725","DOI":"10.1109\/TMM.2023.3240881","volume":"25","author":"Y Du","year":"2023","unstructured":"Du Y, Zhao Z, Song Y, Zhao Y, Su F, Gong T, Meng H (2023) Strongsort: Make deepsort great again. IEEE Trans Multimedia 25:8725\u20138737. https:\/\/doi.org\/10.1109\/TMM.2023.3240881","journal-title":"IEEE Trans Multimedia"},{"key":"2695_CR11","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2020.102991","volume":"197\u2013198","author":"D Freire-Obreg\u00f3n","year":"2020","unstructured":"Freire-Obreg\u00f3n D, Castrill\u00f3n-Santana M, Barra P, Bisogni C, Nappi M (2020) An attention recurrent model for human cooperation detection. Comput Vis Image Underst 197\u2013198:102991. https:\/\/doi.org\/10.1016\/j.cviu.2020.102991","journal-title":"Comput Vis Image Underst"},{"key":"2695_CR12","doi-asserted-by":"publisher","unstructured":"F\u00fctterer T, Goldberg P, B\u00fchler B, Sikimi\u0107 V, Trautwein U, Gerjets P, St\u00fcrmer K, Kasneci E (2023) 12. Artificial intelligence in classroom management: A systematic review on educational purposes, technical implementations, and ethical considerations. https:\/\/doi.org\/10.31219\/osf.io\/wfazn","DOI":"10.31219\/osf.io\/wfazn"},{"key":"2695_CR13","doi-asserted-by":"crossref","unstructured":"Girshick R (2015) Fast R-CNN. In Proceedings of the IEEE international conference on computer vision, pp. 1440\u20131448","DOI":"10.1109\/ICCV.2015.169"},{"key":"2695_CR14","doi-asserted-by":"crossref","unstructured":"Ismail I, Aloshi J (2025) 01. Data Privacy in AI- Driven Education An In-Depth Exploration Into the Data Privacy Concerns and Potential Solutions, pp. 223\u2013252","DOI":"10.4018\/979-8-3693-5443-8.ch008"},{"key":"2695_CR15","doi-asserted-by":"crossref","unstructured":"Jesna J, Narayanan AS, Bijlani K (2016). Automatic hand raise detection by analyzing the edge structures. In International Conference on Emerging Research in Computing, Information, Communication and Applications, pp. 171\u2013180. Springer","DOI":"10.1007\/978-981-10-4741-1_16"},{"key":"2695_CR16","unstructured":"Jocher G (2022) YOLOv5 using the PyTorch framework. https:\/\/github.com\/ultralytics\/yolov5. Accessed: 2022-07-22"},{"key":"2695_CR17","doi-asserted-by":"crossref","unstructured":"K\u00f6p\u00fckl\u00fc O, Gunduz A, Kose, N, Rigoll G (2019) Real-time hand gesture detection and classification using convolutional neural networks. In 2019 14th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2019), pp. 1\u20138. IEEE","DOI":"10.1109\/FG.2019.8756576"},{"key":"2695_CR18","unstructured":"K\u00f6p\u00fckl\u00fc O, Wei X, Rigoll G (2019). You only watch once: A unified cnn architecture for real-time spatiotemporal action localization. ArXiv\u00a0abs\/1911.06644"},{"issue":"02","key":"2695_CR19","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1142\/S2196888822500397","volume":"10","author":"TH Le","year":"2023","unstructured":"Le TH, Tran HN, Nguyen PD, Nguyen HQ, Nguyen TB, Tran TH, Vu H, Tran TT, Le TL (2023) Spatial and temporal hand-raising recognition from classroom videos using locality, relative position-aware non-local networks and hand tracking. Vietnam Journal of Computer Science 10(02):243\u2013271","journal-title":"Vietnam Journal of Computer Science"},{"key":"2695_CR20","doi-asserted-by":"crossref","unstructured":"Lea C, Flynn MD, Vidal R, Reiter A, Hager GD (2017) Temporal convolutional networks for action segmentation and detection. In proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 156\u2013165","DOI":"10.1109\/CVPR.2017.113"},{"key":"2695_CR21","doi-asserted-by":"crossref","unstructured":"Li W, Jiang F, Shen R (2019) Sleep gesture detection in classroom monitor system. In ICASSP 2019-2019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 7640\u20137644. IEEE","DOI":"10.1109\/ICASSP.2019.8683116"},{"key":"2695_CR22","doi-asserted-by":"crossref","unstructured":"Liao W, Xu, W, Kong S, Ahmad F, Liu W (2019) A two-stage method for hand-raising gesture recognition in classroom. In Proceedings of the 2019 8th International Conference on Educational and Information Technology, pp. 38\u201344","DOI":"10.1145\/3318396.3318437"},{"issue":"16","key":"2695_CR23","doi-asserted-by":"publisher","first-page":"5314","DOI":"10.3390\/s21165314","volume":"21","author":"FC Lin","year":"2021","unstructured":"Lin FC, Ngo HH, Dow CR, Lam KH, Le HL (2021) Student behavior recognition system for the classroom environment based on skeleton pose estimation and person detection. Sensors 21(16):5314","journal-title":"Sensors"},{"key":"2695_CR24","doi-asserted-by":"crossref","unstructured":"Liu K, Chen B, Chen L, Xu Y, Lin L, Gao F, Zhao Y (2023) Eduaction: A college student action dataset for classroom attention estimation. In Advanced Intelligent Computing Technology and Applications: 19th International Conference, ICIC 2023, Zhengzhou, China, August 10-13, 2023, Proceedings, Part IV, Berlin, Heidelberg, pp. 237-248. Springer-Verlag","DOI":"10.1007\/978-981-99-4752-2_20"},{"key":"2695_CR25","doi-asserted-by":"crossref","unstructured":"Liu T, Jiang F, Shen R (2020) Fast and accurate hand-raising gesture detection in classroom. international conference on neural information processing: 232\u2013239","DOI":"10.1007\/978-3-030-63820-7_26"},{"key":"2695_CR26","doi-asserted-by":"crossref","unstructured":"Nazar\u00e9 TS, Ponti M (2013) Hand-raising gesture detection with lienhart-maydt method in videoconference and distance learning. In Iberoamerican Congress on Pattern Recognition, pp. 512\u2013519. Springer","DOI":"10.1007\/978-3-642-41827-3_64"},{"key":"2695_CR27","doi-asserted-by":"crossref","unstructured":"Nguyen PD, Le XV, Le VD, Nguyen HL, Le, NT, Kieu TD, Tran TH, Nguyen HQ, Le TL (2023) Skeleton-based student activities recognition from classroom videos. In International Conference on Advances in Information and Communication Technology, pp. 292\u2013299. Springer","DOI":"10.1007\/978-3-031-50818-9_32"},{"key":"2695_CR28","doi-asserted-by":"crossref","unstructured":"Nguyen PD, Nguyen HQ, Nguyen TB, Le TL, Tran TH, Vu H, Huu QN (2022) A new dataset and systematic evaluation of deep learning models for student activity recognition from classroom videos. In 2022 International Conference on Multimedia Analysis and Pattern Recognition (MAPR), pp. 1\u20136. IEEE","DOI":"10.1109\/MAPR56351.2022.9924673"},{"key":"2695_CR29","doi-asserted-by":"crossref","unstructured":"Nguyen QT, Binh HT, Bui TD, NT PD (2019) Student postures and gestures recognition system for adaptive learning improvement. In 2019 6th NAFOSTED Conference on Information and Computer Science (NICS), pp. 494\u2013499. IEEE","DOI":"10.1109\/NICS48868.2019.9023896"},{"key":"2695_CR30","doi-asserted-by":"crossref","unstructured":"Nguyen TT, Kawanishi Y, Komamizu T, Ide I (2024) Action selection learning for multi-label multi-view action recognition. In Proceedings of the 6th ACM International Conference on Multimedia in Asia, MMAsia \u201924, New York, NY, USA. Association for Computing Machinery","DOI":"10.1145\/3696409.3700211"},{"issue":"3","key":"2695_CR31","doi-asserted-by":"publisher","first-page":"279","DOI":"10.3390\/electronics10030279","volume":"10","author":"R Padilla","year":"2021","unstructured":"Padilla R, Passos WL, Dias TL, Netto SL, da Silva EA (2021) A comparative analysis of object detection metrics with a companion open-source toolkit. Electronics 10(3):279","journal-title":"Electronics"},{"issue":"17","key":"2695_CR32","doi-asserted-by":"publisher","first-page":"5699","DOI":"10.3390\/s21175699","volume":"21","author":"V Sharma","year":"2021","unstructured":"Sharma V, Gupta M, Kumar A, Mishra D (2021) Edunet: a new video dataset for understanding human activity in the classroom environment. Sensors 21(17):5699","journal-title":"Sensors"},{"key":"2695_CR33","doi-asserted-by":"crossref","unstructured":"Shrivastava A, Gupta A., Girshick R (2016) Training region-based object detectors with online hard example mining. In Proceedings of the IEEE conference on computer vision and pattern recognition, pp. 761\u2013769","DOI":"10.1109\/CVPR.2016.89"},{"key":"2695_CR34","doi-asserted-by":"publisher","first-page":"69","DOI":"10.1016\/j.neucom.2019.05.031","volume":"359","author":"J Si","year":"2019","unstructured":"Si J, Lin J, Jiang F, Shen R (2019) Hand-raising gesture detection in real classrooms using improved r-fcn. Neurocomputing 359:69\u201376","journal-title":"Neurocomputing"},{"key":"2695_CR35","doi-asserted-by":"publisher","first-page":"8335","DOI":"10.1007\/s00521-020-05587-y","volume":"33","author":"B Sun","year":"2021","unstructured":"Sun B, Wu Y, Zhao K, He J, Yu L, Yan H, Luo A (2021) Student class behavior dataset: a video dataset for recognizing, detecting, and captioning students\u2019 behaviors in classroom scenes. Neural Comput Appl 33:8335\u20138354","journal-title":"Neural Comput Appl"},{"key":"2695_CR36","doi-asserted-by":"crossref","unstructured":"Wang Z, Jiang F, Shen R (2019) An effective yawn behavior detection method in classroom. In International conference on neural information processing, pp. 430\u2013441. Springer","DOI":"10.1007\/978-3-030-36708-4_35"},{"key":"2695_CR37","doi-asserted-by":"crossref","unstructured":"Wojke N, Bewley A, Paulus D (2017) Simple online and realtime tracking with a deep association metric. In 2017 IEEE International Conference on Image Processing (ICIP), pp. 3645\u20133649","DOI":"10.1109\/ICIP.2017.8296962"},{"issue":"1","key":"2695_CR38","doi-asserted-by":"publisher","first-page":"14006","DOI":"10.1038\/s41598-024-63934-8","volume":"14","author":"L Xiao","year":"2024","unstructured":"Xiao L, Luo K, Liu J, Foroughi A (2024) A hybrid deep approach to recognizing student activity and monitoring health physique based on accelerometer data from smartphones. Sci Rep 14(1):14006","journal-title":"Sci Rep"},{"issue":"11","key":"2695_CR39","doi-asserted-by":"publisher","first-page":"5205","DOI":"10.3390\/s23115205","volume":"23","author":"S Zhang","year":"2023","unstructured":"Zhang S, Liu H, Sun C, Wu X, Wen P, Yu F, Zhang J (2023) Msta-slowfast: A student behavior detector for classroom environments. Sensors 23(11):5205","journal-title":"Sensors"},{"key":"2695_CR40","doi-asserted-by":"crossref","unstructured":"Zhao J, Zhang, Y, Li X, Chen H, Shuai B, Xu M, Liu C, Kundu K, Xiong Y, Modolo D, Marsic I, Snoek CG, Tighe J (2022) Tuber: Tubelet transformer for video action detection. In 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 13588\u201313597","DOI":"10.1109\/CVPR52688.2022.01323"},{"key":"2695_CR41","doi-asserted-by":"crossref","unstructured":"Zhao Y, Lv W, Xu S, Wei J, Wang G, Dang Q, Liu Y, Chen J (2024) Detrs beat yolos on real-time object detection. In 2024 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 16965\u201316974","DOI":"10.1109\/CVPR52733.2024.01605"},{"key":"2695_CR42","doi-asserted-by":"crossref","unstructured":"Zheng R, Jiang F, Shen R (2020a) Gesturedet: Real-time student gesture analysis with multi-dimensional attention-based detector. In IJCAI, pp. 680\u2013686","DOI":"10.24963\/ijcai.2020\/95"},{"key":"2695_CR43","doi-asserted-by":"crossref","unstructured":"Zheng R, Jiang F, Shen R (2020b) Intelligent student behavior analysis system for real classrooms. In ICASSP 2020-2020 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 9244\u20139248. IEEE","DOI":"10.1109\/ICASSP40776.2020.9053457"},{"key":"2695_CR44","unstructured":"Zhou H, Jiang F, Shen R (2018) Who are raising their hands? hand-raiser seeking based on object detection and pose estimation. In Asian Conference on Machine Learning, pp. 470\u2013485. PMLR"},{"key":"2695_CR45","doi-asserted-by":"crossref","unstructured":"Zhou W, Qian Y, Jie Z, Ma L (2023) Multi view action recognition for distracted driver behavior localization. In 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 5375\u20135380","DOI":"10.1109\/CVPRW59228.2023.00567"}],"container-title":["International Journal of Machine Learning and Cybernetics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02695-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s13042-025-02695-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s13042-025-02695-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,15]],"date-time":"2025-10-15T16:59:36Z","timestamp":1760547576000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s13042-025-02695-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,1]]},"references-count":45,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["2695"],"URL":"https:\/\/doi.org\/10.1007\/s13042-025-02695-w","relation":{},"ISSN":["1868-8071","1868-808X"],"issn-type":[{"value":"1868-8071","type":"print"},{"value":"1868-808X","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,6,1]]},"assertion":[{"value":"18 September 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"25 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 June 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}