{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,15]],"date-time":"2026-04-15T22:47:53Z","timestamp":1776293273177,"version":"3.50.1"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,11]]},"DOI":"10.1007\/s00371-025-04159-2","type":"journal-article","created":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T14:04:54Z","timestamp":1757513094000},"page":"12325-12337","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal fusion for real-time classroom engagement assessment using YOLOv9 and DeepFace"],"prefix":"10.1007","volume":"41","author":[{"given":"Heng","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanli","family":"Liu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"issue":"9","key":"4159_CR1","doi-asserted-by":"publisher","first-page":"11645","DOI":"10.1007\/s10639-023-12238-x","volume":"29","author":"YJ Wang","year":"2024","unstructured":"Wang, Y.J., Gao, C.L., Ye, X.D.: A data-driven precision teaching intervention mechanism to improve secondary school students\u2019 learning effectiveness[J]. Educ. Inf. Technol. 29(9), 11645\u201311673 (2024)","journal-title":"Educ. Inf. Technol."},{"key":"4159_CR2","doi-asserted-by":"crossref","unstructured":"Xie, P., Jiang, J., Wei, X.: Data-driven precision teaching practice in blended learning[C]. In: Proceedings of the 2023 4th International Conference on Artificial Intelligence and Education (ICAIE 2023). vol. 15, pp. 198. (2023)","DOI":"10.2991\/978-94-6463-242-2_24"},{"issue":"6","key":"4159_CR3","doi-asserted-by":"publisher","first-page":"3559","DOI":"10.1007\/s00530-023-01153-3","volume":"29","author":"N Xie","year":"2023","unstructured":"Xie, N., Liu, Z., Li, Z., et al.: Student engagement detection in online environment using computer vision and multi-dimensional feature fusion[J]. Multimed. Syst. 29(6), 3559\u20133577 (2023)","journal-title":"Multimed. Syst."},{"key":"4159_CR4","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.procs.2024.03.206","volume":"233","author":"A Dey","year":"2024","unstructured":"Dey, A., Anand, A., Samanta, S., et al.: Attention-based AdaptSepCX network for effective student action recognition in online learning[J]. Procedia Comput. Sci. 233, 164\u2013174 (2024)","journal-title":"Procedia Comput. Sci."},{"issue":"1","key":"4159_CR5","doi-asserted-by":"publisher","DOI":"10.1088\/1361-6501\/ad8a80","volume":"36","author":"S Wang","year":"2024","unstructured":"Wang, S., Chen, M., Ratnavelu, K., et al.: Online classroom student engagement analysis based on facial expression recognition using enhanced YOLOv5 for mitigating cyberbullying[J]. Meas. Sci. Technol. 36(1), 015419 (2024)","journal-title":"Meas. Sci. Technol."},{"issue":"35","key":"4159_CR6","doi-asserted-by":"publisher","first-page":"21923","DOI":"10.1007\/s00521-024-10371-3","volume":"36","author":"S Wang","year":"2024","unstructured":"Wang, S., Shibghatullah, A.S., Iqbal, T.J., et al.: A review of multimodal-based emotion recognition techniques for cyberbullying detection in online social media platforms[J]. Neural Comput. Appl. 36(35), 21923\u201321956 (2024)","journal-title":"Neural Comput. Appl."},{"issue":"3","key":"4159_CR7","doi-asserted-by":"publisher","first-page":"171","DOI":"10.1007\/s10489-024-06113-6","volume":"55","author":"S Wang","year":"2025","unstructured":"Wang, S., Ratnavelu, K., Bin Shibghatullah, A.S.: UEFN: Efficient uncertainty estimation fusion network for reliable multimodal sentiment analysis[J]. Appl. Intell. 55(3), 171 (2025)","journal-title":"Appl. Intell."},{"issue":"15","key":"4159_CR8","doi-asserted-by":"publisher","first-page":"9169","DOI":"10.1007\/s00521-025-11076-x","volume":"37","author":"S Wang","year":"2025","unstructured":"Wang, S., Shibghatullah, A.S., Keoy, K.H., et al.: Pedestrian mask-wearing detection based on YOLOv5 and DeepSORT[J]. Neural Comput. Appl. 37(15), 9169\u20139192 (2025)","journal-title":"Neural Comput. Appl."},{"key":"4159_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.imavis.2023.104726","volume":"136","author":"Y Li","year":"2023","unstructured":"Li, Y., Qi, X., Saudagar, A.K.J., et al.: Student behavior recognition for interaction detection in the classroom environment[J]. Image Vis. Comput. 136, 104726 (2023)","journal-title":"Image Vis. Comput."},{"key":"4159_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2023.107706","volume":"206","author":"S Chen","year":"2023","unstructured":"Chen, S., Zou, X., Zhou, X., et al.: Study on fusion clustering and improved YOLOv5 algorithm based on multiple occlusion of Camellia oleifera fruit[J]. Comput. Electron. Agric. 206, 107706 (2023)","journal-title":"Comput. Electron. Agric."},{"issue":"3","key":"4159_CR11","first-page":"840","volume":"17","author":"Q Gao","year":"2023","unstructured":"Gao, Q., He, Z., Jia, X., et al.: Lightweight high-precision pedestrian tracking algorithm in complex occlusion scenarios[J]. KSII Trans. Internet Inf. Syst. (TIIS) 17(3), 840\u2013860 (2023)","journal-title":"KSII Trans. Internet Inf. Syst. (TIIS)"},{"issue":"15","key":"4159_CR12","doi-asserted-by":"publisher","first-page":"9281","DOI":"10.3390\/su14159281","volume":"14","author":"X Chen","year":"2022","unstructured":"Chen, X., Jia, Y., Tong, X., et al.: Research on pedestrian detection and deepsort tracking in front of intelligent vehicle based on deep learning[J]. Sustainability 14(15), 9281 (2022)","journal-title":"Sustainability"},{"issue":"3","key":"4159_CR13","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1007\/s00138-023-01396-0","volume":"34","author":"J Liu","year":"2023","unstructured":"Liu, J., Mu, X., Liu, Z., et al.: Human skeleton behavior recognition model based on multi-object pose estimation with spatiotemporal semantics[J]. Mach. Vis. Appl. 34(3), 44 (2023)","journal-title":"Mach. Vis. Appl."},{"issue":"6","key":"4159_CR14","first-page":"1191","volume":"11","author":"Z Zhou","year":"2022","unstructured":"Zhou, Z., Qin, X.: Research on students\u2019 classroom behavior recognition based on human-object interaction[J]. Softw. Eng. Appl. 11(6), 1191\u20131203 (2022)","journal-title":"Softw. Eng. Appl."},{"key":"4159_CR15","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.125392","volume":"260","author":"Z Wang","year":"2025","unstructured":"Wang, Z., Li, L., Zeng, C., et al.: SLBDetection-Net: towards closed-set and open-set student learning behavior detection in smart classroom of K-12 education[J]. Expert Syst. Appl. 260, 125392 (2025)","journal-title":"Expert Syst. Appl."},{"key":"4159_CR16","first-page":"55","volume":"2","author":"Z Wang","year":"2022","unstructured":"Wang, Z., Shen, C., Zhao, C., Liu, X., Chen, J.: Recognition of classroom learning behaviors based on the fusion of human pose estimation and object detection[J]. J. East China Norm. Univ. (Nat. Sci. Ed.) 2, 55\u201366 (2022)","journal-title":"J. East China Norm. Univ. (Nat. Sci. Ed.)"},{"issue":"1","key":"4159_CR17","doi-asserted-by":"publisher","first-page":"5816","DOI":"10.1038\/s41598-024-56505-4","volume":"14","author":"R Wang","year":"2024","unstructured":"Wang, R., Chen, S., Tian, G., et al.: Post-secondary classroom teaching quality evaluation using small object detection model[J]. Sci. Rep. 14(1), 5816 (2024)","journal-title":"Sci. Rep."},{"key":"4159_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2024.128711","volume":"612","author":"T Liu","year":"2025","unstructured":"Liu, T., Wang, M., Yang, B., et al.: ESERNet: learning spectrogram structure relationship for effective speech emotion recognition with swin transformer in classroom discourse analysis[J]. Neurocomputing 612, 128711 (2025)","journal-title":"Neurocomputing"},{"issue":"4","key":"4159_CR19","doi-asserted-by":"publisher","first-page":"4069","DOI":"10.1007\/s10639-022-11370-4","volume":"28","author":"I Lasri","year":"2023","unstructured":"Lasri, I., Riadsolh, A., Elbelkacemi, M.: Facial emotion recognition of deaf and hard-of-hearing students for engagement detection using deep learning[J]. Educ. Inf. Technol. 28(4), 4069\u20134092 (2023)","journal-title":"Educ. Inf. Technol."},{"key":"4159_CR20","doi-asserted-by":"publisher","first-page":"6821","DOI":"10.1109\/TMM.2022.3214776","volume":"25","author":"J Zhu","year":"2022","unstructured":"Zhu, J., Zhang, Q., Fei, L., et al.: FFFN: frame-by-frame feedback fusion network for video super-resolution[J]. IEEE Trans. Multimed. 25, 6821\u20136835 (2022)","journal-title":"IEEE Trans. Multimed."},{"key":"4159_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110847","volume":"156","author":"Z Liu","year":"2024","unstructured":"Liu, Z., Cai, L., Yang, W., et al.: Sentiment analysis based on text information enhancement and multimodal feature fusion[J]. Pattern Recogn. 156, 110847 (2024)","journal-title":"Pattern Recogn."},{"issue":"1","key":"4159_CR22","doi-asserted-by":"publisher","first-page":"12","DOI":"10.1186\/s40561-023-00231-3","volume":"10","author":"E Dimitriadou","year":"2023","unstructured":"Dimitriadou, E., Lanitis, A.: A critical evaluation, challenges, and future perspectives of using artificial intelligence and emerging technologies in smart classrooms[J]. Smart Learn. Environ. 10(1), 12 (2023)","journal-title":"Smart Learn. Environ."},{"key":"4159_CR23","doi-asserted-by":"crossref","unstructured":"Wang, Y., Wang, Z., Li, C., et al.: A multimodal feature fusion-based method for individual depression detection on sina weibo[C]. In: 2020 IEEE 39th International Performance Computing and Communications Conference (IPCCC). IEEE, pp. 1-8 (2020)","DOI":"10.1109\/IPCCC50635.2020.9391501"},{"key":"4159_CR24","doi-asserted-by":"crossref","unstructured":"Xue, Z., Marculescu, R.: Dynamic multimodal fusion[C]. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2575-2584 (2023)","DOI":"10.1109\/CVPRW59228.2023.00256"},{"issue":"2","key":"4159_CR25","doi-asserted-by":"publisher","DOI":"10.1088\/2516-1091\/acc2fe","volume":"5","author":"C Cui","year":"2023","unstructured":"Cui, C., Yang, H., Wang, Y., et al.: Deep multimodal fusion of image and non-image data in disease diagnosis and prognosis: a review[J]. Prog. Biomed. Eng. 5(2), 022001 (2023)","journal-title":"Prog. Biomed. Eng."},{"key":"4159_CR26","unstructured":"Zhang, Q., Wei, Y., Han, Z., et al.: Multimodal fusion on low-quality data: a comprehensive survey[J]. arXiv preprint arXiv:2404.18947, (2024)"},{"key":"4159_CR27","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","volume":"91","author":"A Gandhi","year":"2023","unstructured":"Gandhi, A., Adhvaryu, K., Poria, S., et al.: Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions[J]. Inf. Fus. 91, 424\u2013444 (2023)","journal-title":"Inf. Fus."},{"issue":"7","key":"4159_CR28","doi-asserted-by":"publisher","first-page":"7975","DOI":"10.1007\/s10639-022-11485-8","volume":"28","author":"Z Luo","year":"2023","unstructured":"Luo, Z., Zheng, C., Gong, J., et al.: 3DLIM: intelligent analysis of students\u2019 learning interest by using multimodal fusion technology[J]. Educ. Inf. Technol. 28(7), 7975\u20137995 (2023)","journal-title":"Educ. Inf. Technol."},{"key":"4159_CR29","doi-asserted-by":"crossref","unstructured":"Xiang, A., Qi, Z., Wang, H., et al.: A multimodal fusion network for student emotion recognition based on transformer and tensor product[C]. In: 2024 IEEE 2nd International Conference on Sensors, Electronics and Computer Engineering (ICSECE). IEEE. pp. 1-4 (2024)","DOI":"10.1109\/ICSECE61636.2024.10729485"},{"key":"4159_CR30","doi-asserted-by":"crossref","unstructured":"Luo, Y., Ye, Z., Lyu, R.: Detecting student depression on Weibo based on various multimodal fusion methods[C]. In: 4th International Conference on Signal Processing and Machine Learning (CONF-SPML 2024). vol. 13077, pp. 130770M (2024)","DOI":"10.1117\/12.3027177"},{"issue":"18","key":"4159_CR31","doi-asserted-by":"publisher","first-page":"3909","DOI":"10.3390\/electronics12183909","volume":"12","author":"J Song","year":"2023","unstructured":"Song, J., Chen, H., Li, C., et al.: MIFM: multimodal information fusion model for educational exercises[J]. Electronics 12(18), 3909 (2023)","journal-title":"Electronics"},{"key":"4159_CR32","doi-asserted-by":"crossref","unstructured":"Yun, T., Lim, H., Lee, J., et al.: TelME: Teacher-leading multimodal fusion network for emotion recognition in conversation[J]. arXiv preprint arXiv:2401.12987, (2024)","DOI":"10.18653\/v1\/2024.naacl-long.5"},{"key":"4159_CR33","doi-asserted-by":"publisher","first-page":"2226","DOI":"10.1109\/TMM.2022.3144890","volume":"25","author":"N Jiang","year":"2022","unstructured":"Jiang, N., Sheng, B., Li, P., et al.: Photohelper: portrait photographing guidance via deep feature retrieval and fusion[J]. IEEE Trans. Multimed. 25, 2226\u20132238 (2022)","journal-title":"IEEE Trans. Multimed."},{"issue":"23","key":"4159_CR34","doi-asserted-by":"publisher","first-page":"63291","DOI":"10.1007\/s11042-023-18032-8","volume":"83","author":"X Miao","year":"2024","unstructured":"Miao, X., Zhang, X., Zhang, H.: Low-rank tensor fusion and self-supervised multi-task multimodal sentiment analysis[J]. Multimed. Tools Appl. 83(23), 63291\u201363308 (2024)","journal-title":"Multimed. Tools Appl."},{"key":"4159_CR35","doi-asserted-by":"crossref","unstructured":"Hu Shuqin, Raga, R.C.: A deep learning model for student sentiment analysis on course reviews[J]. IEEE Access, (2024)","DOI":"10.1109\/ACCESS.2024.3463793"},{"key":"4159_CR36","doi-asserted-by":"crossref","unstructured":"Li, M., Zhou, S., Chen, Y., et al.: EduCross: dual adversarial bipartite hypergraph learning for cross-modal retrieval in multimodal educational slides[J]. Inf. Fus. 109, 102428 (2024)","DOI":"10.1016\/j.inffus.2024.102428"},{"issue":"1","key":"4159_CR37","doi-asserted-by":"publisher","first-page":"304","DOI":"10.1007\/s12559-022-10083-7","volume":"15","author":"C Yan","year":"2023","unstructured":"Yan, C., Liu, J., Liu, W., et al.: Sentiment analysis and topic mining using a novel deep attention-based parallel dual-channel model for online course reviews[J]. Cogn. Comput. 15(1), 304\u2013322 (2023)","journal-title":"Cogn. Comput."},{"issue":"4","key":"4159_CR38","doi-asserted-by":"publisher","first-page":"280","DOI":"10.1016\/j.vrih.2023.06.002","volume":"6","author":"H Zhang","year":"2024","unstructured":"Zhang, H., Wei, Z., Liu, G., et al.: MKEAH: multimodal knowledge extraction and accumulation based on hyperplane embedding for knowledge-based visual question answering[J]. Virtual Real. Intell. Hardw. 6(4), 280\u2013291 (2024)","journal-title":"Virtual Real. Intell. Hardw."},{"issue":"2","key":"4159_CR39","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2230","volume":"35","author":"D Bellenger","year":"2024","unstructured":"Bellenger, D., Chen, M., Xu, Z.: Facial emotion recognition with a reduced feature set for video game and metaverse avatars[J]. Comput. Anim. Virtual Worlds 35(2), e2230 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"issue":"3","key":"4159_CR40","doi-asserted-by":"publisher","DOI":"10.1002\/cav.2268","volume":"35","author":"Y Bao","year":"2024","unstructured":"Bao, Y., Liu, X., Qi, Y., et al.: Adaptive information fusion network for multi?modal personality recognition[J]. Comput. Anim. Virtual Worlds 35(3), e2268 (2024)","journal-title":"Comput. Anim. Virtual Worlds"},{"key":"4159_CR41","unstructured":"Xiang, Y., Zhang, A., Guo, J., et al.: Adaptive multimodal prompt-tuning model for few-shot multimodal sentiment analysis[J]. Int. J. Mach. Learn. Cybern. 1-13 (2025)"},{"issue":"8","key":"4159_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s11227-025-07364-x","volume":"81","author":"S Liu","year":"2025","unstructured":"Liu, S., Zhao, H., Chen, Y., et al.: CU-SEMLP: all-MLP-based multimodal interaction model for multimodal sentiment analysis[J]. J. Supercomput. 81(8), 1\u201326 (2025)","journal-title":"J. Supercomput."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04159-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-04159-2\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-04159-2.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T08:46:05Z","timestamp":1760085965000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-04159-2"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"references-count":42,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2025,11]]}},"alternative-id":["4159"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-04159-2","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"9 June 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 August 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 September 2025","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 declare no Conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}