{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,27]],"date-time":"2026-10-27T18:12:48Z","timestamp":1793124768247,"version":"4.5.0"},"reference-count":47,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,12,1]],"date-time":"2026-12-01T00:00:00Z","timestamp":1796083200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100013139","name":"Humanities and Social Science Fund of Ministry of Education of the People's Republic of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100013139","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100007129","name":"Shandong Province Natural Science Foundation","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100007129","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Pattern Recognition"],"published-print":{"date-parts":[[2026,12]]},"DOI":"10.1016\/j.patcog.2026.114268","type":"journal-article","created":{"date-parts":[[2026,6,27]],"date-time":"2026-06-27T06:47:02Z","timestamp":1782542822000},"page":"114268","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":1,"special_numbering":"PC","title":["Explainable multimodal classroom activity recognition: Dataset, metrics, and benchmark"],"prefix":"10.1016","volume":"180","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0731-9228","authenticated-orcid":false,"given":"Cunling","family":"Bian","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaofang","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weigang","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"issue":"3","key":"10.1016\/j.patcog.2026.114268_b1","first-page":"126","article-title":"Artificial intelligent based video analysis on the teaching interaction patterns in classroom environment","volume":"11","author":"Lv","year":"2021","journal-title":"Int. J. Inf. Educ. Technol."},{"issue":"5","key":"10.1016\/j.patcog.2026.114268_b2","doi-asserted-by":"crossref","first-page":"43","DOI":"10.11648\/j.ijsedu.20150305.11","article-title":"The instructional process: A review of Flanders\u2019 interaction analysis in a classroom setting","volume":"3","author":"Amatari","year":"2015","journal-title":"Int. J. Second. Educ."},{"issue":"8","key":"10.1016\/j.patcog.2026.114268_b3","doi-asserted-by":"crossref","first-page":"11161","DOI":"10.1007\/s10639-022-11080-x","article-title":"Quantitative analysis of Chinese classroom teaching activity under the background of artificial intelligence","volume":"27","author":"Yuan","year":"2022","journal-title":"Educ. Inf. Technol."},{"key":"10.1016\/j.patcog.2026.114268_b4","series-title":"IEEE International Conference on Multimedia and Expo","first-page":"1","article-title":"TBU: A large-scale multi-mask video dataset for teacher behavior understanding","author":"Cai","year":"2024"},{"key":"10.1016\/j.patcog.2026.114268_b5","article-title":"SLBDetection-Net: Towards closed-set and open-set student learning behavior detection in smart classroom of K-12 education","author":"Wang","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114268_b6","article-title":"Automatic classification of activities in classroom videos","volume":"6","author":"Foster","year":"2024","journal-title":"Comput. Educ.: Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114268_b7","doi-asserted-by":"crossref","first-page":"8828","DOI":"10.1007\/s10489-021-02329-y","article-title":"A simple teacher behavior recognition method for massive teaching videos based on teacher set","volume":"51","author":"Gang","year":"2021","journal-title":"Appl. Intell."},{"key":"10.1016\/j.patcog.2026.114268_b8","doi-asserted-by":"crossref","DOI":"10.1016\/j.imavis.2023.104726","article-title":"Student behavior recognition for interaction detection in the classroom environment","volume":"136","author":"Li","year":"2023","journal-title":"Image Vis. Comput."},{"key":"10.1016\/j.patcog.2026.114268_b9","doi-asserted-by":"crossref","unstructured":"M. Xu, Y. Shen, S. Wang, X. Yuan, Oriented Classroom Instructional Behavior Recognition Benchmark, in: International Symposium on Emerging Technologies for Education, 2023, pp. 130\u2013141.","DOI":"10.1007\/978-981-97-4243-1_11"},{"issue":"2","key":"10.1016\/j.patcog.2026.114268_b10","doi-asserted-by":"crossref","first-page":"1012","DOI":"10.1109\/TAFFC.2021.3127692","article-title":"Multimodal engagement analysis from facial videos in the classroom","volume":"14","author":"S\u00fcmer","year":"2021","journal-title":"IEEE Trans. Affect. Comput."},{"key":"10.1016\/j.patcog.2026.114268_b11","article-title":"Explainable artificial intelligence in education","volume":"3","author":"Khosravi","year":"2022","journal-title":"Comput. Educ.: Artif. Intell."},{"key":"10.1016\/j.patcog.2026.114268_b12","doi-asserted-by":"crossref","unstructured":"D.H. Park, L.A. Hendricks, Z. Akata, A. Rohrbach, B. Schiele, T. Darrell, M. Rohrbach, Multimodal explanations: Justifying decisions and pointing to the evidence, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2018, pp. 8779\u20138788.","DOI":"10.1109\/CVPR.2018.00915"},{"key":"10.1016\/j.patcog.2026.114268_b13","series-title":"E-snli-ve: Corrected visual-textual entailment with natural language explanations","author":"Do","year":"2020"},{"issue":"1","key":"10.1016\/j.patcog.2026.114268_b14","article-title":"From blackbox to explainable AI in healthcare: Existing tools and case studies","volume":"2022","author":"Srinivasu","year":"2022","journal-title":"Mob. Inf. Syst."},{"issue":"8","key":"10.1016\/j.patcog.2026.114268_b15","doi-asserted-by":"crossref","first-page":"5031","DOI":"10.1109\/TII.2022.3146552","article-title":"From artificial intelligence to explainable artificial intelligence in industry 4.0: A survey on what, how, and where","volume":"18","author":"Ahmed","year":"2022","journal-title":"IEEE Trans. Ind. Informatics"},{"key":"10.1016\/j.patcog.2026.114268_b16","doi-asserted-by":"crossref","first-page":"569","DOI":"10.1109\/TLT.2023.3301094","article-title":"Student action recognition for improving teacher feedback during tele-education","volume":"17","author":"Dimitriadou","year":"2023","journal-title":"IEEE Trans. Learn. Technol."},{"issue":"1","key":"10.1016\/j.patcog.2026.114268_b17","article-title":"Identifying and monitoring students\u2019 classroom learning behavior based on multisource information","volume":"2022","author":"Yin Albert","year":"2022","journal-title":"Mob. Inf. Syst."},{"key":"10.1016\/j.patcog.2026.114268_b18","first-page":"1","article-title":"Cbph-net: A small object detector for behavior recognition in classroom scenarios","volume":"72","author":"Zhao","year":"2023","journal-title":"IEEE Trans. Instrum. Meas."},{"key":"10.1016\/j.patcog.2026.114268_b19","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.125392","article-title":"SLBDetection-Net: Towards closed-set and open-set student learning behavior detection in smart classroom of K-12 education","volume":"260","author":"Wang","year":"2025","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114268_b20","doi-asserted-by":"crossref","DOI":"10.1016\/j.learninstruc.2024.101926","article-title":"Shedding light on relations between teacher emotions, instructional behavior, and student school well-being\u2013evidence from disadvantaged schools","volume":"92","author":"Holzer","year":"2024","journal-title":"Learn. Instr."},{"issue":"1","key":"10.1016\/j.patcog.2026.114268_b21","article-title":"The recognition of teacher behavior based on multimodal information fusion","volume":"2020","author":"Wu","year":"2020","journal-title":"Math. Probl. Eng."},{"key":"10.1016\/j.patcog.2026.114268_b22","doi-asserted-by":"crossref","first-page":"337","DOI":"10.1016\/j.patrec.2024.11.002","article-title":"Measuring student behavioral engagement using histogram of actions","volume":"186","author":"Abdelkawy","year":"2024","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.patcog.2026.114268_b23","doi-asserted-by":"crossref","unstructured":"H. Duan, Y. Zhao, K. Chen, D. Lin, B. Dai, Revisiting skeleton-based action recognition, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2022, pp. 2969\u20132978.","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"10.1016\/j.patcog.2026.114268_b24","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111205","article-title":"Predicting pedestrian intentions with multimodal IntentFormer: A co-learning approach","volume":"161","author":"Sharma","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114268_b25","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2023.109713","article-title":"A multi-modal transformer network for action detection","volume":"142","author":"Korban","year":"2023","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114268_b26","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2025.129781","article-title":"EPAM-Net: An efficient pose-driven attention-guided multimodal network for video action recognition","volume":"633","author":"Abdelkawy","year":"2025","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patcog.2026.114268_b27","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2023.103805","article-title":"Cross-modal alignment and translation for missing modality action recognition","volume":"236","author":"Park","year":"2023","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.114268_b28","doi-asserted-by":"crossref","DOI":"10.1016\/j.eswa.2024.123145","article-title":"DFN: A deep fusion network for flexible single and multi-modal action recognition","volume":"245","author":"Li","year":"2024","journal-title":"Expert Syst. Appl."},{"key":"10.1016\/j.patcog.2026.114268_b29","article-title":"Cross-scene visual context parsing with large vision-language model","author":"Zhang","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114268_b30","series-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"10.1016\/j.patcog.2026.114268_b31","article-title":"Visual instruction tuning","volume":"36","author":"Liu","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114268_b32","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2024.111189","article-title":"Percept, Chat, Adapt: Knowledge transfer of foundation models for open-world video recognition","volume":"160","author":"Chen","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114268_b33","doi-asserted-by":"crossref","first-page":"18090","DOI":"10.52202\/075280-0795","article-title":"Pengi: An audio language model for audio tasks","volume":"36","author":"Deshmukh","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"10.1016\/j.patcog.2026.114268_b34","doi-asserted-by":"crossref","unstructured":"Y. Yuan, W. Li, J. Liu, D. Tang, X. Luo, C. Qin, L. Zhang, J. Zhu, Osprey: Pixel understanding with visual instruction tuning, in: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2024, pp. 28202\u201328211.","DOI":"10.1109\/CVPR52733.2024.02664"},{"key":"10.1016\/j.patcog.2026.114268_b35","doi-asserted-by":"crossref","unstructured":"S. Moon, A. Madotto, Z. Lin, T. Nagarajan, M. Smith, S. Jain, C.-F. Yeh, P. Murugesan, P. Heidari, Y. Liu, et al., Anymal: An efficient and scalable any-modality augmented language model, in: Conference on Empirical Methods in Natural Language Processing, 2024, pp. 1314\u20131332.","DOI":"10.18653\/v1\/2024.emnlp-industry.98"},{"key":"10.1016\/j.patcog.2026.114268_b36","series-title":"Qwen2-vl: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024"},{"key":"10.1016\/j.patcog.2026.114268_b37","article-title":"Llava-med: Training a large language-and-vision assistant for biomedicine in one day","volume":"36","author":"Li","year":"2024","journal-title":"Adv. Neural Inf. Process. Syst."},{"issue":"12","key":"10.1016\/j.patcog.2026.114268_b38","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1007\/s11432-024-4250-y","article-title":"Docpedia: Unleashing the power of large multimodal model in the frequency domain for versatile document understanding","volume":"67","author":"Feng","year":"2024","journal-title":"Sci. China Inf. Sci."},{"key":"10.1016\/j.patcog.2026.114268_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111765","article-title":"SmokeAgent: Multimodal agent for fine-grained smoke event analysis in large-scale wild environments","author":"Cao","year":"2025","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patcog.2026.114268_b40","series-title":"Minicpm-v: A gpt-4v level mllm on your phone","author":"Yao","year":"2024"},{"key":"10.1016\/j.patcog.2026.114268_b41","unstructured":"C. Tang, W. Yu, G. Sun, X. Chen, T. Tan, W. Li, L. Lu, Z. MA, C. Zhang, SALMONN: Towards Generic Hearing Abilities for Large Language Models, in: International Conference on Learning Representations, 2024."},{"key":"10.1016\/j.patcog.2026.114268_b42","series-title":"Interspeech","article-title":"Funasr: A fundamental end-to-end speech recognition toolkit","author":"Gao","year":"2023"},{"key":"10.1016\/j.patcog.2026.114268_b43","doi-asserted-by":"crossref","first-page":"8335","DOI":"10.1007\/s00521-020-05587-y","article-title":"Student class behavior dataset: A video dataset for recognizing, detecting, and captioning students\u2019 behaviors in classroom scenes","volume":"33","author":"Sun","year":"2021","journal-title":"Neural Comput. Appl."},{"issue":"1","key":"10.1016\/j.patcog.2026.114268_b44","article-title":"Classroom learning status assessment based on deep learning","volume":"2022","author":"Zhou","year":"2022","journal-title":"Math. Probl. Eng."},{"issue":"1","key":"10.1016\/j.patcog.2026.114268_b45","doi-asserted-by":"crossref","first-page":"48","DOI":"10.3390\/bdcc7010048","article-title":"Real-time attention monitoring system for classroom: A deep learning approach for student\u2019s behavior recognition","volume":"7","author":"Trabelsi","year":"2023","journal-title":"Big Data Cogn. Comput."},{"key":"10.1016\/j.patcog.2026.114268_b46","doi-asserted-by":"crossref","DOI":"10.1016\/j.cviu.2024.104068","article-title":"Classroom teacher action recognition based on spatio-temporal dual-branch feature fusion","volume":"247","author":"Wu","year":"2024","journal-title":"Comput. Vis. Image Underst."},{"key":"10.1016\/j.patcog.2026.114268_b47","series-title":"SCB-dataset: A dataset for detecting student classroom behavior","author":"Yang","year":"2023"}],"container-title":["Pattern Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012331?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0031320326012331?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2026,8,20]],"date-time":"2026-08-20T08:54:42Z","timestamp":1787216082000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0031320326012331"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,12]]},"references-count":47,"alternative-id":["S0031320326012331"],"URL":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114268","relation":{},"ISSN":["0031-3203"],"issn-type":[{"value":"0031-3203","type":"print"}],"subject":[],"published":{"date-parts":[[2026,12]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Explainable multimodal classroom activity recognition: Dataset, metrics, and benchmark","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patcog.2026.114268","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2026 Elsevier Ltd. All rights are reserved, including those for text and data mining, AI training, and similar technologies.","name":"copyright","label":"Copyright"}],"article-number":"114268"}}