[{"data":1,"prerenderedAt":-1},["ShallowReactive",2],{"doc-detail-83669-en":3,"doc-seo-83669-105":28,"detail-sidebar-cat-0-en-105":89},{"code":4,"msg":5,"data":6},0,"success",{"doc_id":7,"user_id":8,"nickname":9,"user_avatar":10,"doc_module":4,"category_id":11,"category_name":12,"doc_title":13,"doc_description":14,"doc_content":15,"file_id":16,"file_url":17,"file_type":18,"file_size":19,"view_count":4,"is_deleted":4,"is_public":20,"is_downloadable":20,"audit_status":20,"page_count":11,"language":21,"language_code":22,"site_id":23,"html_lang":22,"table_of_contents":24,"faqs":25,"seo_title":13,"seo_description":14,"update_tm":26,"read_time":27},83669,3848291630094,"Emma Wilson","https://eur-avatar.wpscdn.com/davatar_085a072bc5b1113ac321206ff7593b45",8,"Research & Report","Classroom Behavior Monitoring with YOLO: An Empirical Study in Higher Education Settings","Classroom behavior monitoring is essential for assessing student engagement and improving teaching effectiveness, yet traditional manual observation remains subjective and difficult to scale. This study presents a real-world BAV-Classroom dataset comprising annotated classroom videos from Banking Academy of Vietnam, labeled into nine behavioral categories. State-of-the-art computer vision models are evaluated and compared, with YOLOv11 delivering the strongest results. Findings show concentration commonly drops during the final lecture segment, underscoring challenges in sustained engagement and enabling automated monitoring for academic quality management.","Classroom Behavior Monitoring with YOLO An Empirical Study in  \nHigher Education Settings  \nSinh Vu Trong 1[0009−0004−8161−1686], Dung Nguyen Manh2[0009−0007−1299−3619], Hieu Hoang Minh3[0009−0008−5032−1204], Hieu Pham Trung4[0009−0002−8374−4912], Thu Pham  \nHa5[0009−0005−5101−1863], and Nhu Le Hoang6[0009−0006−4351−5866]  \n1 Banking Academy of Vietnam, Hanoi, [Vietnam sinhvt@hvnh.edu.vn](Vietnam sinhvt@hvnh.edu.vn)  \n2 Banking Academy of Vietnam, Hanoi, [Vietnam nguyenmanhdung0627@gmail.com](Vietnam nguyenmanhdung0627@gmail.com)  \n3 Banking Academy of Vietnam, Hanoi, [Vietnam 26a4041235@hvnh.edu.vn](Vietnam 26a4041235@hvnh.edu.vn)  \n4 Banking Academy of Vietnam, Hanoi, [Vietnam hieupt05.work@gmail.com](Vietnam hieupt05.work@gmail.com)  \n5 Banking Academy of Vietnam, Hanoi, [Vietnam thucan041105@gmail.com](Vietnam thucan041105@gmail.com)  \n6 Banking Academy of Vietnam, Hanoi, [Vietnam hoangnhule017@gmail.com](Vietnam hoangnhule017@gmail.com)  \nAbstract. Classroom behavior monitoring plays a vital role in evaluating student  \nengagement and improving teaching effectiveness. Traditional observation methods remain  \nsubjective and lack scalability. This study introduces a real-world dataset of classroom  \nvideos collected at the Banking Academy of Vietnam (BAV-Classroom dataset), annotated  \nwith nine distinctive behavioral categories. State-of-the-art Computer Vision models were  \nevaluated and compared, with YOLOv11 achieving the best performance. Experimental  \nresults indicate that students’ concentration often decreases notably during the final part of  \nlectures, highlighting challenges in sustaining engagement. Our findings demonstrate the  \nfeasibility of applying computer vision for automated classroom monitoring, providing  \nvaluable insights for academic quality management.  \nKeywords: Computer Vision · Classroom Activity Monitoring · YOLO.  \n1 Introduction  \nIn the current educational environment, classroom activities generate a diverse and abundant range of data, which differs significantly from traditional classroom settings that primarily rely on textual [2], [14] or verbal information [18] . Among these data types, visual data plays a pivotal role in reflecting the dynamics of teaching and learning interactions. Specifically, classroom images can offer rich visual cues about students’ emotional expressions and attention levels [18] .  \nHowever, the analysis of this type of data mainly relies on manual observation and subjective interpretation, which can lead to bias and limit the scalability of its application [2] . To address this challenge, many recent works have sought to automate classroom observation and assessment through image-based analysis methods. Instead of relying solely on traditional indicators such as test scores or surveys, directly analyzing classroom activities through video can provide teachers with deeper insights into students’ levels of attention and engagement [3] .  \nComputer Vision (CV) has emerged as a prominent approach to this problem, allowing systems to collect and extract information from image and video data to recognize faces and detect student behaviors, which opens up opportunities for applications in the educational domain. Integrating Computer Vision into classroom monitoring has the potential to reduce human intervention while providing objective and real-time assessments of classroom status. This not only assists teachers in monitoring classroom activities more effectively but also  \ngenerates valuable data to support the improvement of teaching methodologies.  \nIn this paper, we survey existing Computer Vision models, including R-CNN, Fast R-CNN, Faster R-CNN, YOLO (You Only Look Once) series, and assess their potential for application in classroom video analysis. Specifically, the contributions of the paper are summarized as follows:  \n1. We collect a real-world dataset from the classroom cameras, then annotated manually to ensure the correctness of the student behaviors. W","cbCaiatY4Uw285Si","https://ap.wps.com/l/cbCaiatY4Uw285Si","pdf",460064,1,"English","en",105,"# Introduction\n# Related works","[{\"question\":\"What problem does the study address in classroom monitoring?\",\"answer\":\"The study targets the subjectivity and limited scalability of traditional manual classroom observation when evaluating student engagement and attention.\"},{\"question\":\"What dataset is introduced and how is it labeled?\",\"answer\":\"The paper introduces the BAV-Classroom dataset, built from real classroom video collected at Banking Academy of Vietnam and annotated manually into nine distinctive behavioral categories.\"},{\"question\":\"Which model achieved the best performance and what key behavioral trend was observed?\",\"answer\":\"YOLOv11 achieved the best performance. Results indicate students’ concentration often decreases notably during the final part of lectures, making engagement harder to sustain.\"}]",1784189639,20,{"code":4,"msg":29,"data":30},"ok",{"site_id":23,"language":22,"slug":31,"title":13,"keywords":32,"description":14,"schema_data":33,"social_meta":84,"head_meta":86,"extra_data":88,"updated_unix":26},"classroom-behavior-monitoring-with-yolo-an-empirical-study-in-higher-education-settings","",{"@graph":34,"@context":83},[35,52,66],{"@type":36,"itemListElement":37},"BreadcrumbList",[38,42,46,49],{"item":39,"name":40,"@type":41,"position":20},"https://docshare.wps.com","Home","ListItem",{"item":43,"name":44,"@type":41,"position":45},"https://docshare.wps.com/document/","Document",2,{"item":47,"name":12,"@type":41,"position":48},"https://docshare.wps.com/document/research-report/",3,{"item":50,"name":13,"@type":41,"position":51},"https://docshare.wps.com/document/classroom-behavior-monitoring-with-yolo-an-empirical-study-in-higher-education-settings/83669/",4,{"url":50,"name":13,"@type":53,"author":54,"headline":13,"publisher":56,"fileFormat":59,"inLanguage":22,"description":14,"dateModified":60,"datePublished":60,"encodingFormat":59,"isAccessibleForFree":61,"interactionStatistic":62},"DigitalDocument",{"name":9,"@type":55},"Person",{"url":39,"name":57,"@type":58},"DocShare","Organization","application/pdf","2026-07-16",true,{"@type":63,"interactionType":64,"userInteractionCount":4},"InteractionCounter",{"@type":65},"ViewAction",{"@type":67,"mainEntity":68},"FAQPage",[69,75,79],{"name":70,"@type":71,"acceptedAnswer":72},"What problem does the study address in classroom monitoring?","Question",{"text":73,"@type":74},"The study targets the subjectivity and limited scalability of traditional manual classroom observation when evaluating student engagement and attention.","Answer",{"name":76,"@type":71,"acceptedAnswer":77},"What dataset is introduced and how is it labeled?",{"text":78,"@type":74},"The paper introduces the BAV-Classroom dataset, built from real classroom video collected at Banking Academy of Vietnam and annotated manually into nine distinctive behavioral categories.",{"name":80,"@type":71,"acceptedAnswer":81},"Which model achieved the best performance and what key behavioral trend was observed?",{"text":82,"@type":74},"YOLOv11 achieved the best performance. Results indicate students’ concentration often decreases notably during the final part of lectures, making engagement harder to sustain.","https://schema.org",{"og:url":50,"og:type":85,"og:title":13,"og:site_name":57,"og:description":14},"article",{"robots":87,"canonical":50},"index,follow",{"doc_id":7,"site_id":23},{"code":4,"msg":5,"data":90},[91,95,99,103,108,113,118,121,125,128,132],{"id":20,"doc_module":4,"doc_module_name":44,"category_name":92,"show_sort_weight":93,"slug":94},"Story & Novel",90,"story-novel",{"id":45,"doc_module":4,"doc_module_name":44,"category_name":96,"show_sort_weight":97,"slug":98},"Literature",80,"literature",{"id":51,"doc_module":4,"doc_module_name":44,"category_name":100,"show_sort_weight":101,"slug":102},"Exam",70,"exam",{"id":104,"doc_module":4,"doc_module_name":44,"category_name":105,"show_sort_weight":106,"slug":107},5,"Comic",60,"comic",{"id":109,"doc_module":4,"doc_module_name":44,"category_name":110,"show_sort_weight":111,"slug":112},6,"Technology",50,"technology",{"id":114,"doc_module":4,"doc_module_name":44,"category_name":115,"show_sort_weight":116,"slug":117},7,"Healthcare",40,"healthcare",{"id":11,"doc_module":4,"doc_module_name":44,"category_name":12,"show_sort_weight":119,"slug":120},30,"research-report",{"id":122,"doc_module":4,"doc_module_name":44,"category_name":123,"show_sort_weight":27,"slug":124},9,"Religion & Spirituality","religion-spirituality",{"id":27,"doc_module":4,"doc_module_name":44,"category_name":126,"show_sort_weight":27,"slug":127},"World Cup","world-cup",{"id":129,"doc_module":4,"doc_module_name":44,"category_name":130,"show_sort_weight":129,"slug":131},10,"Lifestyle","lifestyle",{"id":133,"doc_module":4,"doc_module_name":44,"category_name":134,"show_sort_weight":104,"slug":135},19,"General","general"]