{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T11:10:26Z","timestamp":1788952226162,"version":"build-2803163510"},"reference-count":60,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T00:00:00Z","timestamp":1788912000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Public Health"],"abstract":"<jats:sec>\n                    <jats:title>Background<\/jats:title>\n                    <jats:p>Schools are an important setting for developing movement competence and supporting physical activity PA). Teachers provide feedback on how learners move, but individualized observation is difficult to sustain and document in large classes. Existing artificial intelligence (AI) systems typically classify an action or predict one competitive-sport score. These outputs do not identify the specific movement feature that a learner might adjust during practice.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Methods<\/jats:title>\n                    <jats:p>Using three public human action datasets (NTU RGB+D, Penn Action, and a FineGym subset), we benchmarked five representative skeleton-sequence models\u2014recurrent (LSTM, GRU), graph-based (ST-GCN, CTR-GCN), and a Transformer\u2014under a unified setting, and constructed four interpretable movement-profile indicators from joint coordinates and trajectories: movement amplitude, postural stability, left\u2013right coordination, and temporal consistency. Each indicator was normalized against the same-class reference distribution, providing a relative, interpretable description rather than an expert-certified score.<\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Results<\/jats:title>\n                    <jats:p>\n                      Over five random seeds per dataset, independent-test macro-F1 ranged from 0.76 to 0.97; CTR-GCN obtained the highest mean on every dataset (NTU RGB+D 0.970 \u00b1 0.003). Paired tests supported its advantage over all four comparators on NTU RGB+D and FineGym, whereas on Penn Action only the comparison with LSTM remained significant after correction. In the feature ablation, the full kinematic input increased macro-F1 from 0.925 to 0.936 on 3D skeletons (Holm-adjusted\n                      <jats:italic>p<\/jats:italic>\n                      = 0.022); the corresponding 2D change from 0.893 to 0.905 was not significant after correction (\n                      <jats:italic>p<\/jats:italic>\n                      = 0.079). Per-action profiles and a same-action case analysis showed that the indicators capture interpretable kinematic structure. The resulting percentiles describe relative tendencies within these datasets; a low percentile does not by itself identify an incorrect movement or constitute an age-appropriate standard for children.\n                    <\/jats:p>\n                  <\/jats:sec>\n                  <jats:sec>\n                    <jats:title>Conclusion<\/jats:title>\n                    <jats:p>Skeleton-only movement profiles offer a privacy-reducing, teacher-in-the-loop approach to formative feedback that could support digital PA education and health promotion in schools. As a computational proof-of-concept evaluated on public datasets, the study does not include health or learning outcomes, age-specific K\u201312 reference distributions, or authentic-classroom validation. Calibration on curriculum-relevant data from children and validation against teacher or movement-expert ratings are required before the profiles can be interpreted as movement-quality feedback or used to support public-health claims.<\/jats:p>\n                  <\/jats:sec>","DOI":"10.3389\/fpubh.2026.1925220","type":"journal-article","created":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:17:08Z","timestamp":1788949028000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Interpretable skeleton-based movement profiles for formative feedback in school physical activity education"],"prefix":"10.3389","volume":"14","author":[{"given":"Qixuan","family":"Ma","sequence":"first","affiliation":[{"name":"University of Macau","place":["Taipa, Macau SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiao","family":"Lei","sequence":"additional","affiliation":[{"name":"University of Macau","place":["Taipa, Macau SAR, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Feng","family":"Li","sequence":"additional","affiliation":[{"name":"Institute of Orthopaedics, Nankai University","place":["Tianjin, China"]},{"name":"Eugene WuKangYuan (Hangzhou) Health Technology Co., Ltd","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chengmao","family":"Yang","sequence":"additional","affiliation":[{"name":"Institute of Orthopaedics, Nankai University","place":["Tianjin, China"]},{"name":"State Key Laboratory of Medicinal Chemical Biology, College of Life Sciences, Nankai University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jinsui","family":"Du","sequence":"additional","affiliation":[{"name":"Xiguan Guangya Experimental School, Liwan District","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiaxing","family":"Zhu","sequence":"additional","affiliation":[{"name":"Institute of Orthopaedics, Nankai University","place":["Tianjin, China"]},{"name":"Eugene WuKangYuan (Hangzhou) Health Technology Co., Ltd","place":["Hangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongxin","family":"Zhao","sequence":"additional","affiliation":[{"name":"Shaanxi University of Technology","place":["Hanzhong, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhenghu","family":"Jia","sequence":"additional","affiliation":[{"name":"Institute of Orthopaedics, Nankai University","place":["Tianjin, China"]},{"name":"Eugene WuKangYuan (Hangzhou) Health Technology Co., Ltd","place":["Hangzhou, China"]},{"name":"State Key Laboratory of Medicinal Chemical Biology, College of Life Sciences, Nankai University","place":["Tianjin, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,9,9]]},"reference":[{"key":"B1","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/S2352-4642(19)30323-2","article-title":"Global trends in insufficient physical activity among adolescents: a pooled analysis of 298 population-based surveys with 16 million participants","volume":"4","author":"Guthold","year":"2020","journal-title":"Lancet Child Adolesc Health"},{"key":"B2","doi-asserted-by":"publisher","first-page":"1451","DOI":"10.1136\/bjsports-2020-102955","article-title":"World Health Organization 2020 guidelines on physical activity and sedentary behaviour","volume":"54","author":"Bull","year":"2020","journal-title":"Br J Sports Med"},{"key":"B3","volume-title":"Global Action Plan on Physical Activity 2018-2030: More Active People for a Healthier World","year":"2018"},{"key":"B4","doi-asserted-by":"publisher","first-page":"368","DOI":"10.1016\/j.pcad.2014.09.010","article-title":"Supporting public health priorities: recommendations for physical education and physical activity promotion in schools","volume":"57","author":"Hills","year":"2015","journal-title":"Prog Cardiovasc Dis"},{"key":"B5","doi-asserted-by":"publisher","first-page":"290","DOI":"10.1080\/00336297.2008.10483582","article-title":"A developmental perspective on the role of motor skill competence in physical activity: an emergent relationship","volume":"60","author":"Stodden","year":"2008","journal-title":"Quest"},{"key":"B6","doi-asserted-by":"publisher","first-page":"1019","DOI":"10.2165\/11536850-000000000-00000","article-title":"Fundamental movement skills in children and adolescents: review of associated health benefits","volume":"40","author":"Lubans","year":"2010","journal-title":"Sports Med"},{"key":"B7","doi-asserted-by":"publisher","first-page":"371","DOI":"10.1007\/s40279-019-01063-3","article-title":"Physical literacy, physical activity and health: toward an evidence-informed conceptual model","volume":"49","author":"Cairney","year":"2019","journal-title":"Sports Med"},{"key":"B8","doi-asserted-by":"publisher","first-page":"7","DOI":"10.1080\/0969595980050102","article-title":"Assessment and Classroom Learning","volume":"5","author":"Black","year":"1998","journal-title":"Assessm Educ: Princ Policy Pract"},{"key":"B9","doi-asserted-by":"publisher","first-page":"75","DOI":"10.1111\/j.1365-2923.2009.03421.x","article-title":"Motor skill learning and performance: a review of influential factors","volume":"44","author":"Wulf","year":"2010","journal-title":"Med Educ"},{"key":"B10","doi-asserted-by":"publisher","first-page":"172","DOI":"10.1109\/TPAMI.2019.2929257","article-title":"OpenPose: realtime multi-person 2D Pose estimation using part affinity fields","volume":"43","author":"Cao","year":"2021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"B11","first-page":"5693","article-title":"Deep high-resolution representation learning for human pose estimation","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Sun","year":"2019"},{"key":"B12","doi-asserted-by":"publisher","first-page":"0100","DOI":"10.34133\/cbsystems.0100","article-title":"Survey on 3D skeleton-based action recognition using learning method","volume":"5","author":"Ren","year":"2024","journal-title":"Cyborg Bionic Syst"},{"key":"B13","doi-asserted-by":"crossref","DOI":"10.1609\/aaai.v32i1.12328","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"Yan","year":"2018","journal-title":"Proceedings of the AAAI Conference on Artificial Intelligence (AAAI)"},{"key":"B14","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.01311","article-title":"Channel-Wise Topology refinement graph convolution for skeleton-based action recognition","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Chen","year":"2021"},{"key":"B15","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV48922.2021.00782","article-title":"Group-aware contrastive regression for action quality assessment","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Yu","year":"2021"},{"key":"B16","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2412.11149","article-title":"A comprehensive survey of action quality assessment: method and benchmark","author":"Zhou","year":"2024","journal-title":"arXiv"},{"key":"B17","doi-asserted-by":"publisher","first-page":"1","DOI":"10.5672\/apunts.2014-0983.es.(2025\/2).160.0","article-title":"Is artificial intelligence an educational resource in physical education? A systematic review","volume":"41","author":"Bofill","year":"2025","journal-title":"Apunts Educacion Fisica y Deportes"},{"key":"B18","doi-asserted-by":"publisher","first-page":"1484848","DOI":"10.3389\/fpubh.2024.1484848","article-title":"Artificial intelligence in physical education: comprehensive review and future teacher training strategies","volume":"12","author":"Wang","year":"2024","journal-title":"Front Public Health"},{"key":"B19","doi-asserted-by":"publisher","first-page":"355","DOI":"10.1037\/0033-2909.95.3.355","article-title":"Knowledge of results and motor learning: a review and critical reappraisal","volume":"95","author":"Salmoni","year":"1984","journal-title":"Psychol Bull"},{"key":"B20","doi-asserted-by":"publisher","first-page":"21","DOI":"10.3758\/s13423-012-0333-8","article-title":"Augmented visual, auditory, haptic, and multimodal feedback in motor learning: a review","volume":"20","author":"Sigrist","year":"2013","journal-title":"Psychonomic Bullet Rev"},{"key":"B21","volume-title":"Motor Control and Learning: A Behavioral Emphasis","author":"Schmidt","year":"2018"},{"key":"B22","doi-asserted-by":"publisher","first-page":"859","DOI":"10.1111\/obr.12823","article-title":"Are school-based physical activity interventions effective and equitable? A meta-analysis of cluster randomized controlled trials with accelerometer-assessed activity","volume":"20","author":"Love","year":"2019","journal-title":"Obesity Rev"},{"key":"B23","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1016\/j.jadohealth.2017.05.024","article-title":"A systematic review of digital interventions for improving the diet and physical activity behaviors of adolescents","volume":"61","author":"Rose","year":"2017","journal-title":"J Adolesc Health"},{"key":"B24","volume-title":"Global Strategy on Digital Health 2020-2025","year":"2021"},{"key":"B25","first-page":"568","article-title":"Two-stream convolutional networks for action recognition in videos","author":"Simonyan","year":"2014","journal-title":"Advances in Neural Information Processing Systems (NIPS"},{"key":"B26","first-page":"4724","article-title":"Quo vadis, action recognition?","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Carreira","year":"2017"},{"key":"B27","first-page":"6202","article-title":"SlowFast networks for video recognition","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Feichtenhofer","year":"2019"},{"key":"B28","doi-asserted-by":"publisher","first-page":"5121","DOI":"10.3390\/s23115121","article-title":"Deep learning for human activity recognition on 3D human skeleton: survey and comparative study","volume":"23","author":"Nguyen","year":"2023","journal-title":"Sensors"},{"key":"B29","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Du","year":"2015"},{"key":"B30","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-319-46487-9_50","article-title":"Spatio-temporal LSTM with trust gates for 3D human action recognition","volume-title":"Computer Vision-ECCV 2016","author":"Liu","year":"2016"},{"key":"B31","first-page":"12026","article-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Shi","year":"2019"},{"key":"B32","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00810","article-title":"Skeleton-based action recognition with directed graph neural networks","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Shi","year":"2019"},{"key":"B33","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00026","article-title":"Skeleton-based action recognition with shift graph convolutional network","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Cheng","year":"2020"},{"key":"B34","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-030-60639-8_40","article-title":"Disentangling and unifying graph convolutions for skeleton-based action recognition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Liu","year":"2020"},{"key":"B35","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52688.2022.01955","article-title":"InfoGCN: representation learning for human skeleton-based action recognition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chi","year":"2022"},{"key":"B36","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2021.103219","article-title":"Skeleton-based action recognition via spatial and temporal transformer networks","author":"Plizzari","year":"2021","journal-title":"Comp Vision Image Understand"},{"key":"B37","first-page":"401","article-title":"SkateFormer: skeletal-temporal transformer for human action recognition","volume-title":"Computer Vision-ECCV 2024","author":"Do","year":"2024"},{"key":"B38","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.00200","article-title":"BlockGCN: redefine topology awareness for skeleton-based action recognition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Zhou","year":"2024"},{"key":"B39","first-page":"2969","article-title":"Revisiting skeleton-based action recognition","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Duan","year":"2022"},{"key":"B40","doi-asserted-by":"crossref","first-page":"556","DOI":"10.1007\/978-3-319-10599-4_36","article-title":"Assessing the quality of actions","volume-title":"Computer Vision-ECCV 2014","author":"Pirsiavash","year":"2014"},{"key":"B41","first-page":"20","article-title":"Learning to score olympic events","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Parmar","year":"2017"},{"key":"B42","article-title":"What and how well you performed?","author":"Parmar","year":"2019"},{"key":"B43","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00986","article-title":"Uncertainty-aware score distribution learning for action quality assessment","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tang","year":"2020"},{"key":"B44","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00643","article-title":"Action assessment by joint relation graphs","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)","author":"Pan","year":"2019"},{"key":"B45","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-19772-7_25","article-title":"Action quality assessment with temporal parsing transformer","volume-title":"Computer Vision-ECCV 2022","author":"Bai","year":"2022"},{"key":"B46","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR52733.2024.01386","article-title":"FineParser: a fine-grained spatio-temporal action parser for human-centric action quality assessment","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xu","year":"2024"},{"key":"B47","first-page":"2616","article-title":"FineGym: a hierarchical video dataset for fine-grained action understanding","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Shao","year":"2020"},{"key":"B48","first-page":"2949","article-title":"FineDiving: a fine-grained dataset for procedure-aware action quality assessment","author":"Xu","year":"2022","journal-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)"},{"key":"B49","first-page":"21773","article-title":"FineSports: A Multi-person hierarchical sports video dataset for fine-grained action understanding","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Xu","year":"2024"},{"key":"B50","doi-asserted-by":"publisher","first-page":"2846","DOI":"10.1007\/s11263-021-01486-4","article-title":"SportsCap: monocular 3D human motion capture and fine-grained understanding in challenging sports videos","volume":"129","author":"Chen","year":"2021","journal-title":"Int J Comput Vis"},{"key":"B51","first-page":"513","article-title":"RESOUND: towards action recognition without representation bias","volume-title":"Computer Vision-ECCV 2018","author":"Li","year":"2018"},{"key":"B52","doi-asserted-by":"crossref","DOI":"10.1109\/WACV.2019.00161","article-title":"Action quality assessment across multiple actions","volume-title":"IEEE Winter Conference on Applications of Computer Vision (WACV)","author":"Parmar","year":"2019"},{"key":"B53","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2502.02817","article-title":"A decade of action quality assessment: largest systematic survey of trends, challenges, and future directions","author":"Yin","year":"2025","journal-title":"arXiv"},{"key":"B54","doi-asserted-by":"publisher","first-page":"1688","DOI":"10.1523\/JNEUROSCI.05-07-01688.1985","article-title":"The coordination of arm movements: an experimentally confirmed mathematical model","volume":"5","author":"Flash","year":"1985","journal-title":"J Neurosci"},{"key":"B55","doi-asserted-by":"publisher","first-page":"2","DOI":"10.3390\/data3010002","article-title":"A data set of human body movements for physical rehabilitation exercises","volume":"3","author":"Vakanski","year":"2018","journal-title":"Data"},{"key":"B56","doi-asserted-by":"publisher","first-page":"1436","DOI":"10.1109\/TNSRE.2019.2923060","article-title":"The KIMORE dataset: kinematic assessment of movement and clinical scores for remote monitoring of physical rehabilitation","volume":"27","author":"Capecci","year":"2019","journal-title":"IEEE Trans Neural Syst Rehabilitat Eng"},{"key":"B57","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2006.10204","article-title":"BlazePose: on-device real-time body pose tracking","author":"Bazarevsky","year":"2020","journal-title":"CVPR Workshop on Computer Vision for Augmented and Virtual Reality. arXiv"},{"key":"B58","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2303.07399","article-title":"RTMPose: real-time multi-person pose estimation based on MMPose","author":"Jiang","year":"2023","journal-title":"arXiv"},{"key":"B59","first-page":"1010","article-title":"NTU RGB+D: a large scale dataset for 3D human activity analysis","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Shahroudy","year":"2016"},{"key":"B60","first-page":"2248","article-title":"From Actemes to action: a strongly-supervised representation for detailed action understanding","volume-title":"Proceedings of the IEEE International Conference on Computer Vision (ICCV)","author":"Zhang","year":"2013"}],"container-title":["Frontiers in Public Health"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1925220\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,9]],"date-time":"2026-09-09T10:17:17Z","timestamp":1788949037000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fpubh.2026.1925220\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,9,9]]},"references-count":60,"alternative-id":["10.3389\/fpubh.2026.1925220"],"URL":"https:\/\/doi.org\/10.3389\/fpubh.2026.1925220","relation":{},"ISSN":["2296-2565"],"issn-type":[{"value":"2296-2565","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,9,9]]},"article-number":"1925220"}}