{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,5]],"date-time":"2026-11-05T22:00:18Z","timestamp":1793916018007,"version":"4.8.0"},"reference-count":48,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T00:00:00Z","timestamp":1769644800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100002703","name":"Jiangsu university","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100002703","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Neurorobot."],"abstract":"<jats:p>Digital-image technology has broadened the creative space of dance, yet accurately capturing the semantic correspondence between low-level motion data and high-level dance key-points remains challenging, especially when labeled data are scarce. We aim to establish a lightweight, semi-supervised pipeline that can extract discriminative motion features from depth sequences and map them to 3-D key-points of dancers in real time. To achieve pixel-level alignment between dance movement targets and high-dimensional sensory data, we propose a novel LSTM-CNN (Long Short Term Memory-Convolutional Neural Network) framework. Temporal-context features are first extracted by LSTM, after which multi-dimensional spatial features are captured by three convolutional layers and one max-pooling layer; the fused representation is finally regressed to 3-D body key-points. To relieve class imbalance caused by complex postures, an online hard-example mining (OHEM) strategy together with a Dice-cross-entropy weighted loss (3:1) is embedded into semi-supervised learning, enabling the network to converge with only 20% labeled samples. Experiments on the public MSR-Action3D dataset (567 sequences, 20 actions) yielded an average recognition rate of 96.9%, surpassing the best comparison method (MSST) by 1.1%. On our self-established dataset (99 sequences, 11 actions) the accuracy reached 97.99% while training time was reduced by 35% compared with the previous best Multi_perspective_MHPCs approach. Both datasets show low RMSE (\u2264 0.032) between predicted and ground-truth key-points, confirming spatial precision. The results demonstrate that the proposed model can reliably track subtle dance gestures under limited annotation, offering an efficient, low-cost solution for digital choreography, motion-style transfer and interactive stage performance.<\/jats:p>","DOI":"10.3389\/fnbot.2026.1743288","type":"journal-article","created":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T06:43:08Z","timestamp":1769668988000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Motion feature extraction based on semi-supervised learning and long short-term memory network in digital dance"],"prefix":"10.3389","volume":"20","author":[{"given":"Xue","family":"Yang","sequence":"first","affiliation":[{"name":"College of Music, Huaiyin Normal University","place":["Huai'an, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanmin","family":"Sun","sequence":"additional","affiliation":[{"name":"Weihai Art College, Shandong University","place":["Weihai, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yin","family":"Lyu","sequence":"additional","affiliation":[{"name":"College of Music, Huaiyin Normal University","place":["Huai'an, China"]},{"name":"Department of Dance School of Dance, Taipei National University of the Arts","place":["Taipei City, Taiwan"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yang","family":"Sun","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Shenyang Normal University","place":["Shenyang, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2026,1,29]]},"reference":[{"key":"ref1","author":"Abdullah","year":"2023"},{"key":"ref2","doi-asserted-by":"publisher","first-page":"94909","DOI":"10.52202\/079017-3008","article-title":"Adam with model exponential moving average is effective for nonconvex optimization","volume":"37","author":"Ahn","year":"2024","journal-title":"Adv. Neural Inf. Proces. Syst."},{"key":"ref3","doi-asserted-by":"publisher","first-page":"31372","DOI":"10.1038\/s41598-025-16180-5","article-title":"Advanced smart human activity recognition system for disabled people using artificial intelligence with snake optimizer techniques","volume":"15","author":"Alohali","year":"2025","journal-title":"Sci. Rep."},{"key":"ref4","doi-asserted-by":"publisher","first-page":"109","DOI":"10.3390\/info15020109","article-title":"Forensictransmonitor: a comprehensive blockchain approach to reinvent digital forensics and evidence management","volume":"15","author":"Alqahtany","year":"2024","journal-title":"Inform"},{"key":"ref5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/s12938-025-01347-y","article-title":"The effect of depth data and upper limb impairment on lightweight monocular RGB human pose estimation models","volume":"24","author":"Boudreault-Morales","year":"2025","journal-title":"Biomed. Eng. Online"},{"key":"ref6","author":"Chan","year":"2019"},{"key":"ref7","doi-asserted-by":"publisher","first-page":"155","DOI":"10.1007\/s11554-013-0370-1","article-title":"Real-time human action recognition based on depth motion maps","volume":"12","author":"Chen","year":"2016","journal-title":"J. Real-Time Image Proc."},{"key":"ref8","author":"Correia","year":"2022"},{"key":"ref9","doi-asserted-by":"crossref","first-page":"486","DOI":"10.1002\/9781118378625.ch28","article-title":"Futures: lifeform, livelihood, and lifeway","volume-title":"A companion to urban anthropology","author":"Cunningham","year":"2014"},{"key":"ref10","first-page":"108","article-title":"Wayne mcGregor\u2019s choreographic language agent","volume-title":"Transmission in motion: The technologizing of dance","author":"DeLahunta","year":"2017"},{"key":"ref11","doi-asserted-by":"publisher","first-page":"179823","DOI":"10.1109\/ACCESS.2024.3505199","article-title":"Design of a semi-automated system for dietary assessment of image-voice food records","volume":"12","author":"Dodd","year":"2024","journal-title":"IEEE Access"},{"key":"ref12","doi-asserted-by":"publisher","first-page":"104611","DOI":"10.1109\/ACCESS.2024.3435027","article-title":"Chasam: an architecture based on perceptual hashing for image detection in computer forensics","volume":"12","author":"Dos Santos","year":"2024","journal-title":"IEEE Access"},{"key":"ref13","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1155\/2021\/6653056","article-title":"A hybrid method integrating a discrete differential evolution algorithm with tabu search algorithm for the quadratic assignment problem: a new approach for locating hospital departments","volume":"2021","author":"Hameed","year":"2021","journal-title":"Math. Probl. Eng."},{"key":"ref14","doi-asserted-by":"publisher","first-page":"3400","DOI":"10.3390\/su16083400","article-title":"Assessing consumer behavior in sustainable product markets: a structural equation modeling approach with partial least squares analysis","volume":"16","author":"Islam","year":"2024","journal-title":"Sustainability"},{"key":"ref15","doi-asserted-by":"publisher","first-page":"1869","DOI":"10.2298\/CSIS221228034J","article-title":"Heterogenous-view occluded expression data recognition based on cycle-consistent adversarial network and K-SVD dictionary learning under intelligent cooperative robot environment","volume":"20","author":"Jiang","year":"2023","journal-title":"Comput. Sci. Inf. Syst."},{"key":"ref16","author":"Jones","year":"2019"},{"key":"ref17","author":"Jordan","year":"2020"},{"key":"ref18","doi-asserted-by":"publisher","first-page":"317","DOI":"10.1504\/IJESDF.2024.138355","article-title":"Cloud computing-based computer forensics: a deep learning technique","volume":"16","author":"Kalaiyarasi","year":"2024","journal-title":"Int. J. Electron. Secur. Digit. Forensics"},{"key":"ref19","doi-asserted-by":"publisher","first-page":"2563","DOI":"10.1016\/j.patcog.2006.11.014","article-title":"Human gait recognition by the fusion of motion and static spatio-temporal templates","volume":"40","author":"Lam","year":"2007","journal-title":"Pattern Recogn."},{"key":"ref20","doi-asserted-by":"publisher","first-page":"461","DOI":"10.1162\/LEON_a_01074","article-title":"Dance becoming knowledge: designing a digital \u201cbody\u201d","volume":"50","author":"Leach","year":"2017","journal-title":"Leonardo"},{"key":"ref21","doi-asserted-by":"publisher","first-page":"19587","DOI":"10.1007\/s11042-019-7356-3","article-title":"Action recognition from depth sequence using depth motion maps-based local ternary patterns and CNN","volume":"78","author":"Li","year":"2019","journal-title":"Multimed. Tools Appl."},{"key":"ref22","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1016\/j.cnsns.2015.11.019","article-title":"Generalized symmetry classifications, integrable properties and exact solutions to the general nonlinear diffusion equations","volume":"36","author":"Liu","year":"2016","journal-title":"Commun. Nonlinear Sci. Numer. Simul."},{"key":"ref23","doi-asserted-by":"publisher","first-page":"74","DOI":"10.1017\/S0149767700000395","article-title":"Allegories of passing in bill T. Jones","volume":"40","author":"Martin","year":"2008","journal-title":"Dance Res. J."},{"key":"ref24","doi-asserted-by":"publisher","first-page":"105387","DOI":"10.1016\/j.engappai.2022.105387","article-title":"A new approach to dominant motion pattern recognition at the macroscopic crowd level","volume":"116","author":"Matkovic","year":"2022","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref25","author":"Nogueira","year":"2023"},{"key":"ref26","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1080\/14794713.2024.2338927","article-title":"Exploring the impact of machine learning on dance performance: a systematic review","volume":"20","author":"Nogueira","year":"2024","journal-title":"Int. J. Perform. Arts Digit. Media"},{"key":"ref27","doi-asserted-by":"publisher","first-page":"7269","DOI":"10.1109\/TVCG.2025.3543740","article-title":"Introducing agent personality in crowd simulation improves social presence and experienced realism in immersive vr","volume":"31","author":"Pascoli","year":"2025","journal-title":"IEEE Trans. Vis. Comput. Graph."},{"key":"ref28","doi-asserted-by":"publisher","first-page":"571","DOI":"10.1007\/s11280-018-0582-1","article-title":"Deep learning approaches for video-based anomalous activity detection","volume":"22","author":"Pawar","year":"2019","journal-title":"World Wide Web"},{"key":"ref29","doi-asserted-by":"publisher","first-page":"37","DOI":"10.18536\/JGE.2020.01.04","article-title":"Dancing the digital age: a survey of the new technologies in the choreographic process","volume":"4","author":"Preciado-Azanza","year":"2020","journal-title":"J. Genius Emin."},{"key":"ref30","author":"Qader","year":"2019"},{"key":"ref31","doi-asserted-by":"publisher","first-page":"6199","DOI":"10.1007\/s00521-024-10965-x","article-title":"Adaptive loss optimization for enhanced learning performance: application to image-based rock classification","volume":"37","author":"Salavati","year":"2025","journal-title":"Neural Comput. & Applic."},{"key":"ref32","first-page":"171","article-title":"Artificial intelligence-based Bayesian optimization and transformer model for tennis motion recognition","volume":"29","author":"Shi","year":"2026","journal-title":"J. Appl. Sci. Eng."},{"key":"ref33","doi-asserted-by":"publisher","first-page":"749","DOI":"10.1007\/s41870-024-02355-2","article-title":"A modified inter-frame difference method for detection of moving objects in videos","volume":"17","author":"Srinivas","year":"2025","journal-title":"Int. J. Inf. Technol."},{"key":"ref34","doi-asserted-by":"publisher","first-page":"393","DOI":"10.1007\/s00530-025-01983-3","article-title":"Enhanced target recognition and localization using binocular vision and infrared thermal imaging","volume":"31","author":"Su","year":"2025","journal-title":"Multimedia Systems"},{"key":"ref35","author":"Sulzbachner","year":"2011"},{"key":"ref36","doi-asserted-by":"publisher","first-page":"251","DOI":"10.4028\/www.scientific.net\/AMM.462-463.251","article-title":"The blurring and restoring process of the moving object images","volume":"462","author":"Sun","year":"2014","journal-title":"Appl. Mech. Mater."},{"key":"ref37","doi-asserted-by":"publisher","first-page":"1237","DOI":"10.1016\/j.engappai.2010.07.004","article-title":"Model-based human gait recognition using leg and arm movements","volume":"23","author":"Tafazzoli","year":"2010","journal-title":"Eng. Appl. Artif. Intell."},{"key":"ref38","doi-asserted-by":"publisher","first-page":"1409","DOI":"10.2298\/CSIS220321040T","article-title":"BiSeNet-oriented context attention model for image semantic segmentation","volume":"19","author":"Teng","year":"2022","journal-title":"Comput. Sci. Inf. Syst."},{"key":"ref39","doi-asserted-by":"publisher","first-page":"1529","DOI":"10.1109\/TNSM.2023.3273991","article-title":"Flpk-bisenet: federated learning based on priori knowledge and bilateral segmentation network for image edge extraction","volume":"20","author":"Teng","year":"2023","journal-title":"IEEE Trans. Netw. Serv. Manag."},{"key":"ref40","doi-asserted-by":"publisher","first-page":"109456","DOI":"10.1016\/j.knosys.2022.109456","article-title":"Intelligent dual stream CNN and echo state network for anomaly detection","volume":"253","author":"Ullah","year":"2022","journal-title":"Knowl.-Based Syst."},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2508.18695","article-title":"A novel deep hybrid framework with ensemble-based feature optimization for robust real-time human activity recognition","author":"Ullah","year":"2025","journal-title":"arXiv preprint"},{"key":"ref42","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1002\/gdj3.162","article-title":"A novel deep learning-based single shot multibox detector model for object detection in optical remote sensing images","volume":"11","author":"Wang","year":"2024","journal-title":"Geosci. Data J."},{"key":"ref43","doi-asserted-by":"publisher","first-page":"118841","DOI":"10.1016\/j.measurement.2025.118841","article-title":"Novel adaptive sliding-mode control of digital hydraulic systems with nonlinear flow prediction and friction identification","volume":"257","author":"Xu","year":"2025","journal-title":"Measurement"},{"key":"ref44","doi-asserted-by":"publisher","first-page":"2540492","DOI":"10.1142\/S0129156425404929","article-title":"Research on data collection and posture optimization in dance training using smart wearable devices","volume":"35","author":"Ya","year":"2025","journal-title":"Int. J. High Speed Electron. Syst"},{"key":"ref45","doi-asserted-by":"publisher","first-page":"1638772","DOI":"10.3389\/frai.2025.1638772","article-title":"Enhanced YOLOv8 for industrial polymer films: a semi-supervised framework for Micron-scale defect detection","volume":"8","author":"Yu","year":"","journal-title":"Front. Artif. Intell."},{"key":"ref46","author":"Zhang","year":"2009"},{"key":"ref47","doi-asserted-by":"publisher","first-page":"1615276","DOI":"10.3389\/fnins.2025.1615276","article-title":"Advances in computer vision: from deep learning models to practical applications","volume":"19","author":"Zhu","year":"2025","journal-title":"Front. Neurosci."},{"key":"ref48","author":"Zou","year":"2014"}],"container-title":["Frontiers in Neurorobotics"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1743288\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T06:43:09Z","timestamp":1769668989000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/fnbot.2026.1743288\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,29]]},"references-count":48,"alternative-id":["10.3389\/fnbot.2026.1743288"],"URL":"https:\/\/doi.org\/10.3389\/fnbot.2026.1743288","relation":{},"ISSN":["1662-5218"],"issn-type":[{"value":"1662-5218","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,29]]},"article-number":"1743288"}}