{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,3]],"date-time":"2026-10-03T02:15:24Z","timestamp":1790993724894,"version":"4.1.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T00:00:00Z","timestamp":1677196800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100012226","name":"fundamental research funds for the central universities","doi-asserted-by":"publisher","award":["2019CDYGZD004"],"award-info":[{"award-number":["2019CDYGZD004"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"national natural science foundation of china","doi-asserted-by":"publisher","award":["61876026"],"award-info":[{"award-number":["61876026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Virtual Reality"],"published-print":{"date-parts":[[2023,9]]},"DOI":"10.1007\/s10055-023-00773-4","type":"journal-article","created":{"date-parts":[[2023,2,24]],"date-time":"2023-02-24T15:02:47Z","timestamp":1677250967000},"page":"1797-1812","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":16,"title":["Action recognition based on multimode fusion for VR online platform"],"prefix":"10.1007","volume":"27","author":[{"given":"Xuan","family":"Li","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1948-1831","authenticated-orcid":false,"given":"Hengxin","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shengdong","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xinrun","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ping","family":"Yan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bin","family":"Fang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,2,24]]},"reference":[{"key":"773_CR1","doi-asserted-by":"crossref","unstructured":"Abdel-Salam R, Mostafa R, Hadhood M (2021) Human activity recognition using wearable sensors: review, challenges, evaluation benchmark. arXiv preprint arXiv:2101.01665","DOI":"10.1007\/978-981-16-0575-8_1"},{"issue":"3","key":"773_CR2","doi-asserted-by":"publisher","first-page":"1445","DOI":"10.1109\/JSEN.2019.2947446","volume":"20","author":"Z Ahmad","year":"2020","unstructured":"Ahmad Z, Khan N (2020) Human action recognition using deep multilevel multimodal ($${M}^{2}$$) fusion of depth and inertial sensors. IEEE Sens J 20(3):1445\u20131455. https:\/\/doi.org\/10.1109\/JSEN.2019.2947446","journal-title":"IEEE Sens J"},{"key":"773_CR3","doi-asserted-by":"crossref","unstructured":"Baumann C, Krskova H (2016) School discipline, school uniforms and academic performance. Int J Educ Manag 30(6):1003\u20131029","DOI":"10.1108\/IJEM-09-2015-0118"},{"issue":"1","key":"773_CR4","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1080\/1743727X.2011.552307","volume":"34","author":"T Cain","year":"2011","unstructured":"Cain T (2011) Teachers\u2019 classroom-based action research. Int J Res Method Educ 34(1):3\u201316","journal-title":"Int J Res Method Educ"},{"key":"773_CR5","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, Wei SE, Sheikh Y (2017) Realtime multi-person 2d pose estimation using part affinity fields. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 7291\u20137299","DOI":"10.1109\/CVPR.2017.143"},{"key":"773_CR6","doi-asserted-by":"crossref","unstructured":"Carreira J, Zisserman A (2017) Quo vadis, action recognition? a new model and the kinetics dataset. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 6299\u20136308","DOI":"10.1109\/CVPR.2017.502"},{"key":"773_CR7","doi-asserted-by":"crossref","unstructured":"Chen C, Jafari R, Kehtarnavaz N (2015) Utd-mhad: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor. In: 2015 IEEE international conference on image processing (ICIP),  168\u2013172. IEEE","DOI":"10.1109\/ICIP.2015.7350781"},{"key":"773_CR8","doi-asserted-by":"publisher","first-page":"1702","DOI":"10.1002\/cae.22418","volume":"29","author":"X Chen","year":"2021","unstructured":"Chen X, Chen H, Guo S, Li J, Zhang J, Li Z (2021) A virtual reality experiment system for an introductory computer hardware course. Comput Appl Eng Educ 29:1702\u20131717","journal-title":"Comput Appl Eng Educ"},{"key":"773_CR9","unstructured":"Contributors M (2020) Openmmlab\u2019s next generation video understanding toolbox and benchmark. https:\/\/github.com\/open-mmlab\/mmaction2"},{"issue":"5","key":"773_CR10","doi-asserted-by":"publisher","first-page":"1656","DOI":"10.3390\/s21051656","volume":"21","author":"M Dong","year":"2021","unstructured":"Dong M, Fang Z, Li Y, Bi S, Chen J (2021) Ar3d: attention residual 3d network for human action recognition. Sensors 21(5):1656","journal-title":"Sensors"},{"key":"773_CR11","doi-asserted-by":"crossref","unstructured":"Duan H, Zhao Y, Chen K, Shao D, Lin D, Dai B (2021) Revisiting skeleton-based action recognition. arXiv preprint arXiv:2104.13586","DOI":"10.1109\/CVPR52688.2022.00298"},{"key":"773_CR12","doi-asserted-by":"crossref","unstructured":"Feichtenhofer C, Pinz A, Zisserman A (2016) Convolutional two-stream network fusion for video action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 1933\u20131941","DOI":"10.1109\/CVPR.2016.213"},{"key":"773_CR13","unstructured":"Garcia NC, Bargal SA, Ablavsky V, Morerio P, Murino V, Sclaroff S (2019) Dmcl: distillation multiple choice learning for multimodal action recognition. arXiv preprint arXiv:1912.10982"},{"issue":"10","key":"773_CR14","doi-asserted-by":"publisher","first-page":"20","DOI":"10.2352\/ISSN.2470-1173.2017.10.IMAWM-162","volume":"2017","author":"MD Hssayeni","year":"2017","unstructured":"Hssayeni MD, Saxena S, Ptucha R, Savakis A (2017) Distracted driver detection: deep learning vs handcrafted features. Electron Imaging 2017(10):20\u201326","journal-title":"Electron Imaging"},{"key":"773_CR15","doi-asserted-by":"crossref","unstructured":"Islam MM (2022) Mumu: cooperative multitask learning-based guided multimodal fusion. In: International conference on intelligent robots and systems (IROS)","DOI":"10.1609\/aaai.v36i1.19988"},{"issue":"7","key":"773_CR16","doi-asserted-by":"publisher","first-page":"3802","DOI":"10.3390\/su13073802","volume":"13","author":"JS Jauhiainen","year":"2021","unstructured":"Jauhiainen JS (2021) Entrepreneurship and innovation events during the covid-19 pandemic: the user preferences of virbela virtual 3d platform at the shift event organized in finland. Sustainability 13(7):3802","journal-title":"Sustainability"},{"issue":"9","key":"773_CR17","doi-asserted-by":"publisher","first-page":"4293","DOI":"10.1007\/s00521-019-04615-w","volume":"32","author":"C Jing","year":"2020","unstructured":"Jing C, Wei P, Sun H, Zheng N (2020) Spatiotemporal neural networks for action recognition based on joint loss. Neural Comput Appl 32(9):4293\u20134302","journal-title":"Neural Comput Appl"},{"issue":"5","key":"773_CR18","first-page":"1","volume":"v.46;No.513","author":"H Jun","year":"2020","unstructured":"Jun H, Caiqing Z, Xiaozhen L, Dehai Z (2020) A review of deep learning-oriented multi-modal fusion technology. Comput Eng v.46;No.513(5):1\u201311","journal-title":"Comput Eng"},{"key":"773_CR19","doi-asserted-by":"crossref","unstructured":"Ke Q, Bennamoun M, An S, Sohel F, Boussaid F (2017) A new representation of skeleton sequences for 3d action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 3288\u20133297","DOI":"10.1109\/CVPR.2017.486"},{"key":"773_CR20","doi-asserted-by":"crossref","unstructured":"Kim S, Yun K, Park J, Choi JY (2019) Skeleton-based action recognition of people handling objects. In: 2019 IEEE winter conference on applications of computer vision (WACV), 61\u201370. IEEE","DOI":"10.1109\/WACV.2019.00014"},{"key":"773_CR21","doi-asserted-by":"crossref","unstructured":"Kim TS, Reiter A (2017) Interpretable 3d human action analysis with temporal convolutional networks. In: 2017 IEEE conference on computer vision and pattern recognition workshops (CVPRW), 1623\u20131631. IEEE","DOI":"10.1109\/CVPRW.2017.207"},{"key":"773_CR22","doi-asserted-by":"crossref","unstructured":"Kuehne H, Jhuang H, Garrote E, Poggio T, Serre T (2011) Hmdb: a large video database for human motion recognition. In: 2011 International conference on computer vision, 2556\u20132563. IEEE","DOI":"10.1109\/ICCV.2011.6126543"},{"key":"773_CR23","doi-asserted-by":"crossref","unstructured":"Lalioti V, Garcia C, Hasenbrink F (1998) Virtual meeting in cyberstage. In: Proceedings of the ACM symposium on virtual reality software and technology, 205\u2013212","DOI":"10.1145\/293701.293743"},{"key":"773_CR24","doi-asserted-by":"crossref","unstructured":"Liu J, Shahroudy A, Xu D, Wang G (2016) Spatio-temporal lstm with trust gates for 3d human action recognition. In: European conference on computer vision, 816\u2013833. Springer","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"773_CR25","doi-asserted-by":"crossref","unstructured":"Losilla F, Rosique F (2019) An augmented reality mirror exergame using 2d pose estimation. In: ICSOFT, 643\u2013648","DOI":"10.5220\/0007798906430648"},{"key":"773_CR26","doi-asserted-by":"crossref","unstructured":"Mahmud S, Tonmoy M, Bhaumik KK, Rahman A, Amin MA, Shoyaib M, Khan MAH, Ali AA (2020) Human activity recognition from wearable sensor data using self-attention. arXiv preprint arXiv:2003.09018","DOI":"10.3233\/FAIA200236"},{"key":"773_CR27","doi-asserted-by":"crossref","unstructured":"Mavridou I, McGhee JT, Hamedi M, Fatoorechi M, Cleal A, Ballaguer-Balester E, Seiss E, Cox G, Nduka C (2017) Faceteq interface demo for emotion expression in vr. In: 2017 IEEE virtual reality (VR), 441\u2013442. IEEE","DOI":"10.1109\/VR.2017.7892369"},{"key":"773_CR28","doi-asserted-by":"crossref","unstructured":"Memmesheimer R, Theisen N, Paulus D (2021) Sl-dml: Signal level deep metric learning for multimodal one-shot action recognition. In: 2020 25th International conference on pattern recognition (ICPR), 4573\u20134580. IEEE","DOI":"10.1109\/ICPR48806.2021.9413336"},{"key":"773_CR29","unstructured":"Mertler CA (2013) Classroom-based action research: revisiting the process as customizable and meaningful professional development for educators. J Pedagog Dev 3(3):38\u201342"},{"key":"773_CR30","doi-asserted-by":"crossref","unstructured":"Ofli F, Chaudhry R, Kurillo G, Vidal R, Bajcsy R (2013) Berkeley mhad: a comprehensive multimodal human action database. In: 2013 IEEE workshop on applications of computer vision (WACV), 53\u201360. IEEE","DOI":"10.1109\/WACV.2013.6474999"},{"issue":"1","key":"773_CR31","doi-asserted-by":"publisher","first-page":"15","DOI":"10.1007\/s12008-017-0372-5","volume":"12","author":"P Orta-Casta\u00f1on","year":"2018","unstructured":"Orta-Casta\u00f1on P, Urbina-Coronado P, Ahuett-Garza H, Hern\u00e1ndez-de Men\u00e9ndez M, Morales-Menendez R (2018) Social collaboration software for virtual teams: case studies. Int J Interact Des Manuf (IJIDeM) 12(1):15\u201324","journal-title":"Int J Interact Des Manuf (IJIDeM)"},{"issue":"3","key":"773_CR32","doi-asserted-by":"publisher","first-page":"395","DOI":"10.1111\/bjop.12290","volume":"109","author":"X Pan","year":"2018","unstructured":"Pan X, Hamilton AFC (2018) Why and how to use virtual reality to study human social interaction: the challenges of exploring a new research landscape. Br J Psychol 109(3):395\u2013417","journal-title":"Br J Psychol"},{"key":"773_CR33","unstructured":"Peiyi L, Zhou X. A 3d coordinate estimation method, device, terminal, and storage medium[P]. China Patent: CN201810628314.4"},{"issue":"4","key":"773_CR34","first-page":"43","volume":"9","author":"D Phutela","year":"2015","unstructured":"Phutela D (2015) The importance of non-verbal communication. IUP J Soft Skills 9(4):43","journal-title":"IUP J Soft Skills"},{"issue":"5","key":"773_CR35","first-page":"407","volume":"18","author":"CA Pierce","year":"1997","unstructured":"Pierce CA, Aguinis H (1997) Using virtual reality technology in organizational behavior research. J Organ. Behav Int J Ind Occup Organ Psychol Behav 18(5):407\u2013410","journal-title":"J Organ. Behav Int J Ind Occup Organ Psychol Behav"},{"key":"773_CR36","doi-asserted-by":"crossref","unstructured":"Plizzari C, Cannici M, Matteucci M (2020) Spatial temporal transformer network for skeleton-based action recognition. arXiv preprint arXiv:2012.06399","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"773_CR37","doi-asserted-by":"crossref","unstructured":"Qi W, Li F, Zhenzhong L (2010) Review on camera calibration. In: 2010 Chinese control and decision conference, 3354\u20133358. IEEE","DOI":"10.1109\/CCDC.2010.5498574"},{"key":"773_CR38","doi-asserted-by":"crossref","unstructured":"Saunders CP, Bennett JA (2019) The immersive experience: how virtual reality can support student learning. Educ Media Tech Yearbook 42:57\u201366","DOI":"10.1007\/978-3-030-27986-8_6"},{"key":"773_CR39","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT, Wang G (2016) Ntu rgb+ d: a large scale dataset for 3d human activity analysis. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"773_CR40","doi-asserted-by":"crossref","unstructured":"Shao H, Qian S, Liu Y (2020) Temporal interlacing network. In: Proceedings of the 34th AAAI Conference on Artificial Intelligence, 11966-11973","DOI":"10.1609\/aaai.v34i07.6872"},{"key":"773_CR41","doi-asserted-by":"crossref","unstructured":"da Silva MV, Marana AN (2019) Human action recognition using 2d poses. In: 2019 8th Brazilian conference on intelligent systems (BRACIS), 747\u2013752. IEEE","DOI":"10.1109\/BRACIS.2019.00134"},{"key":"773_CR42","unstructured":"Soomro K, Zamir AR, Shah M (2012) Ucf101: a dataset of 101 human actions classes from videos in the wild. arXiv preprint arXiv:1212.0402"},{"key":"773_CR43","doi-asserted-by":"crossref","unstructured":"Tran D, Bourdev L, Fergus R, Torresani L, Paluri M (2015) Learning spatiotemporal features with 3d convolutional networks. In: Proceedings of the IEEE international conference on computer vision, 4489\u20134497","DOI":"10.1109\/ICCV.2015.510"},{"issue":"1","key":"773_CR44","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1111\/apps.12290","volume":"70","author":"B Wang","year":"2021","unstructured":"Wang B, Liu Y, Qian J, Parker SK (2021) Achieving effective remote working during the covid-19 pandemic: a work design perspective. Appl Psychol 70(1):16\u201359","journal-title":"Appl Psychol"},{"key":"773_CR45","doi-asserted-by":"crossref","unstructured":"Wei J, Wang H, Yi Y, Li Q, Huang D (2019) P3d-ctn: Pseudo-3d convolutional tube network for spatio-temporal action detection in videos. In: 2019 IEEE international conference on image processing (ICIP), 300\u2013304. IEEE","DOI":"10.1109\/ICIP.2019.8802979"},{"key":"773_CR46","volume-title":"The classroom x-factor: the power of body language and non-verbal communication in teaching","author":"J White","year":"2013","unstructured":"White J, Gardner J (2013) The classroom x-factor: the power of body language and non-verbal communication in teaching. Routledge, London"},{"key":"773_CR47","doi-asserted-by":"crossref","unstructured":"Wood AB (2017) Classroom-based action research with secondary school students of english literature: a teacher-researcher\u2019s reflection. Engl Teach-Pract Cri 16(1):72\u201384","DOI":"10.1108\/ETPC-08-2016-0100"},{"key":"773_CR48","doi-asserted-by":"publisher","first-page":"104071","DOI":"10.1016\/j.foodqual.2020.104071","volume":"87","author":"C Xu","year":"2021","unstructured":"Xu C, Demir-Kaymaz Y, Hartmann C, Menozzi M, Siegrist M (2021) The comparability of consumers\u2019 behavior in virtual reality and real life: a validation study of virtual reality based on a ranking task. Food Qual Prefer 87:104071","journal-title":"Food Qual Prefer"},{"key":"773_CR49","doi-asserted-by":"crossref","unstructured":"Yan S, Xiong Y, Lin D (2018) Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Thirty-second AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"773_CR50","doi-asserted-by":"crossref","unstructured":"Yang C, Xu Y, Shi J, Dai B, Zhou B (2020) Temporal pyramid network for action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, 591\u2013600","DOI":"10.1109\/CVPR42600.2020.00067"},{"key":"773_CR51","doi-asserted-by":"crossref","unstructured":"Zhang S, Liu X, Xiao J (2017) On geometric features for skeleton-based action recognition using multilayer lstm networks. In: 2017 IEEE winter conference on applications of computer vision (WACV), 148\u2013157","DOI":"10.1109\/WACV.2017.24"},{"issue":"11","key":"773_CR52","doi-asserted-by":"publisher","first-page":"1330","DOI":"10.1109\/34.888718","volume":"22","author":"Z Zhang","year":"2000","unstructured":"Zhang Z (2000) A flexible new technique for camera calibration. IEEE Trans Pattern Anal Mach Intell 22(11):1330\u20131334","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"773_CR53","doi-asserted-by":"crossref","unstructured":"Zhao Z, Zou W, Wang J (2020) Action recognition based on c3d network and adaptive keyframe extraction. In: 2020 IEEE 6th international conference on computer and communications (ICCC), 2441\u20132447. IEEE","DOI":"10.1109\/ICCC51575.2020.9345274"},{"issue":"11","key":"773_CR54","doi-asserted-by":"publisher","first-page":"1633","DOI":"10.1109\/LSP.2019.2942739","volume":"26","author":"J Zhu","year":"2019","unstructured":"Zhu J, Zou W, Zhu Z, Xu L, Huang G (2019) Action machine: toward person-centric action recognition in videos. IEEE Signal Process Lett 26(11):1633\u20131637","journal-title":"IEEE Signal Process Lett"}],"container-title":["Virtual Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10055-023-00773-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10055-023-00773-4\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10055-023-00773-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,9]],"date-time":"2025-04-09T10:56:11Z","timestamp":1744196171000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10055-023-00773-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,2,24]]},"references-count":54,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,9]]}},"alternative-id":["773"],"URL":"https:\/\/doi.org\/10.1007\/s10055-023-00773-4","relation":{},"ISSN":["1359-4338","1434-9957"],"issn-type":[{"value":"1359-4338","type":"print"},{"value":"1434-9957","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,2,24]]},"assertion":[{"value":"5 July 2021","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 February 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 February 2023","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 to have no conflicts of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflicts of interest"}},{"value":"Informed consent was obtained from all individual participants included in the study.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Informed consent"}}]}}