{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,3]],"date-time":"2026-06-03T08:51:25Z","timestamp":1780476685545,"version":"3.54.1"},"reference-count":23,"publisher":"Springer Science and Business Media LLC","issue":"3","license":[{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T00:00:00Z","timestamp":1626825600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/100007219","name":"Natural Science Foundation of Shanghai","doi-asserted-by":"publisher","award":["18ZR1415100"],"award-info":[{"award-number":["18ZR1415100"]}],"id":[{"id":"10.13039\/100007219","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61703262"],"award-info":[{"award-number":["61703262"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Ambient Intell Human Comput"],"published-print":{"date-parts":[[2023,3]]},"DOI":"10.1007\/s12652-021-03399-z","type":"journal-article","created":{"date-parts":[[2021,7,21]],"date-time":"2021-07-21T07:04:01Z","timestamp":1626851041000},"page":"1877-1887","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":5,"title":["A sequence models-based real-time multi-person action recognition method with monocular vision"],"prefix":"10.1007","volume":"14","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5077-9150","authenticated-orcid":false,"given":"Aolei","family":"Yang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wei","family":"Lu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Wasif","family":"Naeem","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ling","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Minrui","family":"Fei","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2021,7,21]]},"reference":[{"key":"3399_CR1","doi-asserted-by":"crossref","unstructured":"Cao Z, Hidalgo G, Simon T et al (2017) Realtime multi-person 2D pose estimation using part affinity fields. In proceedings of the IEEE conference on computer vision and pattern recognition, pp 7291\u20137299","DOI":"10.1109\/CVPR.2017.143"},{"key":"3399_CR2","doi-asserted-by":"crossref","unstructured":"Cheron G, Laptev I, Schmid C (2015) P-CNN: pose-based CNN features for action recognition. Proceedings of the IEEE international conference on computer vision (ICCV), pp 3218\u20133226","DOI":"10.1109\/ICCV.2015.368"},{"issue":"99","key":"3399_CR3","first-page":"1347","volume":"27","author":"W Du","year":"2017","unstructured":"Du W, Wang Y, Qiao Y (2017) Recurrent spatial-temporal attention network for action recognition in videos. IEEE Trans Image Process 27(99):1347\u20131360","journal-title":"IEEE Trans Image Process"},{"key":"3399_CR4","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. 2015 IEEE conference on computer vision and pattern recognition (CVPR), pp 1110\u20131118"},{"issue":"3","key":"3399_CR5","doi-asserted-by":"publisher","first-page":"475","DOI":"10.1007\/s10489-013-0427-7","volume":"39","author":"M Fahim","year":"2013","unstructured":"Fahim M, Fatima I et al (2013) EFM: evolutionary fuzzy model for dynamic activities recognition using a smartphone accelerometer. Appl Intell 39(3):475\u2013488","journal-title":"Appl Intell"},{"issue":"3","key":"3399_CR6","doi-asserted-by":"publisher","first-page":"1192","DOI":"10.1109\/SURV.2012.110112.00192","volume":"15","author":"Lara","year":"2013","unstructured":"Lara, Oscar D, Labrador et al (2013) A survey on human activity recognition using wearable sensors. IEEE Commun Surv Tutor 15(3):1192\u20131209","journal-title":"IEEE Commun Surv Tutor"},{"key":"3399_CR7","first-page":"740","volume-title":"European conference on computer vision","author":"TY Lin","year":"2014","unstructured":"Lin TY, Maire M, Belongie S et al (2014) Microsoft coco: common objects in context. European conference on computer vision. Springer, Cham, pp 740\u2013755"},{"issue":"12","key":"3399_CR8","doi-asserted-by":"publisher","first-page":"3007","DOI":"10.1109\/TPAMI.2017.2771306","volume":"40","author":"J Liu","year":"2017","unstructured":"Liu J, Shahroudy A, Xu D et al (2017a) Skeleton-based action recognition using spatio-temporal LSTM network with trust gates. IEEE Trans Pattern Anal Mach Intell 40(12):3007\u20133021","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"3399_CR9","doi-asserted-by":"publisher","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","volume":"68","author":"M Liu","year":"2017","unstructured":"Liu M, Liu H, Chen C (2017b) Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn 68:346\u2013362","journal-title":"Pattern Recogn"},{"key":"3399_CR10","doi-asserted-by":"crossref","unstructured":"Peng X, Schmid C (2016) Multi-region two-stream r-CNN for action detection. Proceedings of European conference on computer vision (ECCV), pp 744\u2013759","DOI":"10.1007\/978-3-319-46493-0_45"},{"key":"3399_CR11","doi-asserted-by":"crossref","unstructured":"Peng X, Zou C, Qiao Y et al (2014) Action recognition with stacked fisher vectors. Proceedings of European conference on computer vision (ECCV), pp 581\u2013595","DOI":"10.1007\/978-3-319-10602-1_38"},{"key":"3399_CR13","doi-asserted-by":"publisher","first-page":"65","DOI":"10.1016\/j.neucom.2020.02.096","volume":"399","author":"B Sheng","year":"2020","unstructured":"Sheng B, Li J, Xiao F et al (2020) Multilayer deep features with multiple kernel learning for action recognition. Neurocomputing 399:65\u201374","journal-title":"Neurocomputing"},{"issue":"6","key":"3399_CR14","doi-asserted-by":"publisher","first-page":"10146","DOI":"10.3390\/s140610146","volume":"14","author":"M Shoaib","year":"2014","unstructured":"Shoaib M, Bosch S et al (2014) Fusion of smartphone motion sensors for physical activity recognition. Sensors 14(6):10146\u201310176","journal-title":"Sensors"},{"key":"3399_CR15","doi-asserted-by":"crossref","unstructured":"Singh G, Saha S, Sapienza M (2017) Online real-time multiple spatiotemporal action localisation and prediction. Proceedings of the IEEE conference on computer vision (ICCV), pp 1\u201310","DOI":"10.1109\/ICCV.2017.393"},{"issue":"3","key":"3399_CR16","doi-asserted-by":"publisher","first-page":"748","DOI":"10.1109\/TCSVT.2019.2896029","volume":"30","author":"X Song","year":"2019","unstructured":"Song X, Lan C, Zeng W et al (2019) Temporal-spatial mapping for action recognition. IEEE Trans Circuits Syst Video Technol 30(3):748\u2013759","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"3399_CR17","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.patcog.2018.01.020","volume":"79","author":"Z Tu","year":"2018","unstructured":"Tu Z, Xie W, Qin Q et al (2018) Multi-stream CNN: learning representations based on human-related regions for action recognition. Pattern Recogn 79:32\u201343","journal-title":"Pattern Recogn"},{"issue":"1","key":"3399_CR18","doi-asserted-by":"publisher","first-page":"60","DOI":"10.1007\/s11263-012-0594-8","volume":"103","author":"H Wang","year":"2013","unstructured":"Wang H, Klser A, Schmid C et al (2013) Dense trajectories and motion boundary descriptors for action recognition. Int J Comput Vision 103(1):60\u201379","journal-title":"Int J Comput Vision"},{"key":"3399_CR19","doi-asserted-by":"publisher","first-page":"43","DOI":"10.1016\/j.knosys.2018.05.029","volume":"158","author":"P Wang","year":"2018","unstructured":"Wang P, Li W, Li C et al (2018) Action recognition based on joint trajectory maps with convolutional neural networks. Knowl-Based Syst 158:43\u201353","journal-title":"Knowl-Based Syst"},{"key":"3399_CR20","doi-asserted-by":"crossref","unstructured":"Wojke N, Bewley A, Paulus D (2017) Simple online and real-time tracking with a deep association metric. In 2017 IEEE international conference on image processing (ICIP), pp 3645\u20133649","DOI":"10.1109\/ICIP.2017.8296962"},{"issue":"3","key":"3399_CR21","doi-asserted-by":"publisher","first-page":"567","DOI":"10.1109\/TCSVT.2017.2665359","volume":"27","author":"K Xu","year":"2017","unstructured":"Xu K, Jiang X, Sun T (2017) Two-stream dictionary learning architecture for action recognition. IEEE Trans Circuits Syst Video Technol 27(3):567\u2013576","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"issue":"10","key":"3399_CR22","doi-asserted-by":"publisher","first-page":"2951","DOI":"10.1109\/TNNLS.2018.2886008","volume":"30","author":"Z Xu","year":"2019","unstructured":"Xu Z, Hu R, Chen J et al (2019) Semi-supervised discriminant multi-manifold analysis for action recognition. IEEE Trans Neural Netw Learn Syst 30(10):2951\u20132962","journal-title":"IEEE Trans Neural Netw Learn Syst"},{"issue":"1","key":"3399_CR23","doi-asserted-by":"publisher","first-page":"2","DOI":"10.1016\/j.jvcir.2013.03.001","volume":"25","author":"X Yang","year":"2014","unstructured":"Yang X, Tian Y (2014) Effective 3D action recognition using eigen-joints. J vis Commun Image Represent 25(1):2\u201311","journal-title":"J vis Commun Image Represent"},{"key":"3399_CR24","first-page":"115640","volume":"80","author":"Y Yi","year":"2020","unstructured":"Yi Y, Li A, Zhou X (2020) Human action recognition based on action relevance weighted encoding. Signal Process 80:115640","journal-title":"Signal Process"}],"container-title":["Journal of Ambient Intelligence and Humanized Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-021-03399-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s12652-021-03399-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s12652-021-03399-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,2]],"date-time":"2023-03-02T16:52:48Z","timestamp":1677775968000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s12652-021-03399-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,7,21]]},"references-count":23,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2023,3]]}},"alternative-id":["3399"],"URL":"https:\/\/doi.org\/10.1007\/s12652-021-03399-z","relation":{},"ISSN":["1868-5137","1868-5145"],"issn-type":[{"value":"1868-5137","type":"print"},{"value":"1868-5145","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,7,21]]},"assertion":[{"value":"4 November 2020","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 July 2021","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 July 2021","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declaration"}},{"value":"On behalf of all authors, the corresponding author states that there is no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}