{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T20:40:47Z","timestamp":1725741647567},"reference-count":49,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,10,1]],"date-time":"2021-10-01T00:00:00Z","timestamp":1633046400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Journal of Visual Communication and Image Representation"],"published-print":{"date-parts":[[2021,10]]},"DOI":"10.1016\/j.jvcir.2021.103304","type":"journal-article","created":{"date-parts":[[2021,9,4]],"date-time":"2021-09-04T14:46:55Z","timestamp":1630766815000},"page":"103304","update-policy":"http:\/\/dx.doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":7,"special_numbering":"C","title":["What and how well you exercised? An efficient analysis framework for fitness actions"],"prefix":"10.1016","volume":"80","author":[{"given":"Jianwei","family":"Li","sequence":"first","affiliation":[]},{"given":"Qingrui","family":"Hu","sequence":"additional","affiliation":[]},{"given":"Tianxiao","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Siqi","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Yanfei","family":"Shen","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.jvcir.2021.103304_b0005","series-title":"IECON 2016\u201342nd Annual Conference of the IEEE Industrial Electronics Society","article-title":"Imu-based smart fitness devices for weight training, in","author":"Hausberger","year":"2016"},{"key":"10.1016\/j.jvcir.2021.103304_b0010","article-title":"A hybrid hierarchical framework for gym physical activity recognition and measurement using wearable sensors","author":"Qi","year":"2018","journal-title":"IEEE Internet of Things Journal"},{"key":"10.1016\/j.jvcir.2021.103304_b0015","doi-asserted-by":"crossref","DOI":"10.4028\/b-cJP8WQ","article-title":"Automatic badminton action recognition using rgb-d sensor","author":"Ting","year":"2014","journal-title":"Advanced Materials Research"},{"key":"10.1016\/j.jvcir.2021.103304_b0020","doi-asserted-by":"crossref","first-page":"611","DOI":"10.3390\/app10020611","article-title":"Design and validation of rule-based expert system by using kinect v2 for real-time athlete support","volume":"10","author":"\u00d6r\u00fcc\u00fc","year":"2020","journal-title":"Applied Sciences"},{"key":"10.1016\/j.jvcir.2021.103304_b0025","doi-asserted-by":"crossref","first-page":"1212","DOI":"10.1109\/TCSVT.2017.2655624","article-title":"A survey of content-aware video analysis for sports","volume":"28","author":"Shih","year":"2017","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"10.1016\/j.jvcir.2021.103304_b0030","doi-asserted-by":"crossref","first-page":"102700","DOI":"10.1016\/j.jvcir.2019.102700","article-title":"Hierarchical learning-guided human motion quality assessment in big data environment","volume":"71","author":"Huang","year":"2020","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2021.103304_b0035","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"499","article-title":"Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks","author":"Wang","year":"2017"},{"key":"10.1016\/j.jvcir.2021.103304_b0040","doi-asserted-by":"crossref","unstructured":"S. Yan, Y. Xiong, D. Lin, Spatial temporal graph convolutional networks for skeleton-based action recognition, in: Thirty-Second AAAI Conference on Artificial Intelligence, 2018.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"10.1016\/j.jvcir.2021.103304_b0045","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6016","article-title":"End-to-end learning of motion representation for video understanding","author":"Fan","year":"2018"},{"key":"10.1016\/j.jvcir.2021.103304_b0050","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"7083","article-title":"Tsm: Temporal shift module for efficient video understanding","author":"Lin","year":"2019"},{"key":"10.1016\/j.jvcir.2021.103304_b0055","doi-asserted-by":"crossref","first-page":"102846","DOI":"10.1016\/j.jvcir.2020.102846","article-title":"Spatial-temporal saliency action mask attention network for action recognition","volume":"71","author":"Jiang","year":"2020","journal-title":"J. Vis. Commun. Image Represent."},{"key":"10.1016\/j.jvcir.2021.103304_b0060","first-page":"3247","article-title":"Skeleton-based action recognition with multi-stream adaptive graph convolutional networks","author":"Shi","year":"2019","journal-title":"IEEE"},{"key":"10.1016\/j.jvcir.2021.103304_b0065","doi-asserted-by":"crossref","unstructured":"C. Plizzari, M. Cannici, M. Matteucci, Spatial temporal transformer network for skeleton-based action recognition, arXiv preprint arXiv:2008.07404 (2020).","DOI":"10.1007\/978-3-030-68796-0_50"},{"key":"10.1016\/j.jvcir.2021.103304_b0070","unstructured":"F. Zhou, F. Torre, Canonical time warping for alignment of human behavior, in: Advances in neural information processing systems, 2009, pp. 2286\u20132294."},{"key":"10.1016\/j.jvcir.2021.103304_b0075","series-title":"in: Computer Vision and Pattern Recognition (CVPR), 2012 IEEE Conference on","article-title":"Generalized time warping for multi-modal alignment of human motion","author":"Zhou","year":"2012"},{"key":"10.1016\/j.jvcir.2021.103304_b0080","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"667","article-title":"Human motion analysis with deep metric learning","author":"Coskun","year":"2018"},{"key":"10.1016\/j.jvcir.2021.103304_b0085","doi-asserted-by":"crossref","first-page":"103687","DOI":"10.1016\/j.compbiomed.2020.103687","article-title":"A review of computational approaches for evaluation of rehabilitation exercises","volume":"119","author":"Liao","year":"2020","journal-title":"Comput. Biol. Med."},{"year":"2020","series-title":"An Asymmetric Modeling for Action Assessment","author":"Gao","key":"10.1016\/j.jvcir.2021.103304_b0090"},{"key":"10.1016\/j.jvcir.2021.103304_b0095","doi-asserted-by":"crossref","unstructured":"P. Parmar, B.T. Morris, Learning to score olympic events, in: IEEE International Conference on Computer Vision Workshop, 2016.","DOI":"10.1109\/CVPRW.2017.16"},{"key":"10.1016\/j.jvcir.2021.103304_b0100","article-title":"Assessing the quality of actions","author":"Pirsiavash","year":"2014","journal-title":"European Conference on Computer Vision"},{"key":"10.1016\/j.jvcir.2021.103304_b0105","series-title":"in: 2020 IEEE International Conference on Multimedia & Expo Workshops (ICMEW)","first-page":"1","article-title":"Efficient fitness action analysis based on spatio-temporal feature encoding","author":"Li","year":"2020"},{"key":"10.1016\/j.jvcir.2021.103304_b0110","series-title":"2007 IEEE 11th international conference on computer vision","first-page":"1","article-title":"What, where and who? classifying events by scene and object recognition","author":"Li","year":"2007"},{"year":"2014","series-title":"Action recognition in realistic sports videos","author":"Soomro","key":"10.1016\/j.jvcir.2021.103304_b0115"},{"key":"10.1016\/j.jvcir.2021.103304_b0120","series-title":"Proceedings of the European Conference on Computer Vision (ECCV)","first-page":"513","article-title":"Resound: Towards action recognition without representation bias","author":"Li","year":"2018"},{"key":"10.1016\/j.jvcir.2021.103304_b0125","series-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops","first-page":"1038","article-title":"Yoga-82: a new dataset for fine-grained classification of human poses","author":"Verma","year":"2020"},{"key":"10.1016\/j.jvcir.2021.103304_b0130","first-page":"1010","article-title":"Ntu rgb+d: A large scale dataset for 3d human activity analysis","author":"Shahroudy","year":"2016","journal-title":"IEEE Computer Society"},{"key":"10.1016\/j.jvcir.2021.103304_b0135","article-title":"Ntu rgb+d 120: A large-scale benchmark for 3d human activity understanding","author":"Liu","year":"2019","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2021.103304_b0140","article-title":"The kinetics human action video dataset","author":"Kay","year":"2017","journal-title":"CoRR abs\/1705.06950"},{"key":"10.1016\/j.jvcir.2021.103304_b0145","doi-asserted-by":"crossref","first-page":"257","DOI":"10.1109\/34.910878","article-title":"The recognition of human movement using temporal templates","volume":"23","author":"Bobick","year":"2001","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.jvcir.2021.103304_b0150","doi-asserted-by":"crossref","unstructured":"H. Wang, A. Kl\u00e4ser, C. Schmid, C.-L. Liu, Action recognition by dense trajectories, in: CVPR 2011, IEEE, 2011, pp. 3169\u20133176.","DOI":"10.1109\/CVPR.2011.5995407"},{"key":"10.1016\/j.jvcir.2021.103304_b0155","article-title":"Action recognition with improved trajectories","author":"Wang","year":"2014","journal-title":"IEEE International Conference on Computer Vision"},{"key":"10.1016\/j.jvcir.2021.103304_b0160","article-title":"Multi-view action recognition using cross-view video prediction","author":"Vyas","year":"2020","journal-title":"European Conference on Computer Vision"},{"key":"10.1016\/j.jvcir.2021.103304_b0165","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1831","article-title":"Multi-context attention for human pose estimation","author":"Chu","year":"2017"},{"key":"10.1016\/j.jvcir.2021.103304_b0170","doi-asserted-by":"crossref","unstructured":"A. Newell, K. Yang, J. Deng, Stacked hourglass networks for human pose estimation, in: European conference on computer vision, Springer, 2016, pp. 483\u2013499.","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"10.1016\/j.jvcir.2021.103304_b0175","series-title":"in: Proceedings of the IEEE International Conference on Computer Vision","first-page":"1281","article-title":"Learning feature pyramids for human pose estimation","author":"Yang","year":"2017"},{"key":"10.1016\/j.jvcir.2021.103304_b0180","doi-asserted-by":"crossref","first-page":"44","DOI":"10.1145\/3072959.3073596","article-title":"Vnect: Real-time 3d human pose estimation with a single rgb camera","volume":"36","author":"Mehta","year":"2017","journal-title":"Acm Transactions on Graphics"},{"key":"10.1016\/j.jvcir.2021.103304_b0185","series-title":"Proceedings of the IEEE International Conference on Computer Vision","first-page":"2602","article-title":"Compositional human pose regression","author":"Sun","year":"2017"},{"key":"10.1016\/j.jvcir.2021.103304_b0190","unstructured":"P.J. Besl, N.D. McKay, Method for registration of 3-d shapes, in: Sensor Fusion IV: Control Paradigms and Data Structures, volume 1611, International Society for Optics and Photonics, 1992, pp. 586\u2013607."},{"key":"10.1016\/j.jvcir.2021.103304_b0195","unstructured":"H. Doughty, D. Damen, W. Mayol-Cuevas, Whos better, whos best: Skill determination in video using deep ranking, CoRR, abs\/1703.0 (2017) 6057\u20136066."},{"key":"10.1016\/j.jvcir.2021.103304_b0200","first-page":"222","article-title":"An asymmetric modeling for action assessment","author":"Gao","year":"2020","journal-title":"European Conference on Computer Vision, Springer"},{"key":"10.1016\/j.jvcir.2021.103304_b0205","doi-asserted-by":"crossref","unstructured":"J. Scott, R. Collins, C. Funk, Y. Liu, 4d model-based spatiotemporal alignment of scripted taiji quan sequences, in: IEEE International Conference on Computer Vision Workshop, 2017.","DOI":"10.1109\/ICCVW.2017.99"},{"key":"10.1016\/j.jvcir.2021.103304_b0210","doi-asserted-by":"crossref","unstructured":"Z. Cao, G. Hidalgo, T. Simon, S.-E. Wei, Y. Sheikh, OpenPose: realtime multi-person 2D pose estimation using Part Affinity Fields, in: arXiv preprint arXiv:1812.08008, 2018.","DOI":"10.1109\/CVPR.2017.143"},{"key":"10.1016\/j.jvcir.2021.103304_b0215","unstructured":"J. Weston, C. Watkins, Support vector machines for multi-class pattern recognition, in: Proc European Symposium on Artificial Neural Networks, 1999."},{"key":"10.1016\/j.jvcir.2021.103304_b0220","doi-asserted-by":"crossref","unstructured":"C. Schuldt, I. Laptev, B. Caputo, Recognizing human actions: a local svm approach, in: Proceedings of the 17th International Conference on Pattern Recognition, 2004. ICPR 2004, volume 3, IEEE, 2004, pp. 32\u201336.","DOI":"10.1109\/ICPR.2004.1334462"},{"key":"10.1016\/j.jvcir.2021.103304_b0225","first-page":"2247","article-title":"Actions as space-time shapes, Transactions on Pattern Analysis and Machine","volume":"29","author":"Gorelick","year":"2007","journal-title":"Intelligence"},{"key":"10.1016\/j.jvcir.2021.103304_b0230","doi-asserted-by":"crossref","unstructured":"J.J. Mor\u00e9, The levenberg-marquardt algorithm: implementation and theory, in: Numerical analysis, Springer, 1978, pp. 105\u2013116.","DOI":"10.1007\/BFb0067700"},{"key":"10.1016\/j.jvcir.2021.103304_b0235","doi-asserted-by":"crossref","first-page":"299","DOI":"10.1007\/s11263-007-0122-4","article-title":"Unsupervised learning of human action categories using spatial-temporal words","volume":"79","author":"Niebles","year":"2008","journal-title":"Int. J. Comput. Vision"},{"key":"10.1016\/j.jvcir.2021.103304_b0240","series-title":"in: Fifteenth Iapr International Conference on Machine Vision Applications","article-title":"Enhancing discriminability of randomized time warping for motion recognition","author":"De Souza","year":"2017"},{"key":"10.1016\/j.jvcir.2021.103304_b0245","doi-asserted-by":"crossref","unstructured":"C. Thurau, Behavior histograms for action recognition and human detection, in: Workshop on Human Motion, Springer, 2007, pp. 299\u2013312.","DOI":"10.1007\/978-3-540-75703-0_21"}],"container-title":["Journal of Visual Communication and Image Representation"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320321002017?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1047320321002017?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T19:59:55Z","timestamp":1725739195000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1047320321002017"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,10]]},"references-count":49,"alternative-id":["S1047320321002017"],"URL":"https:\/\/doi.org\/10.1016\/j.jvcir.2021.103304","relation":{},"ISSN":["1047-3203"],"issn-type":[{"type":"print","value":"1047-3203"}],"subject":[],"published":{"date-parts":[[2021,10]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"What and how well you exercised? An efficient analysis framework for fitness actions","name":"articletitle","label":"Article Title"},{"value":"Journal of Visual Communication and Image Representation","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.jvcir.2021.103304","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Published by Elsevier Inc.","name":"copyright","label":"Copyright"}],"article-number":"103304"}}