{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T14:29:48Z","timestamp":1775744988634,"version":"3.50.1"},"reference-count":82,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2021,6,1]],"date-time":"2021-06-01T00:00:00Z","timestamp":1622505600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-004"}],"funder":[{"DOI":"10.13039\/501100012328","name":"Beijing Key Laboratory of Network System Architecture and Convergence","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012328","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Applied Soft Computing"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1016\/j.asoc.2021.107236","type":"journal-article","created":{"date-parts":[[2021,3,2]],"date-time":"2021-03-02T03:02:12Z","timestamp":1614654132000},"page":"107236","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":35,"special_numbering":"C","title":["Multi-scale skeleton adaptive weighted GCN for skeleton-based human action recognition in IoT"],"prefix":"10.1016","volume":"104","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0694-6246","authenticated-orcid":false,"given":"Weiyao","family":"Xu","sequence":"first","affiliation":[]},{"given":"Muqing","family":"Wu","sequence":"additional","affiliation":[]},{"given":"Jie","family":"Zhu","sequence":"additional","affiliation":[]},{"given":"Min","family":"Zhao","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"key":"10.1016\/j.asoc.2021.107236_b1","doi-asserted-by":"crossref","unstructured":"V. Gajjar, A. Gurnani, Y. Khandhediya, Human detection and tracking for video surveillance A cognitive science approach, in: 2017 IEEE International Conference on Computer Vision Workshops (ICCVW), 2018.","DOI":"10.1109\/ICCVW.2017.330"},{"key":"10.1016\/j.asoc.2021.107236_b2","series-title":"Multi-source multi-modal activity recognition in aerial video surveillance","author":"Hammoud","year":"2018"},{"key":"10.1016\/j.asoc.2021.107236_b3","article-title":"Automatic human activity recognition in video surveillance system using versatile quadric activity portion classification method","author":"Karthikeswaran","year":"2019","journal-title":"J. Med. Imaging Health Inform."},{"key":"10.1016\/j.asoc.2021.107236_b4","article-title":"Rapid action recognition system for human-computer interaction","author":"Haifeng","year":"2019","journal-title":"Comput. Eng. Appl."},{"key":"10.1016\/j.asoc.2021.107236_b5","article-title":"Design of somatosensory control system based on human-computer interaction technology","author":"Linqiang","year":"2019","journal-title":"Mod. Inf. Technol."},{"key":"10.1016\/j.asoc.2021.107236_b6","doi-asserted-by":"crossref","DOI":"10.1016\/j.concog.2018.11.008","article-title":"Action co-representation and the sense of agency during a joint Simon task: Comparing human and machine co-agents","author":"Sahai","year":"2019","journal-title":"Conscious. Cogn."},{"key":"10.1016\/j.asoc.2021.107236_b7","doi-asserted-by":"crossref","unstructured":"P.C. Nordbeck, M. Lamb, P. Silva, Modelling and simulating action dynamics in underconstrained tasks in virtual reality, in: International Conference on Perception and Action, 2020.","DOI":"10.31234\/osf.io\/u9amh"},{"issue":"11","key":"10.1016\/j.asoc.2021.107236_b8","doi-asserted-by":"crossref","first-page":"2761","DOI":"10.1007\/s00221-019-05642-8","article-title":"Virtually the same? How impaired sensory information in virtual reality may disrupt vision for action","volume":"237","author":"Harris","year":"2019","journal-title":"Exp. Brain Res."},{"key":"10.1016\/j.asoc.2021.107236_b9","series-title":"Learned human-agent decision-making, communication and joint action in a virtual reality environment","author":"Pilarski","year":"2019"},{"issue":"4","key":"10.1016\/j.asoc.2021.107236_b10","doi-asserted-by":"crossref","first-page":"920","DOI":"10.1109\/TCYB.2016.2533424","article-title":"An efficient method for traffic sign recognition based on extreme learning machine","volume":"47","author":"Huang","year":"2016","journal-title":"IEEE Trans. Cybern."},{"issue":"2","key":"10.1016\/j.asoc.2021.107236_b11","doi-asserted-by":"crossref","first-page":"161","DOI":"10.1049\/iet-cvi.2016.0027","article-title":"Fitting-based optimisation for image visual salient object detection","volume":"11","author":"Niu","year":"2017","journal-title":"IET Comput. Vis."},{"key":"10.1016\/j.asoc.2021.107236_b12","doi-asserted-by":"crossref","DOI":"10.1016\/j.knosys.2017.09.033","article-title":"Robust co-clustering via dual local learning and high-order matrix factorization","volume":"138","author":"Wang","year":"2017","journal-title":"Knowl.-Based Syst."},{"issue":"5","key":"10.1016\/j.asoc.2021.107236_b13","doi-asserted-by":"crossref","first-page":"1153","DOI":"10.1007\/s00500-014-1329-2","article-title":"A PSO-based timing-driven Octilinear Steiner tree algorithm forVLSI routing considering bend reduction","volume":"19","author":"Liu","year":"2015","journal-title":"Soft Comput."},{"key":"10.1016\/j.asoc.2021.107236_b14","doi-asserted-by":"crossref","DOI":"10.1016\/j.neucom.2017.04.052","article-title":"A multi-label classification algorithm based on kernel extreme learning machine","author":"Luo","year":"2017","journal-title":"Neurocomputing"},{"issue":"10","key":"10.1016\/j.asoc.2021.107236_b15","article-title":"Relative influence maximization in competitive social networks","year":"2017","journal-title":"ence China Inf. ences"},{"key":"10.1016\/j.asoc.2021.107236_b16","article-title":"LGIEM: Global and local node influence based community detection","volume":"105","author":"Ma","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.asoc.2021.107236_b17","first-page":"1","article-title":"Human action recognition using multilevel depth motion maps","author":"Weiyao","year":"2019","journal-title":"IEEE Access"},{"key":"10.1016\/j.asoc.2021.107236_b18","article-title":"Monitoring technology and algorithm based on depth sensor","author":"Peng-Cheng","year":"2019","journal-title":"Transducer Microsyst. Technol."},{"key":"10.1016\/j.asoc.2021.107236_b19","article-title":"Real-time head pose estimation based on RGBD","author":"Guo-Jun","year":"2019","journal-title":"J. Graph."},{"key":"10.1016\/j.asoc.2021.107236_b20","article-title":"Representation learning of temporal dynamics for skeleton-based action recognition","author":"Yong","year":"2016","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.asoc.2021.107236_b21","doi-asserted-by":"crossref","unstructured":"R. Vemulapalli, F. Arrate, R. Chellappa, Human action recognition by representing 3D skeletons as points in a Lie group, in: 2014 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2014.","DOI":"10.1109\/CVPR.2014.82"},{"key":"10.1016\/j.asoc.2021.107236_b22","series-title":"Rolling rotations for recognizing human actions from 3D skeletal data","first-page":"4471","author":"Vemulapalli","year":"2016"},{"key":"10.1016\/j.asoc.2021.107236_b23","doi-asserted-by":"crossref","unstructured":"P. Koniusz, A. Cherian, F. Porikli, Tensor representations via kernel linearization for action recognition from 3D skeletons, in: European Conference on Computer Vision, 2016.","DOI":"10.1007\/978-3-319-46493-0_3"},{"key":"10.1016\/j.asoc.2021.107236_b24","doi-asserted-by":"crossref","first-page":"25","DOI":"10.1016\/j.patcog.2019.03.031","article-title":"Scalable and compact 3D action recognition with approximated RBF kernel machines","volume":"93","author":"Cavazza","year":"2019","journal-title":"Pattern Recognit."},{"issue":"10","key":"10.1016\/j.asoc.2021.107236_b25","first-page":"1","article-title":"Action recognition from arbitrary views using transferable dictionary learning","volume":"PP","author":"Zhang","year":"2018","journal-title":"IEEE Trans. Image Process."},{"issue":"nov.1","key":"10.1016\/j.asoc.2021.107236_b26","doi-asserted-by":"crossref","first-page":"13","DOI":"10.1016\/j.patrec.2017.02.001","article-title":"Learning features combination for human action recognition from skeleton sequences","volume":"99","author":"Luvizon","year":"2017","journal-title":"Pattern Recognit. Lett."},{"key":"10.1016\/j.asoc.2021.107236_b27","doi-asserted-by":"crossref","first-page":"418","DOI":"10.1016\/j.ins.2015.04.034","article-title":"Human action recognition via multi-task learning base on spatialctemporal feature","volume":"320","author":"Guo","year":"2015","journal-title":"Inform. Sci."},{"issue":"4","key":"10.1016\/j.asoc.2021.107236_b28","article-title":"Rotation-based spatialctemporal feature learning from skeleton sequences for action recognition","volume":"14","author":"Liu","year":"2020","journal-title":"Signal Imag. Video Process."},{"issue":"5","key":"10.1016\/j.asoc.2021.107236_b29","first-page":"989","article-title":"Multilayer obstacle-avoiding X-Architecture steiner minimal tree construction based on particle swarm optimization","volume":"45","author":"Liu","year":"2015","journal-title":"IEEE Trans. Cybern."},{"issue":"11","key":"10.1016\/j.asoc.2021.107236_b30","article-title":"A unified algorithm based on HTS and self-adapting PSO for the construction of octagonal and rectilinear SMT","author":"Liu","year":"2019","journal-title":"Soft Comput."},{"key":"10.1016\/j.asoc.2021.107236_b31","series-title":"Deep learning on Lie groups for skeleton-based action recognition","author":"Huang","year":"2016"},{"key":"10.1016\/j.asoc.2021.107236_b32","article-title":"Discriminative spatio-temporal pyramid compact representations algorithm","author":"Xuehong","year":"2018","journal-title":"Comput. Eng. Appl."},{"key":"10.1016\/j.asoc.2021.107236_b33","doi-asserted-by":"crossref","unstructured":"I. Lee, D. Kim, S. Kang, S. Lee, Ensemble deep learning for skeleton-based action recognition using temporal sliding LSTM networks, in: 2017 IEEE International Conference on Computer Vision (ICCV), 2017.","DOI":"10.1109\/ICCV.2017.115"},{"issue":"99","key":"10.1016\/j.asoc.2021.107236_b34","first-page":"1","article-title":"Sample fusion network: An end-to-end data augmentation network for skeleton-based human action recognition","volume":"PP","author":"Meng","year":"2019","journal-title":"IEEE Trans. Image Process."},{"key":"10.1016\/j.asoc.2021.107236_b35","series-title":"Symbiotic graph neural networks for 3D skeleton-based human action recognition and motion prediction","author":"Li","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b36","series-title":"Actional-structural graph convolutional networks for skeleton-based action recognition","author":"Li","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b37","doi-asserted-by":"crossref","unstructured":"K. Cheng, Y. Zhang, X. He, W. Chen, H. Lu, Skeleton-based action recognition with shift graph convolutional network, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"10.1016\/j.asoc.2021.107236_b38","doi-asserted-by":"crossref","unstructured":"A. Graves, A.R. Mohamed, G. Hinton, Speech recognition with deep recurrent neural networks, in: IEEE International Conference on Acoustics, 2013.","DOI":"10.1109\/ICASSP.2013.6638947"},{"key":"10.1016\/j.asoc.2021.107236_b39","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2020.107511","article-title":"Skeleton-based action recognition with hierarchical spatial reasoning and temporal stack learning network","author":"Si","year":"2020","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.asoc.2021.107236_b40","series-title":"Skeleton-based action recognition with spatial reasoning and temporal stack learning","author":"Si","year":"2018"},{"key":"10.1016\/j.asoc.2021.107236_b41","series-title":"Exploiting inter-frame regional correlation for efficient action recognition","author":"Xu","year":"2020"},{"issue":"oct.25","key":"10.1016\/j.asoc.2021.107236_b42","doi-asserted-by":"crossref","first-page":"50","DOI":"10.1016\/j.neucom.2016.06.078","article-title":"Sparse coding extreme learning machine for classification","volume":"261","author":"Yu","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2021.107236_b43","doi-asserted-by":"crossref","unstructured":"C. Li, Q. Zhong, D. Xie, S. Pu, Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation, in: Twenty-Seventh International Joint Conference on Artificial Intelligence IJCAI-18, 2018.","DOI":"10.24963\/ijcai.2018\/109"},{"key":"10.1016\/j.asoc.2021.107236_b44","series-title":"Make skeleton-based action recognition model smaller, faster and better","author":"Yang","year":"2019"},{"issue":"3","key":"10.1016\/j.asoc.2021.107236_b45","first-page":"538","article-title":"Two-stream temporal convolutional networks for skeleton-based human action recognition","volume":"35","author":"Jia","year":"2020","journal-title":"J. Comput. ence Technol."},{"key":"10.1016\/j.asoc.2021.107236_b46","series-title":"Temporal reasoning graph for activity recognition","author":"Zhang","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b47","series-title":"Spatio-temporal graph convolution for skeleton based action recognition","author":"Li","year":"2018"},{"key":"10.1016\/j.asoc.2021.107236_b48","series-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"Yan","year":"2018"},{"issue":"12","key":"10.1016\/j.asoc.2021.107236_b49","doi-asserted-by":"crossref","first-page":"3818","DOI":"10.1109\/TNNLS.2019.2944869","article-title":"Nonpeaked discriminant analysis for data representation","volume":"30","author":"Ye","year":"2019","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2021.107236_b50","doi-asserted-by":"crossref","first-page":"51","DOI":"10.1016\/j.neunet.2014.05.014","article-title":"Fast Gaussian kernel learning for classification tasks based on specially structured global optimization","volume":"57","author":"Zhong","year":"2014","journal-title":"Neural Netw."},{"issue":"12","key":"10.1016\/j.asoc.2021.107236_b51","doi-asserted-by":"crossref","first-page":"3227","DOI":"10.1109\/TNNLS.2015.2441697","article-title":"A complex-valued projection neural network for constrained optimization of real functions in complex variables","volume":"26","author":"Zhang","year":"2015","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"10.1016\/j.asoc.2021.107236_b52","series-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2018"},{"key":"10.1016\/j.asoc.2021.107236_b53","doi-asserted-by":"crossref","unstructured":"M. Li, S. Chen, Y. Zhao, Y. Zhang, Q. Tian, Dynamic multiscale graph neural networks for 3D skeleton based human motion prediction, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.","DOI":"10.1109\/CVPR42600.2020.00029"},{"key":"10.1016\/j.asoc.2021.107236_b54","doi-asserted-by":"crossref","unstructured":"B. Li, X. Li, Z. Zhang, F. Wu, Spatio-temporal graph routing for skeleton-based action recognition, in: Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33, 2019, pp. 8561\u20138568.","DOI":"10.1609\/aaai.v33i01.33018561"},{"key":"10.1016\/j.asoc.2021.107236_b55","doi-asserted-by":"crossref","unstructured":"L. Shi, Y. Zhang, J. Cheng, H. Lu, Skeleton-based action recognition with directed graph neural networks, in: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.","DOI":"10.1109\/CVPR.2019.00810"},{"key":"10.1016\/j.asoc.2021.107236_b56","series-title":"Disentangling and unifying graph convolutions for skeleton-based action recognition","author":"Liu","year":"2020"},{"key":"10.1016\/j.asoc.2021.107236_b57","series-title":"Self-attention network for skeleton-based human action recognition","author":"Cho","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b58","series-title":"Part-based graph convolutional network for action recognition","author":"Thakkar","year":"2018"},{"key":"10.1016\/j.asoc.2021.107236_b59","doi-asserted-by":"crossref","unstructured":"P. Zhang, C. Lan, W. Zeng, J. Xing, N. Zheng, Semantics-guided neural networks for efficient skeleton-based human action recognition, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.","DOI":"10.1109\/CVPR42600.2020.00119"},{"issue":"3","key":"10.1016\/j.asoc.2021.107236_b60","doi-asserted-by":"crossref","first-page":"621","DOI":"10.1007\/s00371-019-01644-3","article-title":"Skeleton-based action recognition by part-aware graph convolutional networks","volume":"36","author":"Qin","year":"2020","journal-title":"Vis. Comput."},{"key":"10.1016\/j.asoc.2021.107236_b61","series-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.1016\/j.asoc.2021.107236_b62","doi-asserted-by":"crossref","DOI":"10.1007\/s11704-016-6163-5","article-title":"Learning from context: A mutual reinforcement model for chinese microblog opinion retrieval","author":"Wei","year":"2018","journal-title":"Front. Comput. Sci."},{"issue":"dec.6","key":"10.1016\/j.asoc.2021.107236_b63","doi-asserted-by":"crossref","first-page":"333","DOI":"10.1016\/j.neucom.2017.06.018","article-title":"A complex-valued multichannel speech enhancement learning algorithm for optimal tradeoff between noise reduction and speech distortion","volume":"267","author":"Tu","year":"2017","journal-title":"Neurocomputing"},{"key":"10.1016\/j.asoc.2021.107236_b64","series-title":"Learning convolutional neural networks for graphs","author":"Niepert","year":"2016"},{"issue":"APR.","key":"10.1016\/j.asoc.2021.107236_b65","doi-asserted-by":"crossref","first-page":"259","DOI":"10.1016\/j.isprsjprs.2019.02.010","article-title":"A graph convolutional neural network for classification of building patterns using spatial vector data","volume":"150","author":"Yan","year":"2019","journal-title":"ISPRS J. Photogramm. Remote Sens."},{"key":"10.1016\/j.asoc.2021.107236_b66","series-title":"Adaptive spectral graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2018"},{"key":"10.1016\/j.asoc.2021.107236_b67","series-title":"Skeleton-based action recognition with multi-stream adaptive graph convolutional networks","author":"Shi","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b68","doi-asserted-by":"crossref","DOI":"10.1007\/s11042-018-6919-z","article-title":"Multimedia-oriented action recognition in smart city-based IoT using multilayer perceptron","author":"Al\u00a0Zamil","year":"2019","journal-title":"Multimedia Tools Appl."},{"key":"10.1016\/j.asoc.2021.107236_b69","doi-asserted-by":"crossref","first-page":"14","DOI":"10.1016\/j.future.2019.06.009","article-title":"Modified deep residual network architecture deployed on serverless framework of IoT platform based on human activity recognition application","volume":"101","author":"Keshavarzian","year":"2019","journal-title":"Future Gener. Comput. Syst."},{"key":"10.1016\/j.asoc.2021.107236_b70","series-title":"An IoT based framework for activity recognition using deep learning technique","author":"D\u2019Sa","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b71","series-title":"The kinetics human action video dataset","author":"Kay","year":"2017"},{"issue":"2","key":"10.1016\/j.asoc.2021.107236_b72","doi-asserted-by":"crossref","first-page":"4","DOI":"10.1109\/MMUL.2012.24","article-title":"Microsoft kinect sensor and its effect","volume":"19","author":"Zhang","year":"2012","journal-title":"IEEE Multimedia"},{"key":"10.1016\/j.asoc.2021.107236_b73","doi-asserted-by":"crossref","first-page":"286","DOI":"10.1016\/j.patrec.2020.05.005","article-title":"Topology-learnable graph convolution for skeleton-based action recognition","volume":"135","author":"A","year":"2020","journal-title":"Pattern Recognit. Lett."},{"issue":"99","key":"10.1016\/j.asoc.2021.107236_b74","article-title":"Squeeze-and-excitation networks","volume":"PP","author":"Hu","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.asoc.2021.107236_b75","doi-asserted-by":"crossref","unstructured":"Q. Wang, B. Wu, P. Zhu, P. Li, Q. Hu, ECA-Net: Efficient channel attention for deep convolutional neural networks, in: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), 2020.","DOI":"10.1109\/CVPR42600.2020.01152"},{"key":"10.1016\/j.asoc.2021.107236_b76","series-title":"Skeleton-based action recognition with multi-stream adaptive graph convolutional networks","author":"Shi","year":"2019"},{"key":"10.1016\/j.asoc.2021.107236_b77","doi-asserted-by":"crossref","unstructured":"A. Shahroudy, J. Liu, T.-T. Ng, G. Wang, Ntu rgb+ d: A large scale dataset for 3d human activity analysis, in: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, 2016, pp. 1010\u20131019.","DOI":"10.1109\/CVPR.2016.115"},{"key":"10.1016\/j.asoc.2021.107236_b78","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."},{"issue":"1","key":"10.1016\/j.asoc.2021.107236_b79","first-page":"1929","article-title":"Dropout: a simple way to prevent neural networks from overfitting","volume":"15","author":"Srivastava","year":"2014","journal-title":"J. Mach. Learn. Res."},{"key":"10.1016\/j.asoc.2021.107236_b80","doi-asserted-by":"crossref","unstructured":"R. Lin, S. Liu, M. Yang, M. Li, M. Zhou, S. Li, Hierarchical recurrent neural network for document modeling, in: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, 2015, pp. 899\u2013907.","DOI":"10.18653\/v1\/D15-1106"},{"key":"10.1016\/j.asoc.2021.107236_b81","series-title":"Spatio-temporal LSTM with trust gates for 3D human action recognition","author":"Liu","year":"2016"},{"key":"10.1016\/j.asoc.2021.107236_b82","series-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"Song","year":"2016"}],"container-title":["Applied Soft Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494621001599?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S1568494621001599?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,27]],"date-time":"2025-10-27T19:52:43Z","timestamp":1761594763000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S1568494621001599"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":82,"alternative-id":["S1568494621001599"],"URL":"https:\/\/doi.org\/10.1016\/j.asoc.2021.107236","relation":{},"ISSN":["1568-4946"],"issn-type":[{"value":"1568-4946","type":"print"}],"subject":[],"published":{"date-parts":[[2021,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"Multi-scale skeleton adaptive weighted GCN for skeleton-based human action recognition in IoT","name":"articletitle","label":"Article Title"},{"value":"Applied Soft Computing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.asoc.2021.107236","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2021 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}],"article-number":"107236"}}