{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T00:22:02Z","timestamp":1778286122157,"version":"3.51.4"},"reference-count":63,"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"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["elsevier.com","sciencedirect.com"],"crossmark-restriction":true},"short-container-title":["Neurocomputing"],"published-print":{"date-parts":[[2021,6]]},"DOI":"10.1016\/j.neucom.2020.04.150","type":"journal-article","created":{"date-parts":[[2020,11,24]],"date-time":"2020-11-24T11:46:34Z","timestamp":1606218394000},"page":"350-358","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":44,"special_numbering":"C","title":["A fast human action recognition network based on spatio-temporal features"],"prefix":"10.1016","volume":"441","author":[{"given":"Jie","family":"Xu","sequence":"first","affiliation":[]},{"given":"Rui","family":"Song","sequence":"additional","affiliation":[]},{"given":"Haoliang","family":"Wei","sequence":"additional","affiliation":[]},{"given":"Jinhong","family":"Guo","sequence":"additional","affiliation":[]},{"given":"Yifei","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Xiwei","family":"Huang","sequence":"additional","affiliation":[]}],"member":"78","reference":[{"issue":"2","key":"10.1016\/j.neucom.2020.04.150_b0005","doi-asserted-by":"crossref","first-page":"91","DOI":"10.1023\/B:VISI.0000029664.99615.94","article-title":"Distinctive image features from scale-invariant keypoints","volume":"60","author":"Lowe","year":"2004","journal-title":"Int. J. Comput. Vision"},{"key":"10.1016\/j.neucom.2020.04.150_b0010","doi-asserted-by":"crossref","unstructured":"N. Dalal, B. Triggs, Histograms of oriented gradients for human detection, in: 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR\u201905), vol. 1, 2005, pp. 886\u2013893.https:\/\/doi.org\/10.1109\/CVPR.2005.177.","DOI":"10.1109\/CVPR.2005.177"},{"key":"10.1016\/j.neucom.2020.04.150_b0015","doi-asserted-by":"crossref","unstructured":"H. Wang, C. Schmid, Action recognition with improved trajectories, in: 2013 IEEE International Conference on Computer Vision, 2013, pp. 3551\u20133558.https:\/\/doi.org\/10.1109\/ICCV.2013.441.","DOI":"10.1109\/ICCV.2013.441"},{"key":"10.1016\/j.neucom.2020.04.150_b0020","series-title":"Computer Vision \u2013 ECCV 2014","first-page":"581","article-title":"Action recognition with stacked fisher vectors","author":"Peng","year":"2014"},{"key":"10.1016\/j.neucom.2020.04.150_b0025","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"204","article-title":"Beyond gaussian pyramid: multi-skip feature stacking for action recognition","author":"Lan","year":"2015"},{"key":"10.1016\/j.neucom.2020.04.150_b0030","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5378","article-title":"Modeling video evolution for action recognition","author":"Fernando","year":"2015"},{"key":"10.1016\/j.neucom.2020.04.150_b0035","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1581","article-title":"Generalized rank pooling for activity recognition","author":"Cherian","year":"2017"},{"key":"10.1016\/j.neucom.2020.04.150_b0040","first-page":"4489","article-title":"Learning spatiotemporal features with 3d convolutional networks","volume":"2015","author":"Tran","year":"2015","journal-title":"IEEE International Conference on Computer Vision (ICCV)"},{"key":"10.1016\/j.neucom.2020.04.150_b0045","doi-asserted-by":"crossref","unstructured":"A. Karpathy, G. Toderici, S. Shetty, T. Leung, R. Sukthankar, L. Fei-Fei, Large-scale video classification with convolutional neural networks, in: 2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014, pp. 1725\u20131732.https:\/\/doi.org\/10.1109\/CVPR.2014.223.","DOI":"10.1109\/CVPR.2014.223"},{"key":"10.1016\/j.neucom.2020.04.150_b0050","doi-asserted-by":"crossref","unstructured":"L. Sun, K. Jia, D. Yeung, B.E. Shi, Human action recognition using factorized spatio-temporal convolutional networks, in: 2015 IEEE International Conference on Computer Vision (ICCV), 2015, pp. 4597\u20134605.https:\/\/doi.org\/10.1109\/ICCV.2015.522.","DOI":"10.1109\/ICCV.2015.522"},{"key":"10.1016\/j.neucom.2020.04.150_b0055","doi-asserted-by":"crossref","unstructured":"H. Bilen, B. Fernando, E. Gavves, A. Vedaldi, S. Gould, Dynamic image networks for action recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 3034\u20133042.https:\/\/doi.org\/10.1109\/CVPR.2016.331.","DOI":"10.1109\/CVPR.2016.331"},{"key":"10.1016\/j.neucom.2020.04.150_b0060","unstructured":"K. Simonyan, A. Zisserman, Two-stream convolutional networks for action recognition in videos, Advances in Neural Information Processing Systems 1."},{"key":"10.1016\/j.neucom.2020.04.150_b0065","series-title":"Computer Vision \u2013 ECCV 2016","first-page":"20","article-title":"Temporal segment networks: towards good practices for deep action recognition","author":"Wang","year":"2016"},{"key":"10.1016\/j.neucom.2020.04.150_b0070","doi-asserted-by":"crossref","unstructured":"M. Xin, H. Zhang, H. Wang, M. Sun, D. Yuan, Arch: Adaptive recurrent-convolutional hybrid networks for long-term action recognition, Neurocomputing 178 (2016) 87\u2013102 https:\/\/doi.org\/10.1016\/j.neucom.2015.09.112.","DOI":"10.1016\/j.neucom.2015.09.112"},{"key":"10.1016\/j.neucom.2020.04.150_b0075","doi-asserted-by":"crossref","first-page":"962","DOI":"10.1016\/j.neucom.2010.11.013","article-title":"Transform based spatio-temporal descriptors for human action recognition","volume":"74","author":"Shao","year":"2011","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2020.04.150_b0080","doi-asserted-by":"crossref","unstructured":"W. Zhu, J. Hu, G. Sun, X. Cao, Y. Qiao, A key volume mining deep framework for action recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1991\u20131999.https:\/\/doi.org\/10.1109\/CVPR.2016.219.","DOI":"10.1109\/CVPR.2016.219"},{"key":"10.1016\/j.neucom.2020.04.150_b0085","series-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1541","article-title":"Deep temporal linear encoding networks","author":"Diba","year":"2017"},{"key":"10.1016\/j.neucom.2020.04.150_b0090","series-title":"2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"5699","article-title":"Adascan: Adaptive scan pooling in deep convolutional neural networks for human action recognition in videos","author":"Kar","year":"2017"},{"key":"10.1016\/j.neucom.2020.04.150_b0095","doi-asserted-by":"crossref","unstructured":"J. Carreira, A. Zisserman, Quo vadis, action recognition? A new model and the kinetics dataset, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 4724\u20134733.https:\/\/doi.org\/10.1109\/CVPR.2017.502.","DOI":"10.1109\/CVPR.2017.502"},{"key":"10.1016\/j.neucom.2020.04.150_b0100","doi-asserted-by":"crossref","unstructured":"L. Wang, Y. Qiao, X. Tang, Action recognition with trajectory-pooled deep-convolutional descriptors, in: 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 4305\u20134314.https:\/\/doi.org\/10.1109\/CVPR.2015.7299059.","DOI":"10.1109\/CVPR.2015.7299059"},{"key":"10.1016\/j.neucom.2020.04.150_b0105","unstructured":"Y. Wang, V. Tran, M. Hoai, Evolution-preserving dense trajectory descriptors."},{"issue":"1","key":"10.1016\/j.neucom.2020.04.150_b0110","doi-asserted-by":"crossref","first-page":"221","DOI":"10.1109\/TPAMI.2012.59","article-title":"3d convolutional neural networks for human action recognition","volume":"35","author":"Ji","year":"2013","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.04.150_b0115","doi-asserted-by":"crossref","first-page":"5262","DOI":"10.1109\/ACCESS.2017.2684913","article-title":"Improving activity recognition accuracy in ambient-assisted living systems by automated feature engineering","volume":"5","author":"Zdravevski","year":"2017","journal-title":"IEEE Access"},{"key":"10.1016\/j.neucom.2020.04.150_b0120","series-title":"Pattern Recogn","first-page":"214","article-title":"A duality based approach for realtime tv-l1 optical flow","author":"Zach","year":"2007"},{"key":"10.1016\/j.neucom.2020.04.150_b0125","series-title":"Advances in Neural Information Processing Systems 29","first-page":"3468","article-title":"Spatiotemporal residual networks for video action recognition","author":"Feichtenhofer","year":"2016"},{"key":"10.1016\/j.neucom.2020.04.150_b0130","series-title":"Computer Vision \u2013 ECCV 2016 Workshops","first-page":"668","article-title":"Depth2action: exploring embedded depth for large-scale action recognition","author":"Zhu","year":"2016"},{"key":"10.1016\/j.neucom.2020.04.150_b0135","doi-asserted-by":"crossref","unstructured":"J. Ng, J. Choi, J. Neumann, L.S. Davis, Actionflownet: Learning motion representation for action recognition, in: 2018 IEEE Winter Conference on Applications of Computer Vision (WACV), IEEE Computer Society, Los Alamitos, CA, USA, 2018, pp. 1616\u20131624.https:\/\/doi.org\/10.1109\/WACV.2018.00179.","DOI":"10.1109\/WACV.2018.00179"},{"key":"10.1016\/j.neucom.2020.04.150_b0140","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"2718","article-title":"Real-time action recognition with enhanced motion vector cnns","author":"Zhang","year":"2016"},{"issue":"4","key":"10.1016\/j.neucom.2020.04.150_b0145","doi-asserted-by":"crossref","first-page":"250","DOI":"10.1049\/iet-cvi.2015.0233","article-title":"Human action recognition using histogram of motion intensity and direction from multiple views","volume":"10","author":"Chun","year":"2016","journal-title":"IET Comput. Vision"},{"issue":"9","key":"10.1016\/j.neucom.2020.04.150_b0150","doi-asserted-by":"crossref","first-page":"1228","DOI":"10.1109\/TCSVT.2011.2135290","article-title":"Recognizing human action at a distance in video by key poses","volume":"21","author":"Mukherjee","year":"2011","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"issue":"11","key":"10.1016\/j.neucom.2020.04.150_b0155","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1007\/s00371-018-1560-4","article-title":"A unified model for human activity recognition using spatial distribution of gradients and difference of gaussian kernel","volume":"35","author":"Vishwakarma","year":"2019","journal-title":"Visual Comput."},{"key":"10.1016\/j.neucom.2020.04.150_b0160","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"4694","article-title":"Beyond short snippets: deep networks for video classification","author":"Ng","year":"2015"},{"key":"10.1016\/j.neucom.2020.04.150_b0165","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"2166","article-title":"Lattice long short-term memory for human action recognition","author":"Sun","year":"2017"},{"key":"10.1016\/j.neucom.2020.04.150_b0170","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"716","article-title":"Learning long-term dependencies for action recognition with a biologically-inspired deep network","author":"Shi","year":"2017"},{"key":"10.1016\/j.neucom.2020.04.150_b0175","series-title":"Artificial Neural Networks \u2013 ICANN 2010","first-page":"154","article-title":"Action classification in soccer videos with long short-term memory recurrent neural networks","author":"Baccouche","year":"2010"},{"key":"10.1016\/j.neucom.2020.04.150_b0180","doi-asserted-by":"crossref","first-page":"17913","DOI":"10.1109\/ACCESS.2018.2817253","article-title":"Human action recognition by learning spatio-temporal features with deep neural networks","volume":"6","author":"Wang","year":"2018","journal-title":"IEEE Access"},{"issue":"12","key":"10.1016\/j.neucom.2020.04.150_b0185","doi-asserted-by":"crossref","first-page":"9692","DOI":"10.1109\/TIE.2018.2881943","article-title":"Activity recognition using temporal optical flow convolutional features and multilayer lstm","volume":"66","author":"Ullah","year":"2019","journal-title":"IEEE Trans. Industr. Electron."},{"issue":"6","key":"10.1016\/j.neucom.2020.04.150_b0190","doi-asserted-by":"crossref","first-page":"1510","DOI":"10.1109\/TPAMI.2017.2712608","article-title":"Long-term temporal convolutions for action recognition","volume":"40","author":"Varol","year":"2018","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.04.150_b0195","unstructured":"Y. Zhu, Z. Lan, S. Newsam, A.e.G. Hauptmann, Hidden two-stream convolutional networks for action recognition, arXiv e-prints (2017) arXiv:1704.00389 arXiv:1704.00389."},{"key":"10.1016\/j.neucom.2020.04.150_b0200","doi-asserted-by":"crossref","unstructured":"S. Sun, Z. Kuang, L. Sheng, W. Ouyang, W. Zhang, Optical flow guided feature: A fast and robust motion representation for video action recognition, in: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 2018, pp. 1390\u20131399.https:\/\/doi.org\/10.1109\/CVPR.2018.00151.","DOI":"10.1109\/CVPR.2018.00151"},{"key":"10.1016\/j.neucom.2020.04.150_b0205","doi-asserted-by":"crossref","unstructured":"J. Wang, Z. Liu, Y. Wu, J. Yuan, Mining actionlet ensemble for action recognition with depth cameras, in: 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, pp. 1290\u20131297.https:\/\/doi.org\/10.1109\/CVPR.2012.6247813.","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"10.1016\/j.neucom.2020.04.150_b0210","doi-asserted-by":"crossref","unstructured":"L. Seidenari, V. Varano, S. Berretti, A. Del Bimbo, P. Pala, Recognizing actions from depth cameras as weakly aligned multi-part bag-of-poses, in: 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2013, pp. 479\u2013485.https:\/\/doi.org\/10.1109\/CVPRW.2013.77.","DOI":"10.1109\/CVPRW.2013.77"},{"key":"10.1016\/j.neucom.2020.04.150_b0215","unstructured":"K. Soomro, A. Roshan Zamir, M. Shah, Ucf101: a dataset of 101 human actions classes from videos in the wild, CoRR."},{"key":"10.1016\/j.neucom.2020.04.150_b0220","doi-asserted-by":"crossref","unstructured":"Y. Jia, E. Shelhamer, J. Donahue, S. Karayev, J. Long, R. Girshick, S. Guadarrama, T. Darrell, Caffe: convolutional architecture for fast feature embedding, MM 2014 \u2013 Proceedings of the 2014 ACM Conference on Multimedia doi:10.1145\/2647868.2654889.","DOI":"10.1145\/2647868.2654889"},{"key":"10.1016\/j.neucom.2020.04.150_b0225","unstructured":"L. Wang, Y. Xiong, Z. Wang, Y. Qiao, Towards Good Practices for Very Deep Two-Stream ConvNets, arXiv e-prints (2015) arXiv:1507.02159 arXiv:1507.02159."},{"key":"10.1016\/j.neucom.2020.04.150_b0230","doi-asserted-by":"crossref","unstructured":"C. Feichtenhofer, A. Pinz, A. Zisserman, Convolutional two-stream network fusion for video action recognition, in: 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2016, pp. 1933\u20131941.https:\/\/doi.org\/10.1109\/CVPR.2016.213.","DOI":"10.1109\/CVPR.2016.213"},{"key":"10.1016\/j.neucom.2020.04.150_b0235","doi-asserted-by":"crossref","unstructured":"C. Feichtenhofer, A. Pinz, R.P. Wildes, Spatiotemporal multiplier networks for video action recognition, in: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2017, pp. 7445\u20137454.https:\/\/doi.org\/10.1109\/CVPR.2017.787.","DOI":"10.1109\/CVPR.2017.787"},{"key":"10.1016\/j.neucom.2020.04.150_b0240","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"5534","article-title":"Learning spatio-temporal representation with pseudo-3d residual networks","author":"Qiu","year":"2017"},{"key":"10.1016\/j.neucom.2020.04.150_b0245","series-title":"2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"449","article-title":"Mict: mixed 3d\/2d convolutional tube for human action recognition","author":"Zhou","year":"2018"},{"key":"10.1016\/j.neucom.2020.04.150_b0250","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.patcog.2017.01.015","article-title":"Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition","volume":"66","author":"Qiao","year":"2017","journal-title":"Pattern Recogn"},{"issue":"12","key":"10.1016\/j.neucom.2020.04.150_b0255","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.1109\/TPAMI.2016.2533389","article-title":"Histogram of oriented principal components for cross-view action recognition","volume":"38","author":"Rahmani","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"10","key":"10.1016\/j.neucom.2020.04.150_b0260","doi-asserted-by":"crossref","first-page":"2123","DOI":"10.1109\/TPAMI.2015.2505295","article-title":"Multimodal multipart learning for action recognition in depth videos","volume":"38","author":"Shahroudy","year":"2016","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.04.150_b0265","doi-asserted-by":"crossref","unstructured":"O. Oreifej, Z. Liu, Hon4d: histogram of oriented 4d normals for activity recognition from depth sequences, in: 2013 IEEE Conference on Computer Vision and Pattern Recognition, 2013, pp. 716\u2013723.https:\/\/doi.org\/10.1109\/CVPR.2013.98.","DOI":"10.1109\/CVPR.2013.98"},{"key":"10.1016\/j.neucom.2020.04.150_b0270","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1016\/j.neucom.2018.02.056","article-title":"Discriminative parts learning for 3d human action recognition","volume":"291","author":"Huang","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.neucom.2020.04.150_b0275","doi-asserted-by":"crossref","first-page":"202","DOI":"10.1016\/j.patcog.2017.01.015","article-title":"Learning discriminative trajectorylet detector sets for accurate skeleton-based action recognition","volume":"66","author":"Qiao","year":"2017","journal-title":"Pattern Recogn."},{"issue":"11","key":"10.1016\/j.neucom.2020.04.150_b0280","doi-asserted-by":"crossref","first-page":"1633","DOI":"10.1109\/LSP.2019.2942739","article-title":"Action machine: toward person-centric action recognition in videos","volume":"26","author":"Zhu","year":"2019","journal-title":"IEEE Signal Process. Lett."},{"key":"10.1016\/j.neucom.2020.04.150_b0285","doi-asserted-by":"crossref","first-page":"56","DOI":"10.1016\/j.sigpro.2017.08.016","article-title":"Skeleton embedded motion body partition for human action recognition using depth sequences","volume":"143","author":"Ji","year":"2018","journal-title":"Signal Process."},{"key":"10.1016\/j.neucom.2020.04.150_b0290","doi-asserted-by":"crossref","unstructured":"L. Seidenari, V. Varano, S. Berretti, A. Del Bimbo, P. Pala, Recognizing actions from depth cameras as weakly aligned multi-part bag-of-poses, in: 2013 IEEE Conference on Computer Vision and Pattern Recognition Workshops, 2013, pp. 479\u2013485.https:\/\/doi.org\/10.1109\/CVPRW.2013.77.","DOI":"10.1109\/CVPRW.2013.77"},{"issue":"7","key":"10.1016\/j.neucom.2020.04.150_b0295","doi-asserted-by":"crossref","first-page":"1340","DOI":"10.1109\/TCYB.2014.2350774","article-title":"3-d human action recognition by shape analysis of motion trajectories on riemannian manifold","volume":"45","author":"Devanne","year":"2015","journal-title":"IEEE Trans. Cybern."},{"issue":"5","key":"10.1016\/j.neucom.2020.04.150_b0300","doi-asserted-by":"crossref","first-page":"922","DOI":"10.1109\/TPAMI.2016.2564409","article-title":"Elastic functional coding of riemannian trajectories","volume":"39","author":"Anirudh","year":"2017","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.neucom.2020.04.150_b0305","doi-asserted-by":"crossref","unstructured":"Thien Huynh-The, Ba-Vui Le, Sungyoung Lee, Describing body-pose feature \u2013 poselet \u2013 activity relationship using pachinko allocation model, in: 2016 IEEE International Conference on Systems, Man, and Cybernetics (SMC), 2016, pp. 000040\u2013000045.https:\/\/doi.org\/10.1109\/SMC.2016.7844218.","DOI":"10.1109\/SMC.2016.7844218"},{"key":"10.1016\/j.neucom.2020.04.150_b0310","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, 2014, pp. 588\u2013595.https:\/\/doi.org\/10.1109\/CVPR.2014.82.","DOI":"10.1109\/CVPR.2014.82"},{"issue":"5","key":"10.1016\/j.neucom.2020.04.150_b0315","doi-asserted-by":"crossref","first-page":"6329","DOI":"10.1007\/s11042-018-6370-1","article-title":"Effective human action recognition using global and local offsets of skeleton joints","volume":"78","author":"Sun","year":"2019","journal-title":"Multimedia Tools Appl."}],"container-title":["Neurocomputing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231220317781?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0925231220317781?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T19:51:04Z","timestamp":1760385064000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0925231220317781"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,6]]},"references-count":63,"alternative-id":["S0925231220317781"],"URL":"https:\/\/doi.org\/10.1016\/j.neucom.2020.04.150","relation":{},"ISSN":["0925-2312"],"issn-type":[{"value":"0925-2312","type":"print"}],"subject":[],"published":{"date-parts":[[2021,6]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"A fast human action recognition network based on spatio-temporal features","name":"articletitle","label":"Article Title"},{"value":"Neurocomputing","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.neucom.2020.04.150","name":"articlelink","label":"CrossRef DOI link to publisher maintained version"},{"value":"article","name":"content_type","label":"Content Type"},{"value":"\u00a9 2020 Elsevier B.V. All rights reserved.","name":"copyright","label":"Copyright"}]}}