{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,5]],"date-time":"2026-06-05T05:35:33Z","timestamp":1780637733488,"version":"3.54.1"},"reference-count":68,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T00:00:00Z","timestamp":1673308800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100003467","name":"Hangzhou Dianzi University","doi-asserted-by":"publisher","award":["KYP0222010"],"award-info":[{"award-number":["KYP0222010"]}],"id":[{"id":"10.13039\/501100003467","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2023,7]]},"DOI":"10.1007\/s10489-022-04365-8","type":"journal-article","created":{"date-parts":[[2023,1,10]],"date-time":"2023-01-10T19:02:45Z","timestamp":1673377365000},"page":"17629-17643","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":21,"title":["Skeleton-based action recognition with multi-stream, multi-scale dilated spatial-temporal graph convolution network"],"prefix":"10.1007","volume":"53","author":[{"given":"Haiping","family":"Zhang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0107-3119","authenticated-orcid":false,"given":"Xu","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjin","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Liming","family":"Guan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongjing","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Conghao","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zepeng","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,1,10]]},"reference":[{"key":"4365_CR1","unstructured":"Abu-El-Haija S, Perozzi B, Kapoor A et al (2019) MixHop: higher-order graph convolutional architectures via sparsified neighborhood mixing. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, proceedings of machine learning research. https:\/\/proceedings.mlr.press\/v97\/abu-el-haija19a.html, vol 97. PMLR, pp 21\u201329"},{"issue":"3","key":"4365_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1922649.1922653","volume":"43","author":"JK Aggarwal","year":"2011","unstructured":"Aggarwal JK, Ryoo MS (2011) Human activity analysis: a review. Acm Computing Surveys (Csur) 43(3):1\u201343","journal-title":"Acm Computing Surveys (Csur)"},{"key":"4365_CR3","doi-asserted-by":"publisher","first-page":"103,348","DOI":"10.1016\/j.cviu.2021.103348","volume":"216","author":"T Alsarhan","year":"2022","unstructured":"Alsarhan T, Ali U, Lu H (2022) Enhanced discriminative graph convolutional network with adaptive temporal modelling for skeleton-based action recognition. Comput Vis Image Underst 216:103,348. https:\/\/doi.org\/10.1016\/j.cviu.2021.103348. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S107731422100179X","journal-title":"Comput Vis Image Underst"},{"key":"4365_CR4","unstructured":"Atwood J, Towsley D (2016) Diffusion-convolutional neural networks. Advances in Neural Information Processing Systems 29"},{"key":"4365_CR5","unstructured":"Bai S, Kolter JZ, Koltun V (2018) An empirical evaluation of generic convolutional and recurrent networks for sequence modeling. arXiv:1803.01271"},{"key":"4365_CR6","doi-asserted-by":"crossref","unstructured":"Cai J, Jiang N, Han X et al (2021) Jolo-gcn: mining joint-centered light-weight information for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF winter conference on applications of computer vision, pp 2735\u20132744","DOI":"10.1109\/WACV48630.2021.00278"},{"key":"4365_CR7","doi-asserted-by":"crossref","unstructured":"Cao Z, Simon T, Wei SE 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"},{"issue":"4","key":"4365_CR8","doi-asserted-by":"publisher","first-page":"102,950","DOI":"10.1016\/j.ipm.2022.102950","volume":"59","author":"Y Chen","year":"2022","unstructured":"Chen Y, Li Y, Zhang C et al (2022) Informed patch enhanced hypergcn for skeleton-based action recognition. Information Processing & Management 59(4):102,950. https:\/\/doi.org\/10.1016\/j.ipm.2022.102950. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0306457322000723","journal-title":"Information Processing & Management"},{"key":"4365_CR9","doi-asserted-by":"crossref","unstructured":"Chen Z, Li S, Yang B et al (2021) Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition. In: Proceedings of the AAAI conference on artificial intelligence, pp 1113\u20131122","DOI":"10.1609\/aaai.v35i2.16197"},{"key":"4365_CR10","doi-asserted-by":"crossref","unstructured":"Cheng K, Zhang Y, He X et al (2020) Skeleton-based action recognition with shift graph convolutional network. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 183\u2013192","DOI":"10.1109\/CVPR42600.2020.00026"},{"key":"4365_CR11","doi-asserted-by":"crossref","unstructured":"Cho K, Van Merri\u00ebnboer B, Gulcehre C et al (2014) Learning phrase representations using rnn encoder-decoder for statistical machine translation. arXiv:1406.1078","DOI":"10.3115\/v1\/D14-1179"},{"key":"4365_CR12","unstructured":"Dix A, Finlay J, Abowd GD et al (2004) Human-computer interaction. Pearson Education"},{"key":"4365_CR13","unstructured":"Du Y, Wang W, Wang L (2015) Hierarchical recurrent neural network for skeleton based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1110\u20131118"},{"key":"4365_CR14","unstructured":"Duvenaud DK, Maclaurin D, Iparraguirre J et al (2015) Convolutional networks on graphs for learning molecular fingerprints. Advances in Neural Information Processing Systems 28"},{"key":"4365_CR15","doi-asserted-by":"publisher","first-page":"108,714","DOI":"10.1016\/j.sigpro.2022.108714","volume":"201","author":"P Geng","year":"2022","unstructured":"Geng P, Li H, Wang F et al (2022) Adaptive multi-level graph convolution with contrastive learning for skeleton-based action recognition. Signal Process 201:108,714. https:\/\/doi.org\/10.1016\/j.sigpro.2022.108714. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0165168422002535","journal-title":"Signal Process"},{"key":"4365_CR16","unstructured":"Hamilton W, Ying Z, Leskovec J (2017) Inductive representation learning on large graphs. Advances in Neural Information Processing Systems 30"},{"key":"4365_CR17","doi-asserted-by":"publisher","first-page":"2263","DOI":"10.1109\/TIP.2021.3051495","volume":"30","author":"X Hao","year":"2021","unstructured":"Hao X, Li J, Guo Y et al (2021) Hypergraph neural network for skeleton-based action recognition. IEEE Trans Image Process 30:2263\u20132275. https:\/\/doi.org\/10.1109\/TIP.2021.3051495","journal-title":"IEEE Trans Image Process"},{"key":"4365_CR18","unstructured":"Henaff M, Bruna J, LeCun Y (2015) Deep convolutional networks on graph-structured data. arXiv:1506.05163"},{"issue":"3","key":"4365_CR19","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1109\/TSMCC.2004.829274","volume":"34","author":"W Hu","year":"2004","unstructured":"Hu W, Tan T, Wang L et al (2004) A survey on visual surveillance of object motion and behaviors. IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews) 34(3):334\u2013352. https:\/\/doi.org\/10.1109\/TSMCC.2004.829274","journal-title":"IEEE Transactions on Systems Man and Cybernetics Part C (Applications and Reviews)"},{"key":"4365_CR20","unstructured":"Ioffe S, Szegedy C (2015) Batch normalization: accelerating deep network training by reducing internal covariate shift. In: Bach F, Blei D (eds) Proceedings of the 32nd international conference on machine learning, proceedings of machine learning research. https:\/\/proceedings.mlr.press\/v37\/ioffe15.html, vol 37. PMLR, Lille, pp 448\u2013456"},{"key":"4365_CR21","unstructured":"Kay W, Carreira J, Simonyan K et al (2017) The kinetics human action video dataset. arXiv:1705.06950"},{"issue":"5","key":"4365_CR22","doi-asserted-by":"publisher","first-page":"926","DOI":"10.1007\/s12555-010-0501-4","volume":"8","author":"IS Kim","year":"2010","unstructured":"Kim IS, Choi HS, Yi KM et al (2010) Intelligent visual surveillance\u2014a survey. International Journal of Control Automation and Systems 8(5):926\u2013939. https:\/\/doi.org\/10.1007\/s12555-010-0501-4","journal-title":"International Journal of Control Automation and Systems"},{"key":"4365_CR23","unstructured":"Kipf T, Fetaya E, Wang KC et al (2018) Neural relational inference for interacting systems. In: Dy J, Krause A (eds) Proceedings of the 35th international conference on machine learning, proceedings of machine learning research. https:\/\/proceedings.mlr.press\/v80\/kipf18a.html, vol 80. PMLR, pp 2688\u20132697"},{"key":"4365_CR24","unstructured":"Kipf TN, Welling M (2016) Semi-supervised classification with graph convolutional networks. arXiv:160902907"},{"key":"4365_CR25","doi-asserted-by":"publisher","unstructured":"Li B, Dai Y, Cheng X et al (2017) Skeleton based action recognition using translation-scale invariant image mapping and multi-scale deep cnn. In: 2017 IEEE international conference on multimedia & expo workshops (ICMEW), pp 601\u2013604. https:\/\/doi.org\/10.1109\/ICMEW.2017.8026282","DOI":"10.1109\/ICMEW.2017.8026282"},{"key":"4365_CR26","doi-asserted-by":"crossref","unstructured":"Li C, Zhong Q, Xie D et al (2019) Collaborative spatiotemporal feature learning for video action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7872\u20137881","DOI":"10.1109\/CVPR.2019.00806"},{"key":"4365_CR27","doi-asserted-by":"crossref","unstructured":"Li M, Chen S, Chen X et al (2019) Actional-structural graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 3595\u20133603","DOI":"10.1109\/CVPR.2019.00371"},{"key":"4365_CR28","doi-asserted-by":"crossref","unstructured":"Li R, Wang S, Zhu F et al (2018) Adaptive graph convolutional neural networks. In: Proceedings of the AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v32i1.11691"},{"key":"4365_CR29","doi-asserted-by":"crossref","unstructured":"Li S, Li W, Cook C et al (2018) Independently recurrent neural network (indrnn): building a longer and deeper rnn. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5457\u20135466","DOI":"10.1109\/CVPR.2018.00572"},{"key":"4365_CR30","doi-asserted-by":"publisher","first-page":"144:529","DOI":"10.1109\/ACCESS.2020.3014445","volume":"8","author":"W Li","year":"2020","unstructured":"Li W, Liu X, Liu Z et al (2020) Skeleton-based action recognition using multi-scale and multi-stream improved graph convolutional network. IEEE Access 8:144:529\u2013144:542. https:\/\/doi.org\/10.1109\/ACCESS.2020.3014445","journal-title":"IEEE Access"},{"issue":"5","key":"4365_CR31","doi-asserted-by":"publisher","first-page":"3178","DOI":"10.1109\/TCSVT.2021.3103760","volume":"32","author":"Y Li","year":"2022","unstructured":"Li Y, Lu Y, Chen B et al (2022) Learning informative and discriminative features for facial expression recognition in the wild. IEEE Trans Circuits Syst Video Technol 32 (5):3178\u20133189. https:\/\/doi.org\/10.1109\/TCSVT.2021.3103760","journal-title":"IEEE Trans Circuits Syst Video Technol"},{"key":"4365_CR32","doi-asserted-by":"publisher","unstructured":"Liu J, Shahroudy A, Xu D et al (2016) Spatio-temporal lstm with trust gates for 3d human action recognition. In: European conference on computer vision. https:\/\/doi.org\/10.1007\/978-3-319-46487-9_50. Springer, pp 816\u2013833","DOI":"10.1007\/978-3-319-46487-9_50"},{"key":"4365_CR33","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 (2017) Enhanced skeleton visualization for view invariant human action recognition. Pattern Recogn 68:346\u2013362. https:\/\/doi.org\/10.1016\/j.patcog.2017.02.030. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320317300936","journal-title":"Pattern Recogn"},{"key":"4365_CR34","doi-asserted-by":"crossref","unstructured":"Liu Z, Zhang H, Chen Z et al (2020) Disentangling and unifying graph convolutions for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 143\u2013152","DOI":"10.1109\/CVPR42600.2020.00022"},{"key":"4365_CR35","doi-asserted-by":"crossref","unstructured":"Monti F, Boscaini D, Masci J et al (2017) Geometric deep learning on graphs and manifolds using mixture model cnns. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5115\u20135124","DOI":"10.1109\/CVPR.2017.576"},{"issue":"2","key":"4365_CR36","doi-asserted-by":"publisher","first-page":"44","DOI":"10.1145\/274430.274436","volume":"5","author":"BA Myers","year":"1998","unstructured":"Myers BA (1998) A brief history of human-computer interaction technology. Interactions 5 (2):44\u201354","journal-title":"Interactions"},{"key":"4365_CR37","unstructured":"Niepert M, Ahmed M, Kutzkov K (2016) Learning convolutional neural networks for graphs. In: Balcan MF, Weinberger KQ (eds) Proceedings of The 33rd international conference on machine learning, proceedings of machine learning research. https:\/\/proceedings.mlr.press\/v48\/niepert16.html, vol 48. PMLR, New York, pp 2014\u20132023"},{"key":"4365_CR38","doi-asserted-by":"crossref","unstructured":"Peng W, Hong X, Chen H et al (2020) Learning graph convolutional network for skeleton-based human action recognition by neural searching. In: Proceedings of the AAAI conference on artificial intelligence, pp 2669\u20132676","DOI":"10.1609\/aaai.v34i03.5652"},{"key":"4365_CR39","doi-asserted-by":"publisher","first-page":"45","DOI":"10.1016\/j.neucom.2021.05.004","volume":"454","author":"W Peng","year":"2021","unstructured":"Peng W, Shi J, Varanka T et al (2021) Rethinking the st-gcns for 3d skeleton-based human action recognition. Neurocomputing 454:45\u201353. https:\/\/doi.org\/10.1016\/j.neucom.2021.05.004. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0925231221007153","journal-title":"Neurocomputing"},{"key":"4365_CR40","doi-asserted-by":"publisher","first-page":"103,219","DOI":"10.1016\/j.cviu.2021.103219","volume":"208-209","author":"C Plizzari","year":"2021","unstructured":"Plizzari C, Cannici M, Matteucci M (2021) Skeleton-based action recognition via spatial and temporal transformer networks. Comput Vis Image Underst 208-209:103,219. https:\/\/doi.org\/10.1016\/j.cviu.2021.103219. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S1077314221000631","journal-title":"Comput Vis Image Underst"},{"issue":"1","key":"4365_CR41","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1007\/s10462-012-9356-9","volume":"43","author":"SS Rautaray","year":"2015","unstructured":"Rautaray SS, Agrawal A (2015) Vision based hand gesture recognition for human computer interaction: a survey. Artif Intell Rev 43(1):1\u201354. https:\/\/doi.org\/10.1007\/s10462-012-9356-9","journal-title":"Artif Intell Rev"},{"key":"4365_CR42","doi-asserted-by":"crossref","unstructured":"Shahroudy A, Liu J, Ng TT et al (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, pp 1010\u20131019","DOI":"10.1109\/CVPR.2016.115"},{"key":"4365_CR43","doi-asserted-by":"publisher","unstructured":"Sheikh Y, Sheikh M, Shah M (2005) Exploring the space of a human action. In: Tenth IEEE international conference on computer vision (ICCV\u201905). https:\/\/doi.org\/10.1109\/ICCV.2005.90, vol 1, pp 144\u2013149","DOI":"10.1109\/ICCV.2005.90"},{"key":"4365_CR44","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J et al (2019a) Skeleton-based action recognition with directed graph neural networks. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 7912\u20137921","DOI":"10.1109\/CVPR.2019.00810"},{"key":"4365_CR45","doi-asserted-by":"crossref","unstructured":"Shi L, Zhang Y, Cheng J et al (2019b) Two-stream adaptive graph convolutional networks for skeleton-based action recognition. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 12,026\u201312,035","DOI":"10.1109\/CVPR.2019.01230"},{"key":"4365_CR46","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","volume":"29","author":"L Shi","year":"2020","unstructured":"Shi L, Zhang Y, Cheng J et al (2020) Skeleton-based action recognition with multi-stream adaptive graph convolutional networks. IEEE Trans Image Process 29:9532\u20139545. https:\/\/doi.org\/10.1109\/TIP.2020.3028207","journal-title":"IEEE Trans Image Process"},{"key":"4365_CR47","doi-asserted-by":"crossref","unstructured":"Song YF, Zhang Z, Shan C et al (2020) Stronger, faster and more explainable: a graph convolutional baseline for skeleton-based action recognition. ACM","DOI":"10.1145\/3394171.3413802"},{"key":"4365_CR48","doi-asserted-by":"crossref","unstructured":"Soo Kim T, Reiter A (2017) Interpretable 3d human action analysis with temporal convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition workshops, pp 20\u201328","DOI":"10.1109\/CVPRW.2017.207"},{"key":"4365_CR49","doi-asserted-by":"crossref","unstructured":"Strubell E, Verga P, Belanger D et al (2017) Fast and accurate entity recognition with iterated dilated convolutions. arXiv:1702.02098","DOI":"10.18653\/v1\/D17-1283"},{"issue":"3","key":"4365_CR50","doi-asserted-by":"publisher","first-page":"193","DOI":"10.1016\/j.cag.2012.11.004","volume":"37","author":"EA Suma","year":"2013","unstructured":"Suma EA, Krum DM, Lange B et al (2013) Adapting user interfaces for gestural interaction with the flexible action and articulated skeleton toolkit. Computers & Graphics 37 (3):193\u2013201. https:\/\/doi.org\/10.1016\/j.cag.2012.11.004. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0097849312001756","journal-title":"Computers & Graphics"},{"key":"4365_CR51","doi-asserted-by":"crossref","unstructured":"Szegedy C et al (2015) Going deeper with convolutions. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 1\u20139","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"4365_CR52","doi-asserted-by":"crossref","unstructured":"Szegedy C, Vanhoucke V, Ioffe S et al (2016) Rethinking the inception architecture for computer vision. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2818\u20132826","DOI":"10.1109\/CVPR.2016.308"},{"key":"4365_CR53","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V et al (2017) Inception-v4 inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"4365_CR54","doi-asserted-by":"crossref","unstructured":"Tang Y, Tian Y, Lu J et al (2018) Deep progressive reinforcement learning for skeleton-based action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 5323\u20135332","DOI":"10.1109\/CVPR.2018.00558"},{"key":"4365_CR55","doi-asserted-by":"crossref","unstructured":"Tran D, Wang H, Torresani L et al (2018) A closer look at spatiotemporal convolutions for action recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 6450\u20136459","DOI":"10.1109\/CVPR.2018.00675"},{"issue":"3","key":"4365_CR56","first-page":"4","volume":"2","author":"P Velickovic","year":"2019","unstructured":"Velickovic P, Fedus W, Hamilton WL et al (2019) Deep graph infomax. ICLR (Poster) 2 (3):4","journal-title":"ICLR (Poster)"},{"key":"4365_CR57","doi-asserted-by":"crossref","unstructured":"Wang H, Wang L (2017) Modeling temporal dynamics and spatial configurations of actions using two-stream recurrent neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 499\u2013508","DOI":"10.1109\/CVPR.2017.387"},{"key":"4365_CR58","doi-asserted-by":"publisher","unstructured":"Wang J, Liu Z, Wu Y et al (2012) Mining actionlet ensemble for action recognition with depth cameras. In: 2012 IEEE conference on computer vision and pattern recognition. https:\/\/doi.org\/10.1109\/CVPR.2012.6247813, pp 1290\u20131297","DOI":"10.1109\/CVPR.2012.6247813"},{"key":"4365_CR59","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. https:\/\/doi.org\/10.1016\/j.knosys.2018.05.029. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0950705118302582","journal-title":"Knowl-Based Syst"},{"key":"4365_CR60","unstructured":"Wu F, Souza A, Zhang T et al (2019) Simplifying graph convolutional networks. In: Chaudhuri K, Salakhutdinov R (eds) Proceedings of the 36th international conference on machine learning, proceedings of machine learning research. https:\/\/proceedings.mlr.press\/v97\/wu19e.html, vol 97. PMLR, pp 6861\u20136871"},{"key":"4365_CR61","doi-asserted-by":"crossref","unstructured":"Xie S, Sun C, Huang J et al (2018) Rethinking spatiotemporal feature learning: speed-accuracy trade-offs in video classification. In: Proceedings of the European conference on computer vision (ECCV), pp 305\u2013321","DOI":"10.1007\/978-3-030-01267-0_19"},{"key":"4365_CR62","unstructured":"Xu K, Hu W, Leskovec J et al (2018) How powerful are graph neural networks? arXiv:1810.00826"},{"key":"4365_CR63","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":"4365_CR64","doi-asserted-by":"crossref","unstructured":"Ye F, Pu S, Zhong Q et al (2020) Dynamic gcn: context-enriched topology learning for skeleton-based action recognition. In: Proceedings of the 28th ACM international conference on multimedia, pp 55\u201363","DOI":"10.1145\/3394171.3413941"},{"key":"4365_CR65","unstructured":"Yu F, Koltun V (2015) Multi-scale context aggregation by dilated convolutions. arXiv:1511.07122"},{"key":"4365_CR66","doi-asserted-by":"crossref","unstructured":"Yu F, Koltun V, Funkhouser T (2017) Dilated residual networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 472\u2013480","DOI":"10.1109\/CVPR.2017.75"},{"issue":"8","key":"4365_CR67","doi-asserted-by":"publisher","first-page":"2329","DOI":"10.1016\/j.patcog.2015.03.006","volume":"48","author":"M Ziaeefard","year":"2015","unstructured":"Ziaeefard M, Bergevin R (2015) Semantic human activity recognition: a literature review. Pattern Recogn 48(8):2329\u20132345. https:\/\/doi.org\/10.1016\/j.patcog.2015.03.006. https:\/\/www.sciencedirect.com\/science\/article\/pii\/S0031320315000953","journal-title":"Pattern Recogn"},{"key":"4365_CR68","doi-asserted-by":"crossref","unstructured":"Zolfaghari M, Singh K, Brox T (2018) Eco: efficient convolutional network for online video understanding. In: Proceedings of the European conference on computer vision (ECCV), pp 695\u2013712","DOI":"10.1007\/978-3-030-01216-8_43"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04365-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-022-04365-8\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-022-04365-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,7,4]],"date-time":"2023-07-04T12:14:14Z","timestamp":1688472854000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-022-04365-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,10]]},"references-count":68,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2023,7]]}},"alternative-id":["4365"],"URL":"https:\/\/doi.org\/10.1007\/s10489-022-04365-8","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"value":"0924-669X","type":"print"},{"value":"1573-7497","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,10]]},"assertion":[{"value":"25 November 2022","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"10 January 2023","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}