{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,10]],"date-time":"2026-06-10T10:12:41Z","timestamp":1781086361972,"version":"3.54.1"},"reference-count":43,"publisher":"Elsevier BV","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/tdm\/userlicense\/1.0\/"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.elsevier.com\/legal\/tdmrep-license"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-017"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-012"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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":["Pattern Recognition Letters"],"published-print":{"date-parts":[[2022,1]]},"DOI":"10.1016\/j.patrec.2021.12.005","type":"journal-article","created":{"date-parts":[[2021,12,16]],"date-time":"2021-12-16T01:47:19Z","timestamp":1639619239000},"page":"136-143","update-policy":"https:\/\/doi.org\/10.1016\/elsevier_cm_policy","source":"Crossref","is-referenced-by-count":15,"special_numbering":"C","title":["SparseShift-GCN: High precision skeleton-based action recognition"],"prefix":"10.1016","volume":"153","author":[{"given":"Ying","family":"Zang","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"Yang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianjiao","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shuguang","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qingshan","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"78","reference":[{"key":"10.1016\/j.patrec.2021.12.005_bib0001","series-title":"2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1","article-title":"Going deeper with convolutions","author":"Szegedy","year":"2015"},{"key":"10.1016\/j.patrec.2021.12.005_bib0002","series-title":"2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He","year":"2016"},{"key":"10.1016\/j.patrec.2021.12.005_bib0003","series-title":"Computer Science - Computer Vision and Pattern Recognition","article-title":"You only look once: unified, real-time object detection","author":"Redmon","year":"2016"},{"key":"10.1016\/j.patrec.2021.12.005_bib0004","series-title":"Lecture Notes in Computer Science","article-title":"SSD: single S-hot MultiBox Detector, ECCV","author":"Liu","year":"2016"},{"key":"10.1016\/j.patrec.2021.12.005_bib0005","doi-asserted-by":"crossref","first-page":"2481","DOI":"10.1109\/TPAMI.2016.2644615","article-title":"Segnet: a deep convolutional encoder-decoder architecture for image segmentation","author":"Badrinarayanan","year":"2017","journal-title":"Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patrec.2021.12.005_bib0006","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"6230","article-title":"Pyramid scene parsing network","author":"Zhao","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0007","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"4724","article-title":"Convolutional pose machines","author":"Wei","year":"2016"},{"key":"10.1016\/j.patrec.2021.12.005_bib0008","series-title":"European Conference on Computer Vision","first-page":"483","article-title":"Stacked hourglass networks for human pose estimation","author":"Newell","year":"2016"},{"key":"10.1016\/j.patrec.2021.12.005_bib0009","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"3711","article-title":"Towards accurate multi-person pose estimation in the wild","author":"Papandreou","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0010","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"5686","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0011","series-title":"24th International Conference on Pattern Recognition","first-page":"645","article-title":"End-to-end video-level representation learning for action recognition","author":"Zhu","year":"2018"},{"key":"10.1016\/j.patrec.2021.12.005_bib0012","series-title":"24th International Conference on Pattern Recognition","first-page":"597","article-title":"Two stream gated fusion convnets for action recognition","author":"Zhu","year":"2018"},{"key":"10.1016\/j.patrec.2021.12.005_bib0013","doi-asserted-by":"crossref","first-page":"33","DOI":"10.1016\/j.neucom.2018.02.028","article-title":"Action recognition with motion map 3d network","author":"Sun","year":"2018","journal-title":"Neurocomputing"},{"key":"10.1016\/j.patrec.2021.12.005_bib0014","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"180","article-title":"Skeleton-Based Action Recognition with Shift Graph Convolutional Network","author":"Cheng","year":"2020"},{"key":"10.1016\/j.patrec.2021.12.005_bib0015","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1110","article-title":"Hierarchical recurrent neural network for skeleton based action re-cognition","author":"Du","year":"2015"},{"key":"10.1016\/j.patrec.2021.12.005_bib0016","series-title":"AAAI Conference on Artificial Intelligence","first-page":"4263","article-title":"An end-to-end spatio-temporal attention model f-or human action recognition from skeleton data","author":"Song","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0017","unstructured":"L. Li, W. Zheng, Z. Zhang, Y. Huang, L. Wang, Skeleton-Based Relational Modeling for Action Recognition, 2018. arXiv:1805.02556,"},{"key":"10.1016\/j.patrec.2021.12.005_bib0018","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1623","article-title":"Interpretable 3d human action analysis with temporal convolutional networks","author":"Kim","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0019","series-title":"IEEE International Conference on Multimedia & Expo Workshops","first-page":"597","article-title":"Skeleton-based action recognition with convolutional neural networks","author":"Li","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0020","series-title":"Thirty-Second AAAI Conference on Artificial Intelligence","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"Yan","year":"2018"},{"key":"10.1016\/j.patrec.2021.12.005_bib0021","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"538","article-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0022","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","article-title":"Skeleton-based action recognition with multi-stream adaptive graph convolutional networks","author":"Shi","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0023","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","article-title":"Actional-structural graph convolutional networks for skeleton-based action recognition","author":"Li","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0024","series-title":"Proceedings of the 27th ACM International Conference on Multimedia","first-page":"601","article-title":"Optimized skeleton-based action recognition via sparsified graph regression","author":"Gao","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0025","doi-asserted-by":"crossref","unstructured":"D. Tian, Z.M. Lu, X. Chen, L.H. Ma, An attentional spatial temporal graph convolutional network with co-occurrence feature learning for action recognition, 2020, pp. 12679\u201312697.","DOI":"10.1007\/s11042-020-08611-4"},{"key":"10.1016\/j.patrec.2021.12.005_bib0026","series-title":"Proceedings of the IEEE Conference Computer Vision and Patten Recognition","first-page":"9127","article-title":"Shift: a Zero FLOP, Zero parameter alternative to spatial convolutions","author":"Wu","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0027","unstructured":"Gudovskiy D.A., Rigazio L. Shift CNN: Generalized Low-Precision Architecture for Inference of Convolutional Neural Networks 2017."},{"key":"10.1016\/j.patrec.2021.12.005_bib0028","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1213","article-title":"AddressNet: shift-based primitives for efficient convolutional neural networks","author":"Zhong","year":"2018"},{"key":"10.1016\/j.patrec.2021.12.005_bib0029","series-title":"European Conference on Computer Vision","first-page":"11214","article-title":"Motion feature network: fixed motion filter for action recognition","author":"Lee","year":"2018"},{"key":"10.1016\/j.patrec.2021.12.005_bib0030","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1010","article-title":"NTU RGB+D: a large scale dataset for 3D human activity analysis","author":"Shahroudy","year":"2016"},{"key":"10.1016\/j.patrec.2021.12.005_bib0031","first-page":"2684","article-title":"NTU RGB+D 120: a large-scale benchmark for 3d human activity understanding","author":"Liu","year":"2019","journal-title":"CoRR"},{"key":"10.1016\/j.patrec.2021.12.005_bib0032","series-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","first-page":"2649","article-title":"Cross-view action modeling, learning and recognition","author":"Wang. X. Nie","year":"2014"},{"key":"10.1016\/j.patrec.2021.12.005_bib0033","series-title":"2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","first-page":"1227","article-title":"An attention enhanced graph convolutional LSTM network for skeleton-based action recognition","author":"Si","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0034","series-title":"Advancesin Neural Information Processing Systems Workshops","article-title":"Automatic differentiation in PyTorch","author":"Paszke","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0035","series-title":"Proceedings of the IEEE international conference on computer vision","first-page":"4041","article-title":"Differential recurrent neural networks for action recognition","author":"Veeriah","year":"2015"},{"key":"10.1016\/j.patrec.2021.12.005_bib0036","series-title":"2017 IEEE International Conference on Computer Vision (ICCV)","first-page":"2136","article-title":"View adaptive recurrent neural networks for high performance human action recognition from skeleton data","author":"Zhang","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0037","doi-asserted-by":"crossref","first-page":"346","DOI":"10.1016\/j.patcog.2017.02.030","article-title":"Enhanced skeleton visualization for view invariant human action recognition","volume":"68","author":"Liu","year":"2017","journal-title":"Pattern Recognit."},{"key":"10.1016\/j.patrec.2021.12.005_bib0038","series-title":"Proceedings of the AAAI Conference on Artificial Intelligence","first-page":"8989","article-title":"Graph cnns with motif and variable temporal block for skeleton-based action recognition","volume":"33","author":"Wen","year":"2019"},{"key":"10.1016\/j.patrec.2021.12.005_bib0039","series-title":"IEEE\/CVF Conference on Computer Vision and Pattern Recognition","first-page":"7904","article-title":"Skeleton-based action recognition with directed graph neural networks","author":"Shi","year":"2019"},{"issue":"5","key":"10.1016\/j.patrec.2021.12.005_bib0040","doi-asserted-by":"crossref","first-page":"914","DOI":"10.1109\/TPAMI.2013.198","article-title":"Learning actionlet ensemble for 3d human action recognition","volume":"36","author":"Wang","year":"2014","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"10.1016\/j.patrec.2021.12.005_bib0041","series-title":"2017 IEEE International Conference on Computer Vision (ICCV","first-page":"1012","article-title":"Ensemble deep learning for skeleton-based action recognition using temporal sliding LSTM networks","author":"Lee","year":"2017"},{"key":"10.1016\/j.patrec.2021.12.005_bib0042","series-title":"IEEE Conference on Computer Vision and Pattern Recognition","first-page":"1010","article-title":"Disentangling and unifying graph convolutions for skeleton-based action recognition","author":"Liu","year":"2020"},{"key":"10.1016\/j.patrec.2021.12.005_bib0043","doi-asserted-by":"crossref","unstructured":"Y.X. Chen, Z.Q. Zhang, C.F. Yuan, B. Li, Y. Deng and W.M. Hu, Channel-wise topology refinement graph convolution for skeleton-based action recognition, in 2021.","DOI":"10.1109\/ICCV48922.2021.01311"}],"container-title":["Pattern Recognition Letters"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865521004360?httpAccept=text\/xml","content-type":"text\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/api.elsevier.com\/content\/article\/PII:S0167865521004360?httpAccept=text\/plain","content-type":"text\/plain","content-version":"vor","intended-application":"text-mining"}],"deposited":{"date-parts":[[2025,9,29]],"date-time":"2025-09-29T06:16:45Z","timestamp":1759126605000},"score":1,"resource":{"primary":{"URL":"https:\/\/linkinghub.elsevier.com\/retrieve\/pii\/S0167865521004360"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,1]]},"references-count":43,"alternative-id":["S0167865521004360"],"URL":"https:\/\/doi.org\/10.1016\/j.patrec.2021.12.005","relation":{},"ISSN":["0167-8655"],"issn-type":[{"value":"0167-8655","type":"print"}],"subject":[],"published":{"date-parts":[[2022,1]]},"assertion":[{"value":"Elsevier","name":"publisher","label":"This article is maintained by"},{"value":"SparseShift-GCN: High precision skeleton-based action recognition","name":"articletitle","label":"Article Title"},{"value":"Pattern Recognition Letters","name":"journaltitle","label":"Journal Title"},{"value":"https:\/\/doi.org\/10.1016\/j.patrec.2021.12.005","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"}]}}