{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,28]],"date-time":"2025-10-28T18:42:04Z","timestamp":1761676924597,"version":"3.41.2"},"reference-count":36,"publisher":"Wiley","issue":"1","license":[{"start":{"date-parts":[[2021,1,7]],"date-time":"2021-01-07T00:00:00Z","timestamp":1609977600000},"content-version":"vor","delay-in-days":6,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672305","61702295"],"award-info":[{"award-number":["61672305","61702295"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Journal of Sensors"],"published-print":{"date-parts":[[2021,1]]},"abstract":"<jats:p>Action recognition is an important research direction of computer vision, whose performance based on video images is easily affected by factors such as background and light, while deep video images can better reduce interference and improve recognition accuracy. Therefore, this paper makes full use of video and deep skeleton data and proposes an RGB\u2010D action recognition based two\u2010stream network (SV\u2010GCN), which can be described as a two\u2010stream architecture that works with two different data. Proposed Nonlocal\u2010stgcn (S\u2010Stream) based on skeleton data, by adding nonlocal to obtain dependency relationship between a wider range of joints, to provide more rich skeleton point features for the model, proposed a video based Dilated\u2010slowfastnet (V\u2010Stream), which replaces traditional random sampling layer with dilated convolutional layers, which can make better use of depth the feature; finally, two stream information is fused to realize action recognition. The experimental results on NTU\u2010RGB+D dataset show that proposed method significantly improves recognition accuracy and is superior to st\u2010gcn and Slowfastnet in both CS and CV.<\/jats:p>","DOI":"10.1155\/2021\/8864870","type":"journal-article","created":{"date-parts":[[2021,1,8]],"date-time":"2021-01-08T01:14:53Z","timestamp":1610068493000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["RGB\u2010D Human Action Recognition of Deep Feature Enhancement and Fusion Using Two\u2010Stream ConvNet"],"prefix":"10.1155","volume":"2021","author":[{"given":"Yun","family":"Liu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ruidi","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8533-2084","authenticated-orcid":false,"given":"Hui","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Chuanxu","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Tao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2021,1,7]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"crossref","unstructured":"SiC. JingY. WangW. WangL. andTanT. Skeleton-based action recognition with spatial reasoning and temporal stack learning European Conference on Computer Vision 2018 Munich Germany 103\u2013118.","DOI":"10.1007\/978-3-030-01246-5_7"},{"key":"e_1_2_9_2_2","doi-asserted-by":"crossref","unstructured":"LiC. ZhongQ. XieD. andPuS. Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation International Joint Conference on Artificial Intelligence 2018 Stockholm Switzerland 786\u2013792.","DOI":"10.24963\/ijcai.2018\/109"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"GaurU. ZhuY. SongB. andRoy-ChowdhuryA. A \u201cString of feature graphs\u201d model for recognition of complex activities in natural videos International Conference on Computer Vision 2011 Barcelona Spain 2595\u20132602.","DOI":"10.1109\/ICCV.2011.6126548"},{"key":"e_1_2_9_4_2","doi-asserted-by":"publisher","DOI":"10.4018\/IJACI.2017100101"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2002.801449"},{"key":"e_1_2_9_6_2","doi-asserted-by":"crossref","unstructured":"WuC. Y. ZaheerM. HuH. ManmathaR. SmolaA. J. andKr\u00e4henb\u00fchlP. Compressed video action recognition Conference on Computer Vision and Pattern Recognition 2018 Salt Lake City USA 6026\u20136035.","DOI":"10.1109\/CVPR.2018.00631"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"LiC. ZhongQ. XieD. andPuS. Co-occurrence feature learning from skeleton data for action recognition and detection with hierarchical aggregation 2018 http:\/\/arxiv.org\/abs\/1804.06055.","DOI":"10.24963\/ijcai.2018\/109"},{"key":"e_1_2_9_8_2","doi-asserted-by":"crossref","unstructured":"CaoZ. SimonT. WeiS. E. andSheikhY. Realtime multi-person 2d pose estimation using part affinity fields Computer Vision and Pattern Recognition 2017 7291\u20137299.","DOI":"10.1109\/CVPR.2017.143"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"WangL. XiongY. WangZ. QiaoY. LinD. TangX. andVan GoolL. Temporal segment networks: towards good practices for deep action recognition European Conference on Computer Vision 2016 Cham 20\u201336.","DOI":"10.1007\/978-3-319-46484-8_2"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"CarreiraJ.andZissermanA. Quo vadis action recognition? A new model and the kinetics dataset Computer Vision and Pattern Recognition 2017 Hawaii USA 6299\u20136308.","DOI":"10.1109\/CVPR.2017.502"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.59"},{"key":"e_1_2_9_12_2","doi-asserted-by":"crossref","unstructured":"FeichtenhoferC. FanH. MalikJ. andHeK. Slowfast networks for video recognition Conference on Computer Vision 2019 Los Angeles USA 6202\u20136211.","DOI":"10.1109\/ICCV.2019.00630"},{"key":"e_1_2_9_13_2","unstructured":"LiC. ZhongQ. XieD. andPuS. Skeleton-based action recognition with convolutional neural networks International Conference on Multimedia & Expo Workshops 2017 Hong Kong China 597\u2013600."},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"KimT. S.andReiterA. Interpretable 3d human action analysis with temporal convolutional networks Computer Vision and Pattern Recognition Workshops 2017 Honolulu HI USA 1623\u20131631.","DOI":"10.1109\/CVPRW.2017.207"},{"key":"e_1_2_9_15_2","doi-asserted-by":"crossref","unstructured":"KeQ. BennamounM. AnS. SohelF. andBoussaidF. A new representation of skeleton sequences for 3d action recognition Computer Vision and Pattern Recognition 2017 Hawaii USA 3288\u20133297.","DOI":"10.1109\/CVPR.2017.486"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"LiQ. HanZ. andWuX. M. Deeper insights into graph convolutional networks for semi-supervised learning Thirty-Second AAAI Conference on Artificial Intelligence 2018 3538\u20133545.","DOI":"10.1609\/aaai.v32i1.11604"},{"key":"e_1_2_9_17_2","doi-asserted-by":"crossref","unstructured":"MoraisR. LeV. TranT. SahaB. MansourM. andVenkateshS. Learning regularity in skeleton trajectories for anomaly detection in videos Computer Vision and Pattern Recognition 2019 Los Angeles USA 11996\u201312004.","DOI":"10.1109\/CVPR.2019.01227"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"YanS. XiongY. andLinD. Spatial temporal graph convolutional networks for skeleton-based action recognition Thirty-second AAAI conference on artificial intelligence 2018 New Orleans USA.","DOI":"10.1609\/aaai.v32i1.12328"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"TangY. TianY. LuJ. LiP. andZhouJ. Deep progressive reinforcement learning for skeleton-based action recognition Computer Vision and Pattern Recognition 2018 Salt Lake City USA 5323\u20135332.","DOI":"10.1109\/CVPR.2018.00558"},{"key":"e_1_2_9_20_2","doi-asserted-by":"crossref","unstructured":"WangX. GirshickR. GuptaA. andHeK. Non-local neural networks Computer Vision and Pattern Recognition 2018 Salt Lake City USA 7794\u20137803.","DOI":"10.1109\/CVPR.2018.00813"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.2968054"},{"key":"e_1_2_9_22_2","doi-asserted-by":"publisher","DOI":"10.1152\/jn.1965.28.2.229"},{"key":"e_1_2_9_23_2","doi-asserted-by":"publisher","DOI":"10.1126\/science.3283936"},{"key":"e_1_2_9_24_2","doi-asserted-by":"publisher","DOI":"10.1113\/jphysiol.1984.sp015498"},{"key":"e_1_2_9_25_2","doi-asserted-by":"publisher","DOI":"10.1093\/cercor\/1.1.1"},{"key":"e_1_2_9_26_2","doi-asserted-by":"publisher","DOI":"10.1016\/0896-6273(94)90455-3"},{"key":"e_1_2_9_27_2","unstructured":"ChristophR. P. W.andPinzF. A. Spatiotemporal residual networks for video action recognition Advances in Neural Information Processing Systems 2016 3468\u20133476."},{"key":"e_1_2_9_28_2","doi-asserted-by":"crossref","unstructured":"FeichtenhoferC. PinzA. andZissermanA. Convolutional two-stream network fusion for video action recognition Computer Vision and Pattern Recognition 2016 Las Vegas USA 1933\u20131941.","DOI":"10.1109\/CVPR.2016.213"},{"key":"e_1_2_9_29_2","doi-asserted-by":"crossref","unstructured":"LinT. Y. Doll\u00e1rP. GirshickR. HeK. HariharanB. andBelongieS. Feature pyramid networks for object detection Computer Vision and Pattern Recognition 2017 2117\u20132125.","DOI":"10.1109\/CVPR.2017.106"},{"key":"e_1_2_9_30_2","doi-asserted-by":"crossref","unstructured":"ShahroudyA. LiuJ. NgT. T. andWangG. Ntu rgb+d: a large scale dataset for 3d human activity analysis Computer Vision and Pattern Recognition 2016 Las Vegas USA 1010\u20131019.","DOI":"10.1109\/CVPR.2016.115"},{"key":"e_1_2_9_31_2","article-title":"Ntu rgb+d 120: a large-scale benchmark for 3d human activity understanding","volume":"42","author":"Liu J.","year":"2019","journal-title":"IEEE transactions on pattern analysis and machine intelligence"},{"key":"e_1_2_9_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2691321"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"LeaC. FlynnM. D. VidalR. ReiterA. andHagerG. D. Temporal convolutional networks for action segmentation and detection Computer Vision and Pattern Recognition 2017 Hawaii USA 156\u2013165.","DOI":"10.1109\/CVPR.2017.113"},{"key":"e_1_2_9_34_2","unstructured":"PapadopoulosK. GhorbelE. AouadaD. andOtterstenB. Vertex feature encoding and hierarchical temporal modeling in a spatial-temporal graph convolutional network for action recognition 2019 http:\/\/arxiv.org\/abs\/1912.09745."},{"key":"e_1_2_9_35_2","unstructured":"LiC. WangP. WangS. HouY. andLiW. Skeleton-based action recognition using LSTM and CNN International Conference on Multimedia & Expo Workshops 2017 Hong Kong China 585\u2013590."},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"ShiL. ZhangY. ChengJ. andLuH. Two-stream adaptive graph convolutional networks for skeleton-based action recognition Conference on Computer Vision and Pattern Recognition 2019 Long Beach USA 12026\u201312035.","DOI":"10.1109\/CVPR.2019.01230"}],"container-title":["Journal of Sensors"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2021\/8864870.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/js\/2021\/8864870.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1155\/2021\/8864870","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,8,6]],"date-time":"2024-08-06T00:27:46Z","timestamp":1722904066000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1155\/2021\/8864870"}},"subtitle":[],"editor":[{"given":"Giovanni","family":"Diraco","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2021,1]]},"references-count":36,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2021,1]]}},"alternative-id":["10.1155\/2021\/8864870"],"URL":"https:\/\/doi.org\/10.1155\/2021\/8864870","archive":["Portico"],"relation":{},"ISSN":["1687-725X","1687-7268"],"issn-type":[{"type":"print","value":"1687-725X"},{"type":"electronic","value":"1687-7268"}],"subject":[],"published":{"date-parts":[[2021,1]]},"assertion":[{"value":"2020-07-17","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2020-12-24","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-01-07","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"8864870"}}