{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,10,1]],"date-time":"2026-10-01T19:17:31Z","timestamp":1790882251939,"version":"4.1.0"},"reference-count":28,"publisher":"PeerJ","license":[{"start":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T00:00:00Z","timestamp":1732838400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2020YFB1712401"],"award-info":[{"award-number":["2020YFB1712401"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]},{"name":"Nature Science Foundation of China","award":["62006210, 62206252"],"award-info":[{"award-number":["62006210, 62206252"]}]},{"name":"Key Science and Technology Project of Henan Province","award":["221100211200, 221100210100"],"award-info":[{"award-number":["221100211200, 221100210100"]}]},{"name":"Technological Research Projects in Henan Province","award":["232102210090"],"award-info":[{"award-number":["232102210090"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"abstract":"<jats:p>In human skeleton-based action recognition, graph convolutional networks (GCN) have shown significant success. However, existing state-of-the-art methods struggle with complex actions, such as figure skating, where performance is often unsatisfactory. This issue arises from two main factors: the lack of shift, scale, and rotation invariance in GCN, making them especially vulnerable to perspective distortions in 2D coordinates, and the high variability in displacement velocity, which depends more on the athlete\u2019s individual capabilities than the actions themselves, reducing the effectiveness of motion information. To address these challenges, we propose a novel cosine stream to enhance the robustness of spatial features and introduce a Keyframe Sampling algorithm for more effective temporal feature extraction, eliminating the need for motion information. Our methods do not require modifications to the backbone. Experiments on the FSD-10, FineGYM, and NTU RGB+D datasets demonstrate a 2.6% improvement in Top-1 accuracy on the FSD-10 figure skating dataset compared to current state-of-the-art methods. The code has been made available at: <jats:uri xmlns:xlink=\"http:\/\/www.w3.org\/1999\/xlink\" xlink:href=\"https:\/\/github.com\/Jiahao-Guan\/pyskl_cosine\">https:\/\/github.com\/Jiahao-Guan\/pyskl_cosine<\/jats:uri>.<\/jats:p>","DOI":"10.7717\/peerj-cs.2523","type":"journal-article","created":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T10:13:42Z","timestamp":1732875222000},"page":"e2523","source":"Crossref","is-referenced-by-count":3,"title":["Angle information assisting skeleton-based actions recognition"],"prefix":"10.7717","volume":"10","author":[{"given":"Chengming","family":"Liu","sequence":"first","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiahao","family":"Guan","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haibo","family":"Pang","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1170-3911","authenticated-orcid":true,"given":"Lei","family":"Shi","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Engineering, Zhengzhou University, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yidan","family":"Chen","sequence":"additional","affiliation":[{"name":"National Engineering Laboratory for Cyber Science and Technology, Shangu Cyber Security Technology Company Limited, Zhengzhou, Henan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"4443","published-online":{"date-parts":[[2024,11,29]]},"reference":[{"key":"10.7717\/peerj-cs.2523\/ref-1","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1312.6203","article-title":"Spectral networks and locally connected networks on graphs","author":"Bruna","year":"2014"},{"key":"10.7717\/peerj-cs.2523\/ref-2","doi-asserted-by":"publisher","first-page":"13359","DOI":"10.48550\/arXiv.2107.12213","article-title":"Channel-wise topology refinement graph convolution for skeleton-based action recognition","author":"Chen","year":"2021"},{"key":"10.7717\/peerj-cs.2523\/ref-3","doi-asserted-by":"publisher","first-page":"20186","DOI":"10.1109\/CVPR52688.2022.01955","article-title":"Infogcn: representation learning for human skeleton-based action recognition","author":"Chi","year":"2022"},{"key":"10.7717\/peerj-cs.2523\/ref-4","article-title":"Openmmlab\u2019s next generation video understanding toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"10.7717\/peerj-cs.2523\/ref-5","first-page":"3844","article-title":"Convolutional neural networks on graphs with fast localized spectral filtering","volume-title":"Proceedings of the 30th International Conference on Neural Information Processing Systems","author":"Defferrard","year":"2016"},{"key":"10.7717\/peerj-cs.2523\/ref-6","doi-asserted-by":"publisher","first-page":"1110","DOI":"10.1109\/CVPR.2015.7298714","article-title":"Hierarchical recurrent neural network for skeleton based action recognition","author":"Du","year":"2015"},{"key":"10.7717\/peerj-cs.2523\/ref-7","article-title":"Dg-stgcn: dynamic spatial-temporal modeling for skeleton-based action recognition","author":"Duan","year":"2022a"},{"key":"10.7717\/peerj-cs.2523\/ref-8","doi-asserted-by":"publisher","first-page":"7351","DOI":"10.1145\/3503161.3548546","article-title":"Pyskl: towards good practices for skeleton action recognition","author":"Duan","year":"2022b"},{"key":"10.7717\/peerj-cs.2523\/ref-9","doi-asserted-by":"publisher","first-page":"2969","DOI":"10.1109\/CVPR52688.2022.00298","article-title":"Revisiting skeleton-based action recognition","author":"Duan","year":"2022c"},{"key":"10.7717\/peerj-cs.2523\/ref-10","first-page":"2224","article-title":"Convolutional networks on graphs for learning molecular fingerprints","volume-title":"Proceedings of the 28th International Conference on Neural Information Processing Systems","volume":"2","author":"Duvenaud","year":"2015"},{"key":"10.7717\/peerj-cs.2523\/ref-11","doi-asserted-by":"publisher","first-page":"4987","DOI":"10.48550\/arXiv.2209.02986","article-title":"Shifting perspective to see difference: a novel multi-view method for skeleton based action recognition","author":"Hou","year":"2022"},{"key":"10.7717\/peerj-cs.2523\/ref-12","doi-asserted-by":"publisher","first-page":"3288","DOI":"10.1109\/CVPR.2017.486","article-title":"A new representation of skeleton sequences for 3d action recognition","author":"Ke","year":"2017"},{"key":"10.7717\/peerj-cs.2523\/ref-13","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1609.02907","article-title":"Semi-supervised classification with graph convolutional networks","author":"Kipf","year":"2016"},{"key":"10.7717\/peerj-cs.2523\/ref-14","doi-asserted-by":"publisher","first-page":"10444","DOI":"10.1109\/ICCV51070.2023.00958","article-title":"Hierarchically decomposed graph convolutional networks for skeleton-based action recognition","author":"Lee","year":"2023"},{"issue":"3","key":"10.7717\/peerj-cs.2523\/ref-15","doi-asserted-by":"publisher","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 Recognition"},{"key":"10.7717\/peerj-cs.2523\/ref-16","article-title":"Fsd-10: a dataset for competitive sports content analysis","author":"Liu","year":"2020a"},{"key":"10.7717\/peerj-cs.2523\/ref-17","first-page":"143","article-title":"Disentangling and unifying graph convolutions for skeleton-based action recognition","author":"Liu","year":"2020b"},{"key":"10.7717\/peerj-cs.2523\/ref-18","doi-asserted-by":"publisher","first-page":"2014","DOI":"10.48550\/arXiv.1605.05273","article-title":"Learning convolutional neural networks for graphs","author":"Niepert","year":"2016"},{"issue":"4","key":"10.7717\/peerj-cs.2523\/ref-19","doi-asserted-by":"publisher","first-page":"4783","DOI":"10.1109\/TNNLS.2022.3201518","article-title":"Fusing higher-order features in graph neural networks for skeleton-based action recognition","volume":"35","author":"Qin","year":"2022","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"10.7717\/peerj-cs.2523\/ref-20","doi-asserted-by":"publisher","first-page":"1010","DOI":"10.1109\/CVPR.2016.115","article-title":"Ntu rgb+d: a large scale dataset for 3d human activity analysis","author":"Shahroudy","year":"2016"},{"key":"10.7717\/peerj-cs.2523\/ref-21","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR42600.2020.00269","article-title":"Finegym: a hierarchical video dataset for fine-grained action understanding","author":"Shao","year":"2020"},{"key":"10.7717\/peerj-cs.2523\/ref-22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01230","article-title":"Two-stream adaptive graph convolutional networks for skeleton-based action recognition","author":"Shi","year":"2019"},{"key":"10.7717\/peerj-cs.2523\/ref-23","doi-asserted-by":"publisher","first-page":"9532","DOI":"10.1109\/TIP.2020.3028207","article-title":"Skeleton-based action recognition with multi-stream adaptive graph convolutional networks","volume":"29","author":"Shi","year":"2020","journal-title":"IEEE Transactions on Image Processing"},{"key":"10.7717\/peerj-cs.2523\/ref-24","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11212","article-title":"An end-to-end spatio-temporal attention model for human action recognition from skeleton data","author":"Song","year":"2017"},{"key":"10.7717\/peerj-cs.2523\/ref-25","doi-asserted-by":"crossref","DOI":"10.1109\/CVPR.2019.00584","article-title":"Deep high-resolution representation learning for human pose estimation","author":"Sun","year":"2019"},{"key":"10.7717\/peerj-cs.2523\/ref-26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.10903","article-title":"Graph attention networks","author":"Velickovic","year":"2017"},{"issue":"11","key":"10.7717\/peerj-cs.2523\/ref-27","doi-asserted-by":"publisher","first-page":"2740","DOI":"10.1109\/TPAMI.2018.2868668","article-title":"Temporal segment networks for action recognition in videos","volume":"41","author":"Wang","year":"2019","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"10.7717\/peerj-cs.2523\/ref-28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.12328","article-title":"Spatial temporal graph convolutional networks for skeleton-based action recognition","author":"Yan","year":"2018"}],"container-title":["PeerJ Computer Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/peerj.com\/articles\/cs-2523.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2523.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2523.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/peerj.com\/articles\/cs-2523.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T10:13:54Z","timestamp":1732875234000},"score":1,"resource":{"primary":{"URL":"https:\/\/peerj.com\/articles\/cs-2523"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,29]]},"references-count":28,"alternative-id":["10.7717\/peerj-cs.2523"],"URL":"https:\/\/doi.org\/10.7717\/peerj-cs.2523","archive":["CLOCKSS","LOCKSS","Portico"],"relation":{},"ISSN":["2376-5992"],"issn-type":[{"value":"2376-5992","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,11,29]]},"article-number":"e2523"}}