https://scholars.lib.ntu.edu.tw/handle/123456789/581391
標題: | Joint-oriented features for skeleton-based action recognition | 作者: | Liao L.-C Yang Y.-H LI-CHEN FU |
關鍵字: | Benchmarking; Large dataset; Action recognition; Competitive performance; Ensemble modeling; Hard task; Oriented features; State of the art; Musculoskeletal system | 公開日期: | 2019 | 卷: | 2019-October | 起(迄)頁: | 1154-1159 | 來源出版物: | Conference Proceedings - IEEE International Conference on Systems, Man and Cybernetics | 摘要: | In this paper, we propose joint-oriented features for skeleton-based action recognition, which aims to decrease the influence of ambiguous joints in the skeleton sequences. When doing skeleton-based action recognition, we noticed that if the skeleton data contains noisy joints, the result would be influenced by the noise. Since the selections of disambiguous joints might be impossible, it would be a hard task for humans to distinguish whether the joint in the frame is correct. To deal with this situation, we propose joint-oriented features to train joint-oriented models. If some joints are noise in the frame, the corresponding joint-oriented models would not perform well on the case. As we could not preFigure the noise in the data, we apply ensemble modeling with our joint-oriented models to let the disambiguous joints correct the ambiguous ones. To demonstrate the effectiveness of our proposed method, we conducted the experiments on three benchmark skeleton-based action datasets, including the large-scale challenging NTU-RGBD, and our approach achieves competitive performance over the state-of-the-art. ? 2019 IEEE. |
URI: | https://www.scopus.com/inward/record.uri?eid=2-s2.0-85076746114&doi=10.1109%2fSMC.2019.8914565&partnerID=40&md5=20bcc0ea587945821492fcaef88c9a2e https://scholars.lib.ntu.edu.tw/handle/123456789/581391 |
ISSN: | 1062922X | DOI: | 10.1109/SMC.2019.8914565 |
顯示於: | 資訊工程學系 |
在 IR 系統中的文件,除了特別指名其著作權條款之外,均受到著作權保護,並且保留所有的權利。