Hierarchical Human Action Recognition with Self-Selection Classifiers via Skeleton Data<xref rid="ctp_70_5_633fn1" ref-type="fn">*</xref><fn id="ctp_70_5_633fn1"><label>*</label><p>Supported by the National Nature Science Foundation of China under Grant Nos. 11475003, 61603003, and 11471093; the Key Project of Cultivation of Leading Talents in Universities of Anhui Province under Grant No. gxfxZD2016174; Funds of Integration of Cloud Computing and Big Data; Innovation of Science and Technology of Ministry of Education of China under Grant No. 2017A09116; and Anhui Provincial Department of Education Outstanding Top-Notch Talent-Funded Project under Grant No. gxbjZD26</p></fn>

Hierarchical Human Action Recognition with Self-Selection Classifiers via Skeleton Data**

Supported by the National Nature Science Foundation of China under Grant Nos. 11475003, 61603003, and 11471093; the Key Project of Cultivation of Leading Talents in Universities of Anhui Province under Grant No. gxfxZD2016174; Funds of Integration of Cloud Computing and Big Data; Innovation of Science and Technology of Ministry of Education of China under Grant No. 2017A09116; and Anhui Provincial Department of Education Outstanding Top-Notch Talent-Funded Project under Grant No. gxbjZD26

Su Ben-Yue^{1, 2, †}, Wu Huang², Sheng Min^{2, 3}, Shen Chuan-Sheng^{3, ‡}

Schematic illustration of construction of OCU. F_Training and F_Testing represent the feature of training data and testing data, respectively. CV denotes the cross-validation method for determining the best classifier, C(1), C(2),C(j), and C(N) denote classifiers, R(1), R(2), R(j), and R(N) denote the recognition results by different classifiers, D is probability voting mechanism for decision-making, and C(*) indicates the optimal classifier.