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, ‡}

Actions in MSRAction3D dataset, high arm wave (HiW), horizontal arm wave (HoW), hammer (H), hand catch (HCa), forward punch (FP), high throw (HT), draw x (DX), draw tick (DT), draw circle (DC), hand clap (HCl), two hand wave (TH), side-boxing (SB), bend (B), forward kick (FK), side kick (SK), jogging (J), tennis swing (TSw), tennis serve (TSe), golf swing (GS) and pick up & throw (P&T).