Nonnegative Tensor-Based Linear Dynamical Systems for Recognizing Human Action from 3D Skeletons

Table 2

Recognition rate on the MSR-Action3D dataset based on experimental protocol of [8].

Approach	Recognition Accuracy
SE3[12]	89.48
Grassmann Manifold[8]	91.21
Learning features combination [16]	90.36 ± 2.45
ST-LSTM + Trust Gate [17]	94.80
Bi-LSTM [15]	86.18
Our approach	96.97