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

Table 3

Recognition rate on the UTKinect-Action dataset.

Approach	Recognition Accuracy
SE3[12]	97.08
EigenJoints[13]	97.10
Grassmann Manifold[8]	88.5
Key-Pose-Motifs[18]	93.47
Learning features combination[16]	98.00
Ensemble TS-LSTM[14]	96.97
tLDS[6]	96.48
Bi-LSTM[15]	96.89
Our approach	98.23