Task Recognition and Style Analysis in Dance Sequences

In this paper we present a novel approach to recognizing motion styles and identifying persons using the multi factor tensor (MFT) model. We apply a musical information analysis method in segmenting the motion sequence relevant to the key poses and the musical rhythm. We define a task model considering the repetitive motion segment, in which motion is decomposed into task and style. Given the motion data set, we formulate the MFT model and factorize it efficiently in recognizing the tasks, the styles, and the identities of persons. In our experiments, traditional dance by several people is chosen as the motion sequence. We capture the motion data for a few cycles, segment it using the musical analysis approach, normalize the segments, and recognize a task model from them. Various experiments to evaluate the potential of the recognition ability of our proposed approach are performed, and the results demonstrate the high accuracy of our model