A Lightweight Temporal Convolutional Network for Human Motion Prediction
Article
Figures
Metrics
Preview PDF
Reference
Related
Cited by
Materials
Abstract:
A lightweight multi-layer residual temporal convolutional network model (RTCN) is proposed to target the highly complex kinematics and temporal correlation of human motion. RTCN uses 1-D convolution to efficiently obtain the spatial structure information of human motion and extract the correlation in the time series of human motion. The residual structure is applied to the proposed network model to alleviate the problem of gradient disappearance in the deep network. Experiments on the Human 3.6M dataset demonstrate that the proposed method effectively reduces the errors of motion prediction compared with previous methods, especially of long-term prediction.
WANG You, QIAO Bing. A Lightweight Temporal Convolutional Network for Human Motion Prediction[J]. Transactions of Nanjing University of Aeronautics & Astronautics,2022,(S):150-157