摘要
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.
针对人体运动高度复杂的运动学和时间相关性,本文提出了一种轻量级的多层残差时间卷积网络模型(Residual temporal convolutional network,RTCN)。该模型使用一维卷积高效获取人体运动的空间结构信息,提取人体运动时间序列中的相关性。在本文所提出的网络模型中应用残差结构来缓解深度网络中梯度消失的问题。在Human 3.6M数据集上进行的实验表明,与最新的方法相比,本文方法有效地改善了运动预测的误差,特别是在长期预测方面。
