Predicting human poses via recurrent attention network
Jianwei Tang, Jieming Wang, Jian–Fang Hu
Abstract
Abstract Human motion prediction is a challenging task due to the diversity and randomness of future poses. Due to the inherent topology of pose data, most recent work has used graph convolution networks (GCNs) to accomplish the task of human motion prediction. However, the GCN-based method has a major shortcoming in that the modeling of temporal information is insufficient. In this paper, we propose a simple approach that combines recurrent neural networks (RNNs) and attention mechanism for motion prediction, which considers both spatial relations between different joints and temporal correlation. The query, key and value of the attention mechanism allow us to select the information we need for the subsequent prediction. To solve the difficult problem of RNN training, we utilize uncertainty and strong short-term constraints to optimize the training process. We evaluate our method on several standard benchmark datasets for human motion prediction, i.e., the Human3.6M dataset and the CMU MoCap dataset. The experimental results show that our approach outperforms previous approaches.