Adaptive Multi-Order Graph Neural Networks for Human Motion Prediction

Pengxiang Su, Xuanjing Shen, Zenan Shi, Wei Liu

Abstract: Human motion prediction aims at capturing the hidden temporal correlations between historical motion and future poses. Various graph convolution networks have been presented for encoding the spatial dependencies between joints. Empirically, the crucial shortcoming of these methods is that they fail to extract enough spatially relevant information. In this paper, we propose an adaptive multi-order context fusion architecture that consists of two components. A novel message propagation module encodes the interaction between joints, while highlighting contexts from closely related joints. An adaptive aggregation module fuses various information from different-order joint features. Our model is evaluated on Human 3.6 Million dataset. Extensive experiments show that our method achieves state-of-the-art performance on short-term and long-term predictions.