Multi-Semantics Aggregation Network Based on the Dynamic-Attention Mechanism for 3D Human Motion Prediction
Shi Jun-yu, Jianqi Zhong, Wenming Cao
Abstract
Graph convolutional network-based methods have recently shown promising performance in skeleton-based data processing. However, these methods have two critical issues in skeleton-based motion prediction tasks: First, graph modeling of motion poses is based on the fixed graph according to the physical connection of human joints and ignores the exploration of deep implicit information based on human dynamic kinetics. Second, existing methods usually use motion information in a single semantic space to model the whole motion sequences, underestimating diverse semantic patterns for improving the modeling ability. To address the first issue, we propose the Attention-based Dynamic Graph Convolution method, which tries to capture implicit semantic information dynamically. To address the second issue, we propose the Kinematic-based Semantics Aggregation Block (KSAB), which combines various semantic features from four semantic perspectives to rich motion representation. Integrating the above two designs, we propose a novel Multi-Semantics Aggregation Network (MANet), resulting in more comprehensive feature extraction in dynamic implicit semantics learning to enhance motion prediction. Extensive experiments are conducted to validate the effectiveness of MANet, which outperforms state-of-the-art methods by 10.9%, 6.6%, and 19.6% in terms of MPJPE for motion prediction on Human3.6M, CMU Mocap, and 3DPW datasets, respectively.