An Attractor-Guided Neural Networks for Skeleton-Based Human Motion Prediction

05/20/2021
by   Pengxiang Ding, et al.
0

Joint relation modeling is a curial component in human motion prediction. Most existing methods tend to design skeletal-based graphs to build the relations among joints, where local interactions between joint pairs are well learned. However, the global coordination of all joints, which reflects human motion's balance property, is usually weakened because it is learned from part to whole progressively and asynchronously. Thus, the final predicted motions are sometimes unnatural. To tackle this issue, we learn a medium, called balance attractor (BA), from the spatiotemporal features of motion to characterize the global motion features, which is subsequently used to build new joint relations. Through the BA, all joints are related synchronously, and thus the global coordination of all joints can be better learned. Based on the BA, we propose our framework, referred to Attractor-Guided Neural Network, mainly including Attractor-Based Joint Relation Extractor (AJRE) and Multi-timescale Dynamics Extractor (MTDE). The AJRE mainly includes Global Coordination Extractor (GCE) and Local Interaction Extractor (LIE). The former presents the global coordination of all joints, and the latter encodes local interactions between joint pairs. The MTDE is designed to extract dynamic information from raw position information for effective prediction. Extensive experiments show that the proposed framework outperforms state-of-the-art methods in both short and long-term predictions in H3.6M, CMU-Mocap, and 3DPW.

READ FULL TEXT
research
03/17/2020

Dynamic Multiscale Graph Neural Networks for 3D Skeleton-Based Human Motion Prediction

We propose novel dynamic multiscale graph neural networks (DMGNN) to pre...
research
01/06/2019

Self-Expressive Subspace Clustering to Recognize Motion Dynamics of a Multi-Joint Coordination for Chronic Ankle Instability

Ankle sprains and instability are major public health concerns. Up to 70...
research
07/13/2022

Global-local Motion Transformer for Unsupervised Skeleton-based Action Learning

We propose a new transformer model for the task of unsupervised learning...
research
07/08/2021

Uncertainty-aware Human Motion Prediction

Human motion prediction is essential for tasks such as human motion anal...
research
08/09/2023

Joint-Relation Transformer for Multi-Person Motion Prediction

Multi-person motion prediction is a challenging problem due to the depen...
research
03/10/2023

GATOR: Graph-Aware Transformer with Motion-Disentangled Regression for Human Mesh Recovery from a 2D Pose

3D human mesh recovery from a 2D pose plays an important role in various...
research
11/30/2022

T2G-Former: Organizing Tabular Features into Relation Graphs Promotes Heterogeneous Feature Interaction

Recent development of deep neural networks (DNNs) for tabular learning h...

Please sign up or login with your details

Forgot password? Click here to reset