Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting

TL;DR

This paper introduces a lightweight skeletal human motion forecasting model that employs graph convolutions to effectively utilize the body's structural information, achieving competitive prediction accuracy with fewer parameters.

Contribution

The paper presents a novel lightweight model that integrates skeletal structure via graph convolutions for improved motion prediction efficiency.

Findings

Achieves competitive prediction accuracy with fewer parameters.

Effectively leverages skeletal structure through graph convolutions.

Demonstrates the model's efficiency in human motion forecasting.

Abstract

Prediction of movements is essential for successful cooperation with intelligent systems. We propose a model that integrates organized spatial information as given through the moving body's skeletal structure. This inherent structure is exploited in our model through application of Graph Convolutions and we demonstrate how this allows leveraging the structured spatial information into competitive predictions that are based on a lightweight model that requires a comparatively small number of parameters.