Spatio-Temporal Branching for Motion Prediction using Motion Increments

TL;DR

This paper introduces a spatio-temporal branching network that leverages motion increments to improve human motion prediction by decoupling temporal and spatial features, reducing noise, and enhancing accuracy.

Contribution

It proposes a novel decoupled learning framework with knowledge distillation for more effective motion modeling in human motion prediction.

Findings

Outperforms state-of-the-art methods on standard benchmarks.

Effectively reduces noise interference in motion data.

Enhances the expressiveness of motion representations.

Abstract

Human motion prediction (HMP) has emerged as a popular research topic due to its diverse applications, but it remains a challenging task due to the stochastic and aperiodic nature of future poses. Traditional methods rely on hand-crafted features and machine learning techniques, which often struggle to model the complex dynamics of human motion. Recent deep learning-based methods have achieved success by learning spatio-temporal representations of motion, but these models often overlook the reliability of motion data. Additionally, the temporal and spatial dependencies of skeleton nodes are distinct. The temporal relationship captures motion information over time, while the spatial relationship describes body structure and the relationships between different nodes. In this paper, we propose a novel spatio-temporal branching network using incremental information for HMP, which decouples the learning of temporal-domain and spatial-domain features, extracts more motion information, and achieves complementary cross-domain knowledge learning through knowledge distillation. Our approach effectively reduces noise interference and provides more expressive information for characterizing motion by separately extracting temporal and spatial features. We evaluate our approach on standard HMP benchmarks and outperform state-of-the-art methods in terms of prediction accuracy.