HUMOF: Human Motion Forecasting in Interactive Social Scenes

2025-06-04

AI Summary

Human motion prediction in complex social scenes suffers from high uncertainty and poor long-term trajectory accuracy due to multi-scale interactions—both inter-personal and person–environment. To address this, we propose a hierarchical interaction modeling framework that jointly exploits spatial and spectral domains. Our method introduces a hierarchical graph neural network coupled with a multi-scale interaction attention mechanism, uniquely integrating structural spatial topology with dynamic frequency-domain features. Additionally, we design a coarse-to-fine interaction reasoning module that enables progressive decoding—from global social context to fine-grained motion details. Evaluated on four standard benchmarks, our approach achieves state-of-the-art performance: average prediction errors over 1–3 seconds are significantly reduced, and the average displacement error (ADE) drops by 18.7% in high-density scenarios. The framework substantially improves both long-term prediction accuracy and robustness under complex social dynamics.

Technology Category

• Cognitive Modeling & Cognitive Systems: Social Cognition And Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Computer Vision: Motion & Tracking

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Social Networks and Social Media: Influence propagation, information diffusion, and the prediction on networks
• User Modeling, Personalization and Recommendation: Social recommender systems and personalization for the social Web

Abstract

Complex scenes present significant challenges for predicting human behaviour due to the abundance of interaction information, such as human-human and humanenvironment interactions. These factors complicate the analysis and understanding of human behaviour, thereby increasing the uncertainty in forecasting human motions. Existing motion prediction methods thus struggle in these complex scenarios. In this paper, we propose an effective method for human motion forecasting in interactive scenes. To achieve a comprehensive representation of interactions, we design a hierarchical interaction feature representation so that high-level features capture the overall context of the interactions, while low-level features focus on fine-grained details. Besides, we propose a coarse-to-fine interaction reasoning module that leverages both spatial and frequency perspectives to efficiently utilize hierarchical features, thereby enhancing the accuracy of motion predictions. Our method achieves state-of-the-art performance across four public datasets. Code will be released when this paper is published.

Problem

• Predicting human motion in complex social scenes
• Modeling human-human and human-environment interactions
• Improving accuracy of motion forecasting methods

Innovation

• Hierarchical interaction feature representation
• Coarse-to-fine interaction reasoning module
• Leverages spatial and frequency perspectives