HUMOF: Human Motion Forecasting in Interactive Social Scenes

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Sun, Caiyi, Sun, Yujing, Han, Xiao, Yang, Zemin, Liu, Jiawei, Zhu, Xinge, Yiu, Siu Ming, Ma, Yuexin
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866910091981094912
author Sun, Caiyi
Sun, Yujing
Han, Xiao
Yang, Zemin
Liu, Jiawei
Zhu, Xinge
Yiu, Siu Ming
Ma, Yuexin
author_facet Sun, Caiyi
Sun, Yujing
Han, Xiao
Yang, Zemin
Liu, Jiawei
Zhu, Xinge
Yiu, Siu Ming
Ma, Yuexin
contents 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. The source code will be available at https://github.com/scy639/HUMOF.
format Preprint
id arxiv_https___arxiv_org_abs_2506_03753
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle HUMOF: Human Motion Forecasting in Interactive Social Scenes
Sun, Caiyi
Sun, Yujing
Han, Xiao
Yang, Zemin
Liu, Jiawei
Zhu, Xinge
Yiu, Siu Ming
Ma, Yuexin
Computer Vision and Pattern Recognition
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. The source code will be available at https://github.com/scy639/HUMOF.
title HUMOF: Human Motion Forecasting in Interactive Social Scenes
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2506.03753