Simple Baseline for Single Human Motion Forecasting

2021/10/14 by Chenxi Wang, Wang, Chenxi, Yunfeng Wang +5
Computer Science · #Anomaly Detection Techniques and Applications #Computer Vision and Pattern Recognition (cs.CV) #FOS: Computer and information sciences #Human Pose and Action Recognition #Video Surveillance and Tracking Methods

paper · pdf · doi:10.48550/arxiv.2110.07495

openalex publication_date 2021/10/14 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28

Abstract

Global human motion forecasting is important in many fields, which is the combination of global human trajectory prediction and local human pose prediction. Visual and social information are often used to boost model performance, however, they may consume too much computational resource. In this paper, we establish a simple but effective baseline for single human motion forecasting without visual and social information, equipped with useful training tricks. Our method "futuremotion_ICCV21" outperforms existing methods by a large margin on SoMoF benchmark. We hope our work provide new ideas for future research.

Citations

• Semi-Supervised Classification with Graph Convolutional Networks

Related

• Personalized Pose Forecasting
• Towards Accurate Human Motion Prediction via Iterative Refinement
• Progressively Generating Better Initial Guesses Towards Next Stages for High-Quality Human Motion Prediction
• Socially and Contextually Aware Human Motion and Pose Forecasting
• Disentangling Human Dynamics for Pedestrian Locomotion Forecasting with Noisy Supervision