Decoding Children's Gait Behavior

2026-07-31

AI Summary

This study addresses the limitations of existing 3D sensor–based pediatric gait analysis systems, which are costly, intrusive, and poorly suited for routine clinical use, particularly in capturing subtle and irregular gait patterns in children aged 3–17 years. To bridge this gap, the work introduces pediatric gait analysis into the domain of RGB video action recognition, presenting a large-scale dataset comprising over 1,100 high-frame-rate videos from 110 participants. The authors propose a unified end-to-end framework that decodes clinically relevant gait features directly from standard RGB videos. By leveraging high-frame-rate capture, anonymized pose sequence alignment, and multi-view gait cycle modeling, the method effectively captures fine-grained gait dynamics. The study further exposes the shortcomings of current foundation models and multimodal large language models on this task and establishes the first automated, clinically oriented benchmark for pediatric gait assessment, offering a practical pathway for early screening of motor impairments in children.

Abstract

We introduce a new problem domain for human action recognition: the fine-grained analysis of children's gait behaviors from standard RGB video. We specifically target the ambulatory patterns of children aged 3-17 years. Such behaviors arise naturally in the diagnosis and treatment of several critical developmental and neuromuscular disorders, such as cerebral palsy and hemiplegia. Despite their clinical value, current 3D sensor-based gait analysis systems are expensive, intrusive, and often impractical for young subjects. To address this, we introduce a new dataset comprising over 1,100 high-frame-rate (60 FPS) video sequences from 110 subjects, accompanied by synchronized, anonymized pose sequences. In each session, the child performs a 5-second "walk-around" task, capturing the gait cycle from multiple viewpoints. Crucially, we demonstrate that current state-of-the-art approaches, including gait foundation models and Multimodal Large Language Models (MLLMs), fail to effectively resolve these clinical nuances. We identify the key technical challenges in analyzing these erratic and subtle motor patterns and describe a unified end-to-end framework for decoding fundamental components of pediatric gait. Through comprehensive experimental results, we demonstrate the potential of this dataset to drive novel research questions and establish a rigorous baseline for automated child gait assessment.

Problem

• children's gait
• human action recognition
• developmental disorders
• neuromuscular disorders
• RGB video analysis

Innovation

• pediatric gait analysis
• RGB video-based action recognition
• fine-grained motor behavior
• end-to-end gait decoding
• clinical motion assessment