Dataset for: Interpretable Performance Modeling in Gymnastics Using Video-Based Pose Estimation
Abstract
This repository contains the processed datasets and analysis code used in the study “Interpretable performance modeling in gymnastics using video-based pose estimation”.The data include extracted human pose keypoints, derived kinematic features, and scripts for model training and evaluation.Raw video data are not shared due to privacy and ethical considerations.Version noteThis version replaces the previously uploaded raw video files. Raw video data were removed due to privacy and ethical considerations. The updated dataset contains only processed pose keypoints, derived kinematic features, and analysis scripts necessary to reproduce the study findings.
Fields of Study & Subjects
Human Pose and Action Recognition
Sports Dynamics and Biomechanics
Physical Education and Training Studies
Publication details
- Journal / source
- Zenodo (CERN European Organization for Nuclear Research)
- Publication date
- 9 February 2026
- Document type
- Dataset