MediaPipe Feature Extractions — Equine-Human Behaviour Recognition
收藏官方服务：
资源简介：
MediaPipe feature extractions (410MB) generated from 28 equine-human interaction videos using YOLOv8 and MediaPipe Pose. Part of the dataset accompanying: "Multi-Modal Feature Fusion and Hierarchical Classification for Automated Equine-Human Interaction Behavior Recognition", submitted to MDPI Sensors, March 2026. Main code repository: https://doi.org/10.5281/zenodo.19167080
提供机构：
Zenodo创建时间：
2026-03-22
