A Multi-Species Acceleration Dataset for Self-Supervised Pretraining in Animal Behavior Recognition

Read full text Summarise with VIRAT
Authors: Yizhen Han, Pengcheng Zhu
Cited by: 0

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

AAR-Accel-Dataset is a unified multi-species animal activity recognition (AAR) dataset constructed from multiple publicly available livestock acceleration datasets. The dataset integrates heterogeneous tri-axial accelerometer recordings collected from different animal species. This repository organizes raw datasets, processed datasets, and unified pretraining data to facilitate reproducible research in animal behavior analysis.

Fields of Study & Subjects

Context-Aware Activity Recognition Systems Animal Behavior and Welfare Studies Smart Agriculture and AI

Publication details

Journal / source
Zenodo (CERN European Organization for Nuclear Research)
Publication date
19 March 2026
Language
EN
Document type
Dataset