Sample Data and Annotations for "Beyond Proximity: Pose-Based Interaction Inference in Dairy Cattle"

Read full text
Authors: Sibi Chakravathy Parivendan, Kashfia Sailunaz, Suresh Raja Neethirajan
Cited by: 0

Abstract

This repository provides representative sample data supporting the manuscript“Beyond Proximity: A Keypoint-Trajectory Framework for Classifying Affiliative and Agonistic Social Networks in Dairy Cattle.” The dataset includes: Selected sample video frames from a commercial dairy barn (overhead camera view), Corresponding cow bounding box annotations, Anatomical keypoint annotations (subset), Example interaction clips illustrating affiliative and agonistic behaviors, Derived feature representations used for interaction classification. These data are released for transparency, reproducibility, and reviewer inspection only.Due to farm privacy agreements and animal data governance constraints, full raw video streams are not publicly released. Access to additional data may be considered upon reasonable request to the corresponding author. The samples demonstrate key methodological aspects discussed in the paper, including pose-based interaction inference, tolerance to partial occlusion during close contact, and the distinction between proximity-only and keypoint-trajectory-based interaction analysis.

Fields of Study & Subjects

Human Pose and Action Recognition Animal Behavior and Welfare Studies Smart Agriculture and AI

Publication details

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