PlayClass: Automated Play Behaviour Classification in Poultry
For animal welfare researchers, this work provides an automated method to detect positive welfare behaviours (play) in poultry, though performance is moderate and dataset challenges persist.
PlayClass introduces a pipeline for classifying play behaviour in poultry from top-down video, achieving 77.0 macro-averaged F1 using V-JEPA 2.1 with handcrafted features, though challenges remain due to similar kinematics and occlusion.
Automated monitoring of animal welfare has largely targeted negative indicators, leaving positive welfare behaviours such as play underexplored. To address this gap, we present PlayClass, a pipeline for play-behaviour classification in poultry from top-down pen video. The pipeline leverages long-duration tracking with SAM 3 via YOLO-guided chunk boundaries to minimise identity errors in point-based prompting, and frozen embeddings from image and video foundation models for play action classification. Although handcrafted motion features from tracked masks alone achieved competitive accuracy, V-JEPA 2.1 consistently outperformed all other backbones across model scales, reaching 77.0 macro-averaged F$_1$ when combined with handcrafted features. Despite this result, the dataset remains challenging due to play sub-types sharing similar kinematic profiles with non-play and inter-bird occlusion. Overall, our work provides encouraging evidence towards automated frameworks for play behaviour classification in poultry.