To address these challenges, we propose the Social Behavior Atlas (SBeA), a few-shot learning framework for multi-animal 3D pose estimation, identity recognition and social behaviour classification. We propose a continuous occlusion copy-and-paste algorithm (COCA) for data augmentation in SBeA, co...
Multi-animal 3D social pose estimation, identification and behaviour embedding with a few-shot learning frameworkThe quantification of animal social behaviour is an essential step to reveal brain functions and psychiatric disorders during interaction phases. While deep learning-based approaches have enabled...
In the code, we provide 3D support for multi-animal pose estimation (via multi-camera use), plus this multi-animal variant can be integrated with our real-time software, DeepLabCut-Live!28. Another important user input is at the stage of tracking, where users can input how many animals ...
The desire to understand how the brain generates and patterns behavior has driven rapid methodological innovation in tools to quantify natural animal behavior. While advances in deep learning and computer vision have enabled markerless pose estimation in