Catflw: Cat facial landmarks in the wild dataset

This paper introduces the Cat Facial Landmarks in the Wild (CatFLW) dataset, which aims to address the significant lack of datasets for automated facial analysis in animals, particularly for recognizing internal states like pain and emotions. The CatFLW dataset comprises 2016 images of cat faces captured in various environments and conditions, each annotated with 48 specific facial landmarks. These landmarks were carefully selected based on their relationship with underlying musculature and their relevance to cat-specific Facial Action Units (CatFACS), making them reliable for pain recognition. The dataset was created using a semi-supervised, human-in-the-loop (AI-assisted) annotation method, which significantly reduced the time required for annotation compared to purely manual approaches. By providing the largest available amount of cat facial landmarks, the CatFLW dataset is intended to advance automatic detection of pain and emotions in cats and serve as a foundational resource for developing similar datasets for other animal species.