“…Flourished deep learning methods, especially convolutional neural networks (CNNs) ( Lecun et al, 1998 ), could adaptively extract features from diversified datasets. Also, they have been proven more potent than classic computer vision algorithms like wavelet transforms ( Romero et al, 2009 ) and Radon transforms ( Aradhya et al, 2007 ) on a famous grayscale dataset MNIST, even without supervising ( Ji et al, 2019 ). Therefore, we attempt to adopt CNNs to achieve end-to-end feature extractions of animal behaviors that are comprehensive and discriminative.…”