Deep learning has enabled computers to "see" like humans across many domains. Initial successes were in object-level visual recognition, such as object recognition, detection, and instance-level segmentation. As people are generally the dominant subjects in most images, this has facilitated the collection of large datasets, and has led to breakthroughs in person-centric applications, such as face detection and recognition, re-identification, pose estimation, and activity recognition. Much less attention has been paid to the wider class of animals. Beyond people and inanimate objects, deep vision can play a role in our understanding of animal behaviour and social structure, from insects to mammals. In this talk, I will describe recent collaborations with biologists and environmental scientists that involve fine-grained vision, from the level of the species to the individual.