Humans are at the centre of a significant amount of research in computer vision.Endowing machines with the ability to perceive people from visual data is an immense scientific challenge with a high degree of direct practical relevance. Success in automatic perception can be measured at different levels of abstraction, and this will depend on which intelligent behaviour we are trying to replicate: the ability to localise persons in an image or in the environment,understanding how persons are moving at the skeleton and at the surface level, interpreting their interactions with the environment including with other people, and perhaps even anticipating future actions. In this thesis we tackle different sub-problems of the broad research area referred to as "looking at people", aiming to perceive humans in images at different levels of granularity. This includes bounding-box level pedestrian detection, different pixel-level recognition tasks, and 3D human shape and pose estimation. We conclude with a discussion of benchmarking practices in computer vision.