EE Thesis Defense

Methods to advance a machine's visual awareness of people with a focus on understanding `who is where' in video are presented. Who is used in a broad sense that includes not only the identity of a person but attributes of that person as well. Four problems are studied: 1) one-shot, real-time, instance detection, 2) real-time tracking, 3) fine-grained classification of people and 4) person re-identification. This work shows that using video for visual recognition is better than using single images. It also shows that it is possible to learn on-the-fly from single training examples.