We present a novel approach for detecting global behaviour
anomalies in multiple disjoint cameras by learning
time delayed dependencies between activities cross camera
views. Sp...
This paper describes a novel approach to teaching computer networking through packet traces of actual network traffic. The paper describes a set of exercises that use packet trace...
Automatic semantic summarisation of human activity and detection of unusual inactivity are useful goals for a vision system operating in a supportive home environment. Learned mod...
This paper addresses the problem of learning object models from egocentric video of household activities, using extremely weak supervision. For each activity sequence, we know onl...
Most previous work on trainable language generation has focused on two paradigms: (a) using a statistical model to rank a set of generated utterances, or (b) using statistics to i...