Many learning tasks for computer vision problems can be described by multiple views or multiple features. These views can be exploited in order to learn from unlabeled data, a.k.a....
Research in visual surveillance systems is shifting from using few stationary, passive cameras to employing large heterogeneous sensor networks. One promising type of sensor in pa...
This paper describes a system which uses multiple visual processes to detect and track faces for video compression and transmission. The system is based on an architecture in whic...
This paper describes the application of a computational vision sensor to active binocular tracking. The sensor outputs are used to control the vergence angles of the two cameras a...
This paper proposes a learnt data-driven approach for accurate, real-time tracking of facial features using only intensity information. Constraints such as a-priori shape models o...
Eng-Jon Ong, Yuxuan Lan, Barry Theobald, Richard H...