This paper presents a novel discriminative feature transformation, named full-rank generalized likelihood ratio discriminant analysis (fGLRDA), on the grounds of the likelihood ra...
Recently, there have been several attempts at creating `video textures', that is, synthesising new (potentially infinitely long) video clips based on existing ones. One way t...
Neill W. Campbell, Colin J. Dalton, David P. Gibso...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
We present an integrated framework for dynamic face detection and recognition, where head pose is estimated using Support Vector Regression, face detection is performed by Support...
Attentive vision is characterized by selective sensing in space and time as well as selective processing with respect to a specic task. Selection in space involves the splitting ...