—Visual categorization is important to manage large collections of digital images and video, where textual metadata is often incomplete or simply unavailable. The bag-of-words mo...
Koen E. A. van de Sande, Theo Gevers, Cees G. M. S...
The Support Vector Machine (SVM) methodology is an effective, supervised, machine learning method that gives stateof-the-art performance for brain state classification from funct...
Yongxin Taylor Xi, Hao Xu, Ray Lee, Peter J. Ramad...
Compressive sensing accurately reconstructs a signal that is sparse in some basis from measurements, generally consisting of the signal’s inner products with Gaussian random vec...
Markov random field (MRF) theory provides a basis for modeling contextual constraints in visual processing and interpretation. It enables us to develop optimal vision algorithms sy...
During tracking, lens zoom acts as a gain between scene dynamics and fixation errors, providing a trade-off between maximising resolution and minimising tracking error. Using a li...