The paper presents results of the face verification contest that was organized in conjunction with International Conference on Pattern Recognition 2000 [14]. Participants had to u...
Jiri Matas, Miroslav Hamouz, Kenneth Jonsson, Jose...
Many reconfigurable architectures offer partial dynamic configurability, but current system-level tools cannot guarantee feasible implementations when exploiting this feature. We ...
Sudarshan Banerjee, Elaheh Bozorgzadeh, Nikil D. D...
We consider the problem of learning a similarity function from a set of positive equivalence constraints, i.e. 'similar' point pairs. We define the similarity in informa...
Many kernel learning methods have to assume parametric forms for the target kernel functions, which significantly limits the capability of kernels in fitting diverse patterns. Som...
Graph-based methods for semi-supervised learning have recently been shown to be promising for combining labeled and unlabeled data in classification problems. However, inference f...