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...
The maximum flow algorithm for minimizing energy functions of binary variables has become a standard tool in computer vision. In many cases, unary costs of the energy depend linea...
Abstract. In the European cognitive vision project VAMPIRE (IST2001-34401), mobile AR-kits are used for interactive teaching of a visual active memory. This is achieved by 3D augme...
Multiple Instance Learning (MIL) has been widely exploited in many computer vision tasks, such as image retrieval, object tracking and so on. To handle ambiguity of instance label...
A computer vision software library is a key component of vision-based applications. While there are several existing libraries, most are large and comple or limited to a particular...