In many real-world applications, such as image retrieval, it would be natural to measure the distances from one instance to others using instance specific distance which captures ...
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...
Several researchers have pointed out and begun to demonstrate that it is now possible to digitize an entire lifetime of experiences into a pocket-sized storage device, and thus to...
Visual understanding is often based on measuring similarity between observations. Learning similarities specific to a certain perception task from a set of examples has been show...
Michael Bronstein, Alexander Bronstein, Nikos Para...
Movies segmentation into semantically correlated units is a quite tedious task due to ”semantic gap”. Low-level features do not provide useful information about the semantical...