We consider the problem of embedding arbitrary objects (e.g., images, audio, documents) into Euclidean space subject to a partial order over pairwise distances. Partial order cons...
We discuss the problem of clustering elements according to the sources that have generated them. For elements that are characterized by independent binary attributes, a closedform...
A key aspect of semantic image segmentation is to integrate local and global features for the prediction of local segment labels. We present an approach to multi-class segmentatio...
Almost all tree kernels proposed in the literature match substructures without taking into account their relative positioning with respect to one another. In this paper, we propos...
Fabio Aiolli, Giovanni Da San Martino, Alessandro ...
We propose a class of graphical models appropriate for structure prediction problems where the model structure is a function of the output structure. Incremental Sigmoid Belief Ne...