Discriminative learning is challenging when examples are sets of features, and the sets vary in cardinality and lack any sort of meaningful ordering. Kernel-based classification m...
High-level generative models provide elegant descriptions of videos and are commonly used as the inference framework in many unsupervised motion segmentation schemes. However, app...
This paper presents a new formulation of the problem of motion estimation which attempts to give solutions to classical problems in the field, such as detection of motion disconti...
In this paper we propose a new framework for modeling 2D shapes. A shape is first described by a sequence of local features (e.g., curvature) of the shape boundary. The resulting ...
We propose a method for reconstruction of human brain states directly from functional neuroimaging data. The method extends the traditional multivariate regression analysis of dis...
Sennay Ghebreab, Arnold W. M. Smeulders, Pieter W....