Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...
Conditional random fields (CRF) are widely used for predicting output variables that have some internal structure. Most of the CRF research has been done on structured classificati...
Abstract. Many real world problems are given in the form of multiple measurements comprising local descriptions or tasks. We propose that a dynamical organization of a population o...
Cloth modeling and recognition is an important and challenging problem in both vision and graphics tasks, such as dressed human recognition and tracking, human sketch and portrait...
This paper introduces a new formulation for discrete image labeling tasks, the Decision Tree Field (DTF), that combines and generalizes random forests and conditional random fiel...
Sebastian Nowozin, Carsten Rother, Shai Bagon, Ban...