This study develops a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We present and evaluate t...
With the goal of reducing computational costs without sacrificing accuracy, we describe two algorithms to find sets of prototypes for nearest neighbor classification. Here, the te...
Simultaneously segmenting and labeling images is a fundamental problem in Computer Vision. In this paper, we introduce a hierarchical CRF model to deal with the problem of labelin...
Predicting the occurrence of links is a fundamental problem in networks. In the link prediction problem we are given a snapshot of a network and would like to infer which interact...
Log-linear and maximum-margin models are two commonly-used methods in supervised machine learning, and are frequently used in structured prediction problems. Efficient learning of...
Michael Collins, Amir Globerson, Terry Koo, Xavier...