Abstract. We propose a generative approach to the problem of labeling images containing configurations of objects from multiple classes. The main building blocks are dense statisti...
The task of Semantic Role Labeling (SRL) is often divided into two sub-tasks: verb argument identification, and argument classification. Current SRL algorithms show lower results ...
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...
This paper presents a codebook learning approach for image classification and retrieval. It corresponds to learning a weighted similarity metric to satisfy that the weighted simil...
We consider the following setting: a decision maker must make a decision based on reported data points with binary labels. Subsets of data points are controlled by different selfi...
Reshef Meir, Ariel D. Procaccia, Jeffrey S. Rosens...