This paper presents a method of learning and recognizing generic object categories using part-based spatial models. The models are multiscale, with a scene component that specifie...
In multiagent systems ontologies are essential because they facilitate tasks like communications and reasoning. In this paper, inspired by studies in cognitive psychology, we pres...
Most existing object segmentation algorithms suffer from a so-called under-segmentation problem, where parts of the segmented object are missing and holes often occur inside the ob...
We present a novel method for unsupervised classification, including the discovery of a new category and precise object and part localization. Given a set of unlabelled images, som...
Leonid Karlinsky, Michael Dinerstein, Dan Levi, Sh...
The advent of social tagging systems has enabled a new community-based view of the Web in which objects like images, videos, and Web pages are annotated by thousands of users. Und...