In this paper, we present a fast approach to obtain semantic scene segmentation with high precision. We employ a two-stage classifier to label all image pixels. First, we use the ...
Wen Yang, Dengxin Dai, Bill Triggs, Gui-Song Xia, ...
Many methods are available for computing semantic similarity between individual words, but certain NLP tasks require the comparison of word pairs. This paper presents a kernel-bas...
Visual vocabulary serves as a fundamental component in many computer vision tasks, such as object recognition, visual search, and scene modeling. While state-of-the-art approaches...
In the paper we present a generalized discriminative multiple instance learning algorithm (GD-MIL) for multimedia semantic concept detection. It combines the capability of the MIL...
Abstract. Ontologies are used for sharing information and are often collaboratively developed. They are adapted for different applications and domains resulting in multiple version...