Current uses of tagged images typically exploit only the most explicit information: the link between the nouns named and the objects present somewhere in the image. We propose to ...
Sung Ju Hwang, University of Texas, Kristen Grauma...
Previous works have demonstrated that the face recognition performance can be improved significantly in low dimensional linear subspaces. Conventionally, principal component analy...
Due to the tremendous increase of electronic information with respect to the size of data sets as well as their dimension, dimension reduction and visualization of high-dimensiona...
One of the fundamental problems in Content-Based Image Retrieval (CBIR) has been the gap between low-level visual features and high-level semantic concepts. To narrow down this gap...
The High-Energy Physics (HEP) community spearheaded Open Access with over half a century of dissemination of pre-prints, culminating in the arXiv system. It is now proposing an Op...