Image auto-annotation, i.e., the association of words to whole images, has attracted considerable attention. In particular, unsupervised, probabilistic latent variable models of t...
In information retrieval, sub-space techniques are usually used to reveal the latent semantic structure of a data-set by projecting it to a low dimensional space. Non-negative mat...
Unsupervised vector-based approaches to semantics can model rich lexical meanings, but they largely fail to capture sentiment information that is central to many word meanings and...
Andrew L. Maas, Raymond E. Daly, Peter T. Pham, Da...
Easy reuse and integration of declaratively described information in a distributed setting is one of the main motivations for building the Semantic Web. Despite of this claim, reu...
Online photo services such as Flickr and Zooomr allow users to share their photos with family, friends, and the online community at large. An important facet of these services is ...