We propose a new system to mine visual knowledge on the Web. There are huge image data as well as text data on the Web. However, mining image data from the Web is paid less attent...
Polysemy is a problem for methods that exploit image search engines to build object category models. Existing unsupervised approaches do not take word sense into consideration. We...
Given an unstructured collection of captioned images of cluttered scenes featuring a variety of objects, our goal is to learn both the names and appearances of the objects. Only a...
Michael Jamieson, Afsaneh Fazly, Sven J. Dickinson...
MIWeb realizes a mediator-based integration of heterogeneous metadata sources over the Web. Mediators are well known from database integration. They improve the quality of search ...
This paper presents a method for automatically annotating and retrieving animal images. Our model is a multi-modality ontology extended from our previous works in the sense that b...