This paper introduces a web image dataset created by NUS’s Lab for Media Search. The dataset includes: (1) 269,648 images and the associated tags from Flickr, with a total of 5,...
In this paper, we address the challenges of content transfer in opportunistic networks, and propose techniques to better facilitate data dissemination based on the characteristics ...
The World Wide Web is a vast source of information accessible to computers, but understandable only to humans. The goal of the research described here is to automatically create a...
Mark Craven, Dan DiPasquo, Dayne Freitag, Andrew M...
The PC Desktop is a very rich repository of personal information, efficiently capturing user's interests. In this paper we propose a new approach towards an automatic persona...
Paul-Alexandru Chirita, Claudiu S. Firan, Wolfgang...
We address the task of answering natural language questions by using the large number of Frequently Asked Questions (FAQ) pages available on the web. The task involves three steps...