This paper discusses the problem of knowledge discovery in image databases with particular focus on the issues which arise when absolute ground truth is not available. It is often...
Padhraic Smyth, Michael C. Burl, Usama M. Fayyad, ...
We propose a new discriminative framework, namely Hidden Dynamic Conditional Random Fields (HDCRFs), for building probabilistic models which can capture both internal and external...
Background knowledge is an important factor in privacy preserving data publishing. Probabilistic distributionbased background knowledge is a powerful kind of background knowledge w...
Raymond Chi-Wing Wong, Ada Wai-Chee Fu, Ke Wang, Y...
The emergence of Web 2.0 has resulted in a huge amount of heterogeneous data that are contributed by a large number of users, engendering new challenges for data management and qu...
In this paper, we present the ArchIS system that achieves full-functionality transaction-time databases without requiring temporal extensions in XML or database standards. ArchIS&...