This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
The problem of identifying approximately duplicate objects in databases is an essential step for the information integration process. Most existing approaches have relied on gener...
This brief presents an efficient and scalable online learning algorithm for recurrent neural networks (RNNs). The approach is based on the real-time recurrent learning (RTRL) algor...
We describe a data mining system to detect frauds that are camouflaged to look like normal activities in domains with high number of known relationships. Examples include accounti...
—With the rapid development of the World Wide Web, people benefit more and more from the sharing of information. However, Web pages with obscene, harmful, or illegal content can ...
Weiming Hu, Ou Wu, Zhouyao Chen, Zhouyu Fu, Stephe...