Within the field of action recognition, features and descriptors are often engineered to be sparse and invariant to transformation. While sparsity makes the problem tractable, it ...
The web log data embed much of web users' browsing behavior. From the web logs, one can discover patterns that predict the users' future requests based on their current b...
Abstract. There is currently a large interest in relational probabilistic models. While the concept of context-specific independence (CSI) has been well-studied for models such as ...
A fundamental premise of tagging systems is that regular users can organize large collections for browsing and other tasks using uncontrolled vocabularies. Until now, that premise...
Paul Heymann, Andreas Paepcke, Hector Garcia-Molin...
Multilayer perceptrons are often trained using error backpropagation (BP). BP training can be done in either a batch or continuous manner. Claims have frequently been made that bat...