In our research, we have developed a transfer-based machine translation architecture for the translation from Japanese into German. One main feature of the system is the fully auto...
Standard inductive learning requires that training and test instances come from the same distribution. Transfer learning seeks to remove this restriction. In shallow transfer, tes...
Related objects may look similar at low-resolutions; differences begin to emerge naturally as the resolution is increased. By learning across multiple resolutions of input, knowle...
We study the problem of object classification when training
and test classes are disjoint, i.e. no training examples of
the target classes are available. This setup has hardly be...
Christoph H. Lampert, Hannes Nickisch, Stefan Harm...
Facilitating the transfer of knowledge between knowledge workers represents one of the main challenges of knowledge management. Knowledge transfer instruments, such as the experie...
Markus Strohmaier, Eric S. K. Yu, Jennifer Horkoff...