Background
Deep learning has enabled reliable image classification and object detection. In our reseach, we focus on the transferability of deep learning techniques to the art domain. However, deep learning technologies are based on deep neural networks consisting of millions of parameters that nee...
Conference "Information - digitally packaged"
Library work means to provide information services against the background of new technical possibilities and increasing information abundance. Digitization is creating new tasks and fields of activity in scientific libraries. The Zurich Central Library ...
For archaeologists, it is often desirable to present statues in their original material and coloration. With projection mapping, real-world surfaces are augmented by digital content to create compelling alterations of the scene’s visual appearance without actually altering or even damaging the objec...
This work exploits style transfer in combination with transfer learning to recognize characters in art historical images. Our approach focuses on recognizing two central characters in the “Annunciation of the Lord” scene from Art history, Mary and Gabriel across varied art-works from different artists, times and styles.
