We propose a spatially continuous formulation of Ishikawa's discrete multi-label problem. We show that the resulting non-convex variational problem can be reformulated as a co...
Thomas Pock, Thomas Schoenemann, Gottfried Graber,...
The application of semi-supervised learning algorithms to large scale vision problems suffers from the bad scaling behavior of most methods. Based on the Expectation Regularization...
While image registration has been studied in different areas of computer vision, aligning images depicting different scenes remains a challenging problem, closer to recognition tha...
Ce Liu, Jenny Yuen, Antonio B. Torralba, Josef Siv...
Automatically assigning keywords to images is of great interest as it allows one to index, retrieve, and understand large collections of image data. Many techniques have been propo...