Abstract. There is considerable interest in techniques capable of identifying anomalies and unusual events in busy outdoor scenes, e.g. road junctions. Many approaches achieve this...
In this paper, a generic bi-directional framework is proposed for parametric image alignment, that extends the classification of [1]. Four main categories (Forward, Inverse, Depend...
Abstract. In the sequential approach to three-dimensional reconstruction, adding prior knowledge about camera pose improves reconstruction accuracy. We add a smoothing penalty on t...
We propose a new algorithm for two-phase, piecewise-smooth segmentation with shape prior. The image is segmented by a binary template that is deformed by a regular geometric transf...
Benoit Mory, Laurent D. Cohen, Oudom Somphone, Sh&...
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...
Distance metric learning has been widely investigated in machine learning and information retrieval. In this paper, we study a particular content-based image retrieval application ...