This paper presents a novel approach for labeling objects based on multiple spatially-registered images of a scene. We argue that such a multi-view labeling approach is a better fi...
Scott Helmer, David Meger, Marius Muja, James J. L...
We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of mode...
—There has been a growing interest in exploiting contextual information in addition to local features to detect and localize multiple object categories in an image. A context mod...
For the specification of object-oriented systems, usually several models representing different views are developed. The necessary integration of views is often delayed until impl...
Annette Laue, Matthias Liedtke, Daniel Moldt, Ivan...
The design and development of complex products invariably involves many actors who have different points of view on the problem they are addressing, the product being developed, a...