We present a novel feature screening algorithm by deriving relevance measures from the decision boundary of Support Vector Machines. It alleviates the "independence" assu...
Detecting instances of unknown categories is an important task for a multitude of problems such as object recognition, event detection, and defect localization. This paper investig...
In this paper we present a novel shape descriptor based on shape context, which in combination with hierarchical distance based hashing is used for word and graphical pattern base...
We propose a closely coupled object detection and segmentation algorithm for enhancing both processes in a cooperative and iterative manner. Figure-ground segmentation reduces the...
We propose a novel probabilistic framework for learning
visual models of 3D object categories by combining appearance
information and geometric constraints. Objects are
represen...