Visual tracking plays an important role in many computer vision tasks. A common assumption in previous methods is that the video frames are blur free. In reality, motion blurs are...
Abstract. We consider geometric shortest path queries between arbitrary pairs of objects on a connected polyhedral surface P of genus g. The query objects are points, vertices, edg...
We describe a kernel method which uses the maximization of Onicescu’s informational energy as a criteria for computing the relevances of input features. This adaptive relevance d...
Automatic image categorization using low-level features is a challenging research topic in computer vision. In this paper, we formulate the image categorization problem as a multi...
Recent works in image editing are opening up new possibilities to manipulate and enhance input images. Within this context, we leverage well-known characteristics of human percept...