Current object class recognition systems typically target 2D bounding box localization, encouraged by benchmark data sets, such as Pascal VOC. While this seems suitable for the de...
Bojan Pepik, Michael Stark, Peter V. Gehler, Bernt...
Abstract. This paper presents the integration of 3D shape knowledge into a variational model for level set based image segmentation and tracking. Having a 3D surface model of an ob...
In this paper, it is suggested an approach and a design pattern for developing object-oriented models that need to be persistent, including the databases of moderate size, with us...
We propose a method of acquiring attribute words for a wide range of objects from Japanese Web documents. The method is a simple unsupervised method that utilizes the statistics of...
In this paper, we discuss the use of fragmented bandwidth to improve the performance of staggered striping in a multimedia system. It is observed that potential disruptions can occ...