We address the problem of learning object class models and object segmentations from unannotated images. We introduce LOCUS (Learning Object Classes with Unsupervised Segmentation...
Reconstruction of 3D structures from uncalibrated image sequences has a wealthy history. Most work has been focused on rigid objects or static scenes. This paper studies the probl...
Abstract. The Full Search Block-Matching Motion Estimation (FSBME) algorithm is often employed in video coding for its regular dataflow and straightforward architectures. By iterat...
Vincent M. Dwyer, Shahrukh Agha, Vassilios A. Chou...
In this paper, we introduce a novel framework for clustering web data which is often heterogeneous in nature. As most existing methods often integrate heterogeneous data into a un...
Abstract— A distributed online learning framework for support vector machines (SVMs) is presented and analyzed. First, the generic binary classification problem is decomposed in...