Abstract. Recurrent neural networks (RNNs) have proved effective at one dimensional sequence learning tasks, such as speech and online handwriting recognition. Some of the properti...
Scale-space representation of an image is a significant way to generate features for classification. However, for a specific classification task, the entire scale-space may not be...
Context-based adaptive entropy coding is an essential feature of modern image compression algorithms; however, the design of these coders is non-trivial due to the balance that mu...
Abstract. Graph cuts have become very popular in many areas of computer vision including segmentation, energy minimization, and 3D reconstruction. Their ability to find optimal res...
In this paper, we present 2-D direction-adaptive transforms for coding prediction residuals of video. These Direction-Adaptive Residual Transforms (DART) are shown to be more effe...
Robert A. Cohen, Sven Klomp, Anthony Vetro, Huifan...