We present a novel method for inferring three-dimensional shape from a collection of defocused images. It is based on the observation that defocused images are the null-space of ce...
We consider the problem of multiple kernel learning (MKL), which can be formulated as a convex-concave problem. In the past, two efficient methods, i.e., Semi-Infinite Linear Prog...
Abstract. Object viewpoint classification aims at predicting an approximate 3D pose of objects in a scene and is receiving increasing attention. State-of-the-art approaches to view...
The ability of fast similarity search at large scale is of great importance to many Information Retrieval (IR) applications. A promising way to accelerate similarity search is sem...
In this paper, we propose a learning-based demosaicing and a restoration error detection. A Vector Quantization (VQ)based method is utilized for learning. We take advantage of a s...