Abstract. In recent years the problem of object recognition has received considerable attention from both the machine learning and computer vision communities. The key challenge of...
Abstract. PatchMatch is a fast algorithm for computing dense approximate nearest neighbor correspondences between patches of two image regions [1]. This paper generalizes PatchMatc...
Labeling objects in images is an essential prerequisite for many visual learning and recognition applications that depend on training data, such as image retrieval, object detecti...
Abstract. We present a novel approach to statistically characterize histograms of model-relative image regions. A multiscale model is used as an aperture to define image regions a...
Robert E. Broadhurst, Joshua Stough, Stephen M. Pi...
Histograms of local appearance descriptors are a popular representation for visual recognition. They are highly discriminant with good resistance to local occlusions and to geomet...