We propose using multi-layer multiple instance learning (MMIL) for image set classification and applying it to the task of cannabis website classification. We treat each image as a...
We present an ensemble learning approach that achieves accurate predictions from arbitrarily partitioned data. The partitions come from the distributed processing requirements of ...
Larry Shoemaker, Robert E. Banfield, Lawrence O. H...
—We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object’s appearance due to changing camera pose and li...
While low-dimensional image representations have been very popular in computer vision, they suffer from two limitations: (i) they require collecting a large and varied training se...
In this paper we describe a novel technique which implements a spatiotemporal model as a set of sub-models based on first order logic. These sub-models model different, typicall...