We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our approach...
Abstract. Figure/ground assignment is a key step in perceptual organization which assigns contours to one of the two abutting regions, providing information about occlusion and all...
We consider object recognition as the process of attaching meaningful labels to specific regions of an image, and propose a model that learns spatial relationships between objects....
Transduction is an inference mechanism “from particular to particular”. Its application to classification tasks implies the use of both labeled (training) data and unlabeled (...
We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...