We present a fast and robust graph matching approach for 2D specific object recognition in images. From a small number of training images, a model graph of the object to learn is a...
Most methods for object class segmentation are formulated as a labelling problem over a single choice of quantisation of an image space - pixels, segments or group of segments. It...
Lubor Ladicky, Christopher Russell, Pushmeet Kohli...
Viola and Jones (VJ) cascade classification methods have proven to be very successful in detecting objects belonging to a single class -- e.g., faces. This paper addresses the mor...
Ahmed M. Elgammal, Ramana Isukapalli, Russell Grei...
We present a novel semi-supervised training algorithm for learning dependency parsers. By combining a supervised large margin loss with an unsupervised least squares loss, a discr...
Tracking multiple interacting objects represents a challenging area in computer vision. The tracking problem in general can be formulated as the task of recovering the spatio-temp...