We present a new method for training deformable models. Assume that we have training images where part locations have been labeled. Typically, one fits a model by maximizing the l...
We present motion planning for dexterous manipulation by whole arm grasp system based on switching contact modes. Motion planning for such a system should consider changing dynami...
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...
Automated facial expression recognition has received increased attention over the past two decades. Existing works in the field usually do not encode either the temporal evolutio...
We present a dynamic near-regular texture (NRT) tracking algorithm nested in a lattice-based Markov-Random-Field (MRF) model of a 3D spatiotemporal space. One basic observation use...