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...
Most of the online multimedia collections, such as picture galleries or video archives, are categorized in a fully manual process, which is very expensive and may soon be infeasib...
This paper presents a multi-scale generative model for representing animate shapes and extracting meaningful parts of objects. The model assumes that animate shapes (2D simple clo...
Assumptions of brightness constancy and spatial smoothness underlie most optical flow estimation methods. In contrast to standard heuristic formulations, we learn a statistical mod...
Deqing Sun, Stefan Roth, J. P. Lewis, Michael J. B...
In this paper, we propose a method for human tracking using 3D human body model in a video sequence with a monocular moving camera. Tracking a human with unconstrained movement in...