Non-negative matrix factorization (NMF) is an excellent tool for unsupervised parts-based learning, but proves to be ineffective when parts of a whole follow a specific pattern. ...
Computer vision requires the solution of many ill-posed problems such as optical flow, structure from motion, shape from shading, surface reconstruction, image restoration and ed...
Changjiang Yang, Ramani Duraiswami, Larry S. Davis
We present a novel approach for summarizing video in the form of a multiscale image that is continuous in both the spatial domain and across the scale dimension: There are no hard...
Connelly Barnes, Dan B. Goldman, Eli Shechtman, Ad...
Abstract. In this article we propose a cardiac motion estimation technique that uses non-rigid registration to compute the dense cardiac displacement field from 2D ultrasound sequ...
We show that the set of all ow- elds in a sequence of frames imaging a rigid scene resides in a lowdimensional linear subspace. Based on this observation, we develop a method for ...