We propose a statistical formulation for 2-D human pose estimation from single images. The human body configuration is modeled by a Markov network and the estimation problem is to...
We present a tunable representation for tracking that simultaneously encodes appearance and geometry in a manner that enables the use of mean-shift iterations for tracking. The cl...
In its full generality, motion analysis of crowded objects necessitates recognition and segmentation of each moving entity. The difficulty of these tasks increases considerably wi...
Recent research in visual inference from monocular images has shown that discriminatively trained image-based predictors can provide fast, automatic qualitative 3D reconstructions...
Atul Kanaujia, Cristian Sminchisescu, Dimitris N. ...
We propose a family of kernels between images, defined as kernels between their respective segmentation graphs. The kernels are based on soft matching of subtree-patterns of the r...