We present a novel framework for characterizing signals in images using techniques from computational algebraic topology. This technique is general enough for dealing with noisy mu...
The task of 2-D articulated human pose estimation in natural images is extremely challenging due to the high level of variation in human appearance. These variations arise from di...
Motivated by improving statistical shape analysis, this paper presents a novel landmark-based method for accurate shape correspondence, where the general goal is to align multiple...
Abstract. Automatic delineation of anatomical structures in 3-D volumetric data is a challenging task due to the complexity of the object appearance as well as the quantity of info...
Wei Hong, Bogdan Georgescu, Xiang Sean Zhou, Srira...
We propose a novel nonlinear, probabilistic and variational method for adding shape information to level setbased segmentation and tracking. Unlike previous work, we represent sha...