We introduce a technique for measuring local scale, based on a special property of the so-called total variational (TV) flow. For TV flow, pixels change their value with a speed th...
Large intersubject variability is a well-described feature of fMRI studies, making inter-group inference, of critical importance for biological interpretation, difficult. Therefor...
Martin J. McKeown, Junning Li, Xuemei Huang, Z. Ja...
This paper proposes contour-based features for articulated pose estimation. Most of recent methods are designed using tree-structured models with appearance evaluation only within...
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
Invariant feature descriptors such as SIFT and GLOH have been demonstrated to be very robust for image matching and visual recognition. However, such descriptors are generally par...