Human action video sequences can be considered as nonlinear dynamic shape manifolds in the space of image frames. In this paper, we address learning and classifying human actions ...
We present a robust and efficient algorithm for the pairwise non-rigid registration of partially overlapping 3D surfaces. Our approach treats non-rigid registration as an optimiza...
Qi-Xing Huang, Bart Adams, Martin Wicke, Leonidas ...
In this paper we address the problem of how to learn a structural prototype that can be used to represent the variations present in a set of trees. The prototype serves as a patte...
We propose the use of a haptic touchscreen to convey graphical and mathematical concepts through aural and/or vibratory tactile feedback. We hypothesize that an important applicat...
Jenna L. Toennies, Jessica Burgner, Thomas J. With...
We consider visual category recognition in the framework of measuring similarities, or equivalently perceptual distances, to prototype examples of categories. This approach is qui...
Alexander C. Berg, Hao Zhang 0003, Jitendra Malik,...