This paper presents a novel framework for matching video sequences using the spatiotemporal segmentation of videos. Instead of using appearance features for region correspondence ...
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are ...
In this paper we present a novel method for creating realistic, controllable motion. Given a corpus of motion capture data, we automatically construct a directed graph called a mo...
The causal estimation of three-dimensional motion from a sequence of two-dimensional images can be posed as a nonlinear filtering problem. We describe the implementation of an algo...
Alessandro Chiuso, Paolo Favaro, Hailin Jin, Stefa...
Privacy issues have hindered centralised authentication approaches from being adopted by a wide range of users. This also applies to authorizations which suffer from privacy probl...