In this paper we propose an approach for action recognition based on a vocabulary of local motion-appearance features and fast approximate search in a large number of trees. Large...
A novel method for the simultaneous modeling and tracking (SMAT) of a feature set during motion sequence is proposed. The method requires no prior information. Instead the a poste...
Active Appearance Models (AAMs) typically only use 50-100 mesh vertices because they are usually constructed from a set of training images with the vertices hand-labeled on them. ...
Krishnan Ramnath, Simon Baker, Iain Matthews, Deva...
In this paper we consider the images taken from pairs of parabolic catadioptric cameras separated by discrete motions. Despite the nonlinearity of the projection model, the epipol...
We present a robust framework for estimating non-rigid 3D shape and motion in video sequences. Given an input video sequence, and a user-specified region to reconstruct, the algori...