This paper presents a unified framework for achieving robust and real-time image stabilization and rectification. While compensating for a small amount of image jitter due to plat...
General multi view reconstruction from affine or projective cameras has so far been solved most efficiently using methods of factorizing image data matrices into camera and scene p...
This paper presents a framework for view-invariant action recognition in image sequences. Feature-based human detection becomes extremely challenging when the agent is being observ...
Bhaskar Chakraborty, Marco Pedersoli, Jordi Gonz&a...
Local appearance models in the neighborhood of salient image features, together with local and/or global geometric constraints, serve as the basis for several recent and effective...
In the Pegasus prototype multidatabase system, the key to the problem of object identity is a differentiation between the view of a data administrator, capturing all the underlyin...
William Kent, Rafi Ahmed, Joseph Albert, Mohammad ...