We propose a new semantics for modeling belief, mixing conncepts from qualitative probabilistic and classical possible world accounts. Our belief structures are coherent sets of q...
This paper suggests using discrete feature displacements and optical flow simultaneously to determine the camera motion and its velocity. This is advantageous when the number of ...
We introduce `Joint Feature Distributions', a general statistical framework for feature based multi-image matching that explicitly models the joint probability distributions ...
In this paper we propose a new probabilistic relaxation framework to perform robust multiple motion estimation and segmentation from a sequence of images. Our approach uses displa...
Which one comes first: segmentation or recognition? We propose a unified framework for carrying out the two simultaneously and without supervision. The framework combines a fle...