Tracking multiple objects is important in many application domains. We propose a novel algorithm for multi-object tracking that is capable of working under very challenging conditi...
When estimating foreground and background layers (or equivalently an alpha matte), it is often the case that pixel measurements contain mixed colours which are a combination of for...
Yonatan Wexler, Andrew W. Fitzgibbon, Andrew Zisse...
We propose a method that we call auto-adaptive convolution which extends the classical notion of convolution in pictures analysis to function analysis on a discrete set. We define...
This paper proposes an appearance generative mixture model based on key frames for meanshift tracking. Meanshift tracking algorithm tracks object by maximizing the similarity betwe...
We propose a novel affine-invariant modeling of hand shapeappearance images, which offers a compact and descriptive representation of the hand configurations. Our approach combine...