Abstract. We present a new approach to modeling and processing multimedia data. This approach is based on graphical models that combine audio and video variables. We demonstrate it...
One of the main difficult problem in video analysis is to track moving objects during a video sequence, especially in presence of occlusions. Unfortunately, almost all the differ...
We present an approach to visual tracking based on dividing a
target into multiple regions, or fragments. The target is represented
by a Gaussian mixture model in a joint feature...
Given an image region of pixels, second order statistics can be used to construct a descriptor for object representation. One example is the covariance matrix descriptor, which sh...
Xiaopeng Hong, Hong Chang, Shiguang Shan, Xilin Ch...
This paper presents an enhanced hypothesis verification strategy for 3D object recognition. A new learning methodology is presented which integrates the traditional dichotomic obj...
James M. Ferryman, Anthony D. Worrall, Stephen J. ...