We present a probabilistic framework for component-based automatic detection and tracking of objects in video. We represent objects as spatio-temporal two-layer graphical models, w...
Leonid Sigal, Ying Zhu, Dorin Comaniciu, Michael J...
Nowadays, one of the main research issues of great interest is the efficient tracking of mobile objects that enables the effective answering of spatiotemporal queries. This line o...
Katerina Raptopoulou, Michael Vassilakopoulos, Yan...
Abstract. To realize Weiser’s vision of ubiquitous computing, a popular approach has been to create so-called smart living objects, which are everyday objects in our living envir...
In this paper, we study the problem of the fast selection of video objects, as an aid for the efficient semi-automatic annotation of video programs. In a regular system, the user ...
A number of recent systems for unsupervised featurebased learning of object models take advantage of cooccurrence: broadly, they search for clusters of discriminative features tha...