In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
Relational clustering has attracted more and more attention due to its phenomenal impact in various important applications which involve multi-type interrelated data objects, such...
Video query by semantic keywords is one of the most challenging research issues in video data management. To go beyond low-level similarity and access video data content by semanti...
Milind R. Naphade, Igor Kozintsev, Thomas S. Huang
A framework for the logical and statistical analysis and annotation of dynamic scenes containing occlusion and other uncertainties is presented. This framework consists of three e...
Brandon Bennett, Derek R. Magee, Anthony G. Cohn, ...
We derive a probabilistic framework for robust, realtime, visual tracking of multiple previously unseen objects from a moving camera. This framework models the discrete depth orde...