Abstract. In this paper we introduce a new representation for shapebased object class detection. This representation is based on very sparse and slightly flexible configurations of...
In this paper, we propose a Boosted Interactively Distributed Particle Filter (BIDPF) to address the problem of automatic multi-object tracking in the application of player tracki...
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...
In this paper, we present a novel methodology to detect and recognize objects in cluttered scenes by proposing boosted contextual descriptors of landmarks in a framework of multi-...