Probabilistic relational models are an efficient way to learn and represent the dynamics in realistic environments consisting of many objects. Autonomous intelligent agents that gr...
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
In this paper, we propose an approach to learning appearance models of moving objects directly from compressed video. The appearance of a moving object changes dynamically in vide...
Social tagging provides valuable and crucial information for large-scale web image retrieval. It is ontology-free and easy to obtain; however, irrelevant tags frequently appear, a...
This paper presents a simple and efficient method of modeling synthetic vision, memory, and learning for autonomous animated characters in real-time virtual environments. The mode...