Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
Leonid Taycher, John W. Fisher III, Trevor Darrell
Dynamic Probabilistic Networks (DPNs) are exploited for modelling the temporal relationships among a set of different object temporal events in the scene for a coherent and robust...
Abstract. This paper presents a novel probabilistic approach to integrating multiple cues in visual tracking. We perform tracking in different cues by interacting processes. Each p...
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Image categorization involves the well known difficulties with different visual appearances of a single object, but introduces also the problem of within-category variation. This ...