Robust, real-time tracking of objects from visual data requires probabilistic fusion of multiple visual cues. Previous approaches have either been ad hoc or relied on a Bayesian n...
Domain-specific features are important in representing problem structure throughout machine learning and decision-theoretic planning. In planning, once state features are provide...
Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogue...
It is difficult to maintain the exact location of mobile objects due to the limited resources in a mobile network. A consequence of this problem is that the update cost for a locat...
Coarse-to-fine approaches use sequences of increasingly fine approximations to control the complexity of inference and learning. These techniques are often used in NLP and visio...