Recognition of chatting activities in social interactions is useful for constructing human social networks. However, the existence of multiple people involved in multiple dialogue...
In artificial intelligence and pervasive computing research, inferring users' high-level goals from activity sequences is an important task. A major challenge in goal recogni...
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...
In this paper, we introduce a first-order probabilistic model that combines multiple cues to classify human activities from video data accurately and robustly. Our system works in...
This paper presents a new criterion for viewpoint selection in the context of active Bayesian object recognition and pose estimation. Recognition is performed by probabilistically...