This paper presents a framework for robustly recognizing physical team behaviors by exploiting spatio-temporal patterns. Agent team behaviors in athletic and military domains typi...
This paper presents a novel method for learning object manipulation such as rotating an object or placing one object on another. In this method, motions are learned using referenc...
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 this paper, we present a novel approach for incorporating structural information into the hidden Markov Modeling (HMM) framework for offline handwriting recognition. Traditiona...
Hidden Markov Models (HMMs) are the most commonly used acoustic model for speech recognition. In HMMs, the probability of successive observations is assumed independent given the ...