TY - CONF T1 - Learning dynamics for exemplar-based gesture recognition T2 - Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on Y1 - 2003 A1 - Elgammal,A. A1 - Shet,V. A1 - Yacoob,Yaser A1 - Davis, Larry S. KW - arbitrary KW - body KW - by KW - Computer KW - constraint; KW - detection; KW - discrete KW - distribution KW - dynamics; KW - edge KW - estimation; KW - example; KW - exemplar KW - exemplar-based KW - extraction; KW - feature KW - framework; KW - gesture KW - gesture; KW - hidden KW - HMM; KW - human KW - image KW - learning KW - Markov KW - matching; KW - model; KW - models; KW - motion; KW - nonparametric KW - pose KW - probabilistic KW - recognition; KW - sequence; KW - space; KW - state; KW - statistics; KW - system KW - temporal KW - tool; KW - view-based KW - vision; AB - This paper addresses the problem of capturing the dynamics for exemplar-based recognition systems. Traditional HMM provides a probabilistic tool to capture system dynamics and in exemplar paradigm, HMM states are typically coupled with the exemplars. Alternatively, we propose a non-parametric HMM approach that uses a discrete HMM with arbitrary states (decoupled from exemplars) to capture the dynamics over a large exemplar space where a nonparametric estimation approach is used to model the exemplar distribution. This reduces the need for lengthy and non-optimal training of the HMM observation model. We used the proposed approach for view-based recognition of gestures. The approach is based on representing each gesture as a sequence of learned body poses (exemplars). The gestures are recognized through a probabilistic framework for matching these body poses and for imposing temporal constraints between different poses using the proposed non-parametric HMM. JA - Computer Vision and Pattern Recognition, 2003. Proceedings. 2003 IEEE Computer Society Conference on VL - 1 M3 - 10.1109/CVPR.2003.1211405 ER -