Issue No. 09 - September (2006 vol. 28)
Michal Irani , IEEE
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extents.
Action recognition, video indexing, temporal segmentation.
M. Irani and L. Zelnik-Manor, "Statistical Analysis of Dynamic Actions," in IEEE Transactions on Pattern Analysis & Machine Intelligence, vol. 28, no. , pp. 1530-1535, 2006.