After more than a decade of e-government research, little work has been done to envision the longer term future of government and society and the unanswered questions associated w...
Abstract. We address the problem of visual event recognition in surveillance where noise and missing observations are serious problems. Common sense domain knowledge is exploited t...
We introduce an online adaptive algorithm for learning gesture models. By learning gesture models in an online fashion, the gesture recognition process is made more robust, and th...
We present an approach for tracking varying number of objects through both temporally and spatially significant occlusions. Our method builds on the idea of object permanence to r...
A new problem of retrieving social games from unstructured videos is proposed. Social games are characterized by repetitions (with variations) of alternating turns between two pla...