We describe a probabilistic framework for recognizing human activities in monocular video based on simple silhouette observations in this paper. The methodology combines kernel pr...
In this paper, we present a new solution to the problem of matching tracking sequences across different cameras. Unlike snapshot-based appearance matching which matches objects by...
We present a scalable approach to recognizing and describing complex activities in video sequences. We are interested in long-term, sequential activities that may have several par...
We propose a new neural network architecture, called Simple Recurrent Temporal-Difference Networks (SR-TDNs), that learns to predict future observations in partially observable en...
Intelligent agents embedded in physical environments need ity to connect, or anchor, the symbols used to perform abstract reasoning to the physical entities which these symbols ref...