— We present ELVIS, a new approach for localizing a first responder (e.g., firefighter) inside a building. We assume that the first responder emits RF energy, which undergoes...
Recent work shows how to use local spatio-temporal features to learn models of realistic human actions from video. However, existing methods typically rely on a predefined spatial...
Symbolic model checking is a successful technique for checking properties of large finite-state systems. This method has been used to verify a number of real-world hardware desig...
We investigate a form of modular neural network for classification with (a) pre-separated input vectors entering its specialist (expert) networks, (b) specialist networks which ar...
This paper explores the use of alternating sequential patterns of local features and saccading actions to learn robust and compact object representations. The temporal encoding rep...