This paper proposes a system architecture for event recognition that integrates information from multiple sources (e.g., gesture and speech recognition from distributed sensors in...
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...
In this paper, we present a novel type and effect analysis for detecting type cast errors and memory errors in C source code. Our approach involves a type system with effect, regi...
Persons may perform an activity in many different styles, or noise may cause an identical activity to have different temporal structures. We present a robust methodology for recog...
We present Hector, a software tool for combining different abstraction methods to extract sound models of heap-manipulating imperative programs with recursion. Extracted models ma...