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...
This paper introduces the RL-TOPs architecture for robot learning, a hybrid system combining teleo-reactive planning and reinforcement learning techniques. The aim of this system ...
Abstract. In many cases, human actions can be identified not only by the singular observation of the human body in motion, but also properties of the surrounding scene and the rel...
Recently there has been a surge of interest in making computer science education attractive to potential students, motivating to current students, and relevant to graduating stude...
Lakshman Myneni, Margaret Ross, T. Dean Hendrix, N...
Many time-series experiments seek to estimate some signal as a continuous function of time. In this paper, we address the sampling problem for such experiments: determining which ...
Rohit Singh, Nathan Palmer, David K. Gifford, Bonn...