The automatic annotation of images presents a particularly complex problem for machine learning researchers. In this work we experiment with semantic models and multi-class learnin...
Real-time human tracking is very important in surveillance and robot applications. We note that the performance of any human tracking system depends on its accuracy and its ability...
Fayez Idris, Mazen Abu-Zaher, Rashad J. Rasras, Ib...
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...
Abstract—We present a distributed connectivity service that allows agents in a mobile ad-hoc network to move while preserving connectivity. This allows unmodified motion plannin...
A robotic chauffeur should reason about spatial information with a variety of scales, dimensions, and ontologies. Rich representations of both the quantitative and qualitative cha...
Patrick Beeson, Matt MacMahon, Joseph Modayil, Ani...