Flexible general purpose robots need to tailor their visual processing to their task, on the fly. We propose a new approach to this within a planning framework, where the goal is ...
Accurately and automatically conveying the structure of a volume model is a problem not fully solved by existing volume rendering approaches. Physics-based volume rendering approa...
This paper uncovers a new phenomenon in web search that we call domain bias — a user’s propensity to believe that a page is more relevant just because it comes from a particul...
Samuel Ieong, Nina Mishra, Eldar Sadikov, Li Zhang
We propose a semi-supervised model which segments and annotates images using very few labeled images and a large unaligned text corpus to relate image regions to text labels. Give...
This video describes a new type of 3D curves, which generalizes the family of 2D Euler spirals. They are defined as the curves having both their curvature and their torsion evolv...