Most existing sketch understanding systems require a closed domain to achieve recognition. This paper describes an incremental learning technique for opendomain recognition. Our s...
Andrew M. Lovett, Morteza Dehghani, Kenneth D. For...
In many structured prediction problems, the highest-scoring labeling is hard to compute exactly, leading to the use of approximate inference methods. However, when inference is us...
The constructs of "common ground" and "grounding" are frequently invoked in the CSCW literature as a mechanism by which participants engaged in joint activity c...
In this paper, we examine emerging frontiers in the evolution of content-based retrieval systems that rely on an intelligent infrastructure. Here, we refer to intelligence as the ...
Dimensionality reduction is a commonly used step in many algorithms for visualization, classification, clustering and modeling. Most dimensionality reduction algorithms find a low...