The recognition of text in everyday scenes is made difficult by viewing conditions, unusual fonts, and lack of linguistic context. Most methods integrate a priori appearance info...
David Smith, Jacqueline Feild, Eric Learned-Miller
During this talk, I will introduce a novel family of contextual measures of similarity between distributions: the similarity between two distributions q and p is measured in the co...
Florent Perronnin (Xerox Research Centre Europe), ...
We have created the first image search engine based entirely on faces. Using simple text queries such as "smiling men with blond hair and mustaches," users can search thr...
Nearest neighbor queries are important in many settings, including spatial databases (Find the k closest cities) and multimedia databases (Find the k most similar images). Previou...
Many scalable data mining tasks rely on active learning to provide the most useful accurately labeled instances. However, what if there are multiple labeling sources (`oracles...