Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
The distortion caused by an interactive fisheye lens can make it difficult for people to remember items and locations in the data space. In this paper we introduce the idea of vis...
We propose to model relative attributes1 that capture the relationships between images and objects in terms of human-nameable visual properties. For example, the models can captur...
Finding the location where a picture was taken is an important problem for a variety of applications including surveying, interactive traveling and homeland security among others....
—In this paper, we present a novel approach to search and retrieve from document image collections, without explicit recognition. Existing recognition-free approaches such as wor...