In the context of large databases, data preparation takes a greater importance : instances and explanatory attributes have to be carefully selected. In supervised learning, instanc...
Current approaches to object category recognition require datasets of training images to be manually prepared, with varying degrees of supervision. We present an approach that can...
Robert Fergus, Fei-Fei Li 0002, Pietro Perona, And...
Interacting with mobile applications and services remains difficult for users because of the impact of mobility on both device capabilities and the cognitive resources of users. I...
Michael Harding, Oliver Storz, Nigel Davies, Adria...
Decoding noisy document images is commonly needed in applications such as enterprise content management. Available OCR solutions are still not satisfactory especially on noisy ima...
In this paper, we propose a robust isotropic tetrahedral mesh generation method. An advancing front method is employed to control local mesh density and to easily preserve the ori...