Learning from imbalanced data occurs frequently in many machine learning applications. One positive example to thousands of negative instances is common in scientific applications...
Ink-bleed interference is a serious problem that affects the legibility of old documents. Ink-bleed can be reduced reasonably well using pixel classification based on user supplie...
Abstract. With the increasing capability of MR imaging and Computational Fluid Dynamics (CFD) techniques, a significant amount of data related to the haemodynamics of the cardiovas...
Bernardo Silva Carmo, Yin-Heung Pauline Ng, Adam P...
During the last years, a wide range of huge networks has been made available to researchers. The discovery of natural groups, a task called graph clustering, in such datasets is a ...
Automatic facial feature localization has been a longstanding challenge in the field of computer vision for several decades. This can be explained by the large variation a face i...
Minh Hoai Nguyen, Joan Perez, Fernando De la Torre