In recent years, gradient-based LSTM recurrent neural networks (RNNs) solved many previously RNN-unlearnable tasks. Sometimes, however, gradient information is of little use for t...
In this paper, a novel automatic image annotation system is proposed, which integrates two sets of support vector machines (SVMs), namely the multiple instance learning (MIL)-base...
In this work we discuss author identification for documents written in Portuguese. Two different approaches were compared. The first is the writer-independent model which reduces ...
Daniel Pavelec, Edson J. R. Justino, Leonardo Vida...
—The use of vital signs as a biometric is a potentially viable approach in a variety of application scenarios such as security and personalized health care. In this paper, a nove...
— Detecting the boundaries of objects is a key step in separating foreground objects from the background, which is useful for robotics and computer vision applications, such as o...
Kiho Kwak, Daniel F. Huber, Jeongsook Chae, Takeo ...