We transform the outputs of each hidden neuron in a multi-layer perceptron network to have zero output and zero slope on average, and use separate shortcut connections to model th...
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Single-ISA heterogeneous multi-core processors are typically composed of small (e.g., in-order) power-efficient cores and big (e.g., out-of-order) high-performance cores. The eff...
Kenzo Van Craeynest, Aamer Jaleel, Lieven Eeckhout...
—Direct replays of the experience of a user in a virtual environment are difficult for others to watch due to unnatural camera motions. We present methods for replaying and summ...
—The projection of a photographic dataset on a 3D model is a robust and widely applicable way to acquire appearance information of an object. The first step of this procedure is...
Matteo Dellepiane, Ricardo Marroquim, Marco Callie...