Buscar recursos académicos

We propose a deep learning method for single image super-resolution (SR). Our method directly learns an end-to-end mapping between the low/high-resolution images. The mapping is represented as a deep convolutional neural...

Fil: Maidana, Liliana Beatriz. Universidad Nacional de Quilmes; Argentina. En este trabajo de investigación analizo el proceso de construcción de algunos rasgos distintivos de la docencia partiendo de la teoría de los...

Existing deep convolutional neural networks (CNNs) require a fixed-size (e.g., 224 × 224) input image. This requirement is "artificial" and may reduce the recognition accuracy for the images or sub-images of an arbitrar...