Buscar recursos académicos

El objetivo del trabajo es realizar un diagnóstico socio-territorial de dos asentamientos espontáneos de la ciudad de Puerto Madryn (Chubut, Argentina): La Lomita y Alta Tensión, a partir de la aplicación del Método...

Convolutional networks are powerful visual models that yield hierarchies of features. We show that convolutional networks by themselves, trained end-to-end, pixels-to-pixels, improve on the previous best result in semant...

State-of-the-art object detection networks depend on region proposal algorithms to hypothesize object locations. Advances like SPPnet [1] and Fast R-CNN [2] have reduced the running time of these detection networks, expo...

In this work, we revisit the global average pooling layer proposed in [13], and shed light on how it explicitly enables the convolutional neural network (CNN) to have remarkable localization ability despite being trained...