Cerca risorse accademiche

The discriminative model learning for image denoising has been recently attracting considerable attentions due to its favorable denoising performance. In this paper, we take one step forward by investigating the construc...

In object detection, an intersection over union (IoU) threshold is required to define positives and negatives. An object detector, trained with low IoU threshold, e.g. 0.5, usually produces noisy detections. However, det...

Remarkable progress has been made in image recognition, primarily due to the availability of large-scale annotated datasets and deep convolutional neural networks (CNNs). CNNs enable learning data-driven, highly represen...

Point clouds provide a flexible geometric representation suitable for countless applications in computer graphics; they also comprise the raw output of most 3D data acquisition devices. While hand-designed features on po...

This paper proposes a Fast Region-based Convolutional Network method (Fast R-CNN) for object detection. Fast R-CNN builds on previous work to efficiently classify object proposals using deep convolutional networks. Compa...

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...

We present a conceptually simple, flexible, and general framework for object instance segmentation. Our approach efficiently detects objects in an image while simultaneously generating a high-quality segmentation mask fo...

In the last few years, the deep learning (DL) computing paradigm has been deemed the Gold Standard in the machine learning (ML) community. Moreover, it has gradually become the most widely used computational approach in ...

Materie / parole chiave: Computer science; FLOPS; Metric (unit); Architecture; Computation; Performance metric; Computer engineering; Distributed computing; Computer architecture; Parallel computing; Algorithm; Operations management

En este libro se introducen los conceptos fundamentales del aprendizaje profundo (Deep learning, DL) mediante el uso de redes neuronales artificiales (Artificial neural networks, ANN). El lector podrá encontrar una revi...

An end-to-end methodology based on deep learning for the detection and localization of microcalcifications in digital mammograms introduces a novel methodology designed for the preprocessing and localization of clusters ...

Israel es una democracia de corte occidental que descansa en una clara separación de poderes y un Parlamento del que procede el primer ministro; pero sus instituciones, el sistema electoral imperante y los partidos gene...

El presente libro tiene una clara vocación didáctica, se dirige a todas las personas que quieren adentrarse en el apasionante campo del aprendizaje automático combinando la teórica con la práctica para que sea senci...

Los avances continuos en la visión artificial permiten resolver problemas de distinta índole, como pueden ser la conducción autónoma, el reconocimiento biométrico, la detección de defectos industriales o la interac...

El vertiginoso crecimiento y la precisión de las técnicas de Inteligencia Artificial (AI, del inglés Artificial Intelligence) permiten analizar grandes volúmenes de datos de forma rápida y eficiente. En ese sentido,...

"We propose the use of convolutional neural networks (CNN) for counting and positioning people in visible and infrared images. Our data set is made of semi-artificial images created from real photographs taken from a dro...

We report on a series of experiments with convolutional neural networks (CNN) trained on top of pre-trained word vectors for sentence-level classification tasks. We show that a simple CNN with little hyperparameter tunin...

Predicting face attributes in the wild is challenging due to complex face variations. We propose a novel deep learning framework for attribute prediction in the wild. It cascades two CNNs, LNet and ANet, which are fine-t...

Convolutional neural networks (CNNs) are inherently limited to model geometric transformations due to the fixed geometric structures in their building modules. In this work, we introduce two new modules to enhance the tr...

Recently, channel attention mechanism has demonstrated to offer great potential in improving the performance of deep convolutional neural networks (CNNs). However, most existing methods dedicate to developing more sophis...

Feature pyramids are a basic component in recognition systems for detecting objects at different scales. But pyramid representations have been avoided in recent object detectors that are based on deep convolutional netwo...

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are...

The highest accuracy object detectors to date are based on a two-stage approach popularized by R-CNN, where a classifier is applied to a sparse set of candidate object locations. In contrast, one-stage detectors that are...