Buscar recursos académicos

We introduce YOLO9000, a state-of-the-art, real-time object detection system that can detect over 9000 object categories. First we propose various improvements to the YOLO detection method, both novel and drawn from prio...

Materias / palabras clave: Computer science; Deep learning; Artificial intelligence; Abstraction; Representation (politics); Layer (electronics); Object (grammar); Backpropagation; Convolutional neural network; Feature learning; Pattern recognitio...

Materias / palabras clave: Artificial intelligence; Computer science; Face detection; AdaBoost; Pattern recognition (psychology); Object-class detection; Classifier (UML); Computer vision; Detector; Face (sociological concept); Facial recognition ...

We study the question of feature sets for robust visual object recognition; adopting linear SVM based human detection as a test case. After reviewing existing edge and gradient based descriptors, we show experimentally t...

The explosion of image data on the Internet has the potential to foster more sophisticated and robust models and algorithms to index, retrieve, organize and interact with images and multimedia data. But exactly how such ...

Today, visual recognition systems are still rarely employed in robotics applications. Perhaps one of the main reasons for this is the lack of demanding benchmarks that mimic such scenarios. In this paper, we take advanta...

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 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...

The way that information propagates in neural networks is of great importance. In this paper, we propose Path Aggregation Network (PANet) aiming at boosting information flow in proposal-based instance segmentation framew...

Despite the breakthroughs in accuracy and speed of single image super-resolution using faster and deeper convolutional neural networks, one central problem remains largely unsolved: how do we recover the finer texture de...

Point cloud is an important type of geometric data structure. Due to its irregular format, most researchers transform such data to regular 3D voxel grids or collections of images. This, however, renders data unnecessaril...

We present the automated techniques we have developed for new software that optimally detects, deblends, measures and classifies sources from astronomical images: SExtractor (Source Extractor ). We show that a very relia...

BACKGROUND: Receiver operating characteristic (ROC) curves are useful tools to evaluate classifiers in biomedical and bioinformatics applications. However, conclusions are often reached through inconsistent use or insuff...

Clustering is the unsupervised classification of patterns (observations, data items, or feature vectors) into groups (clusters). The clustering problem has been addressed in many contexts and by researchers in many disci...

La envoltura bacteriana de Lactobacillus acidophilus ATCC 4356 tiene las características de una bacteria Gram positiva, pero además posee proteínas de superficie o Surface layers (S-layers), las cuales se asocian con ...

Segmentation is often a critical step in image analysis. Microscope image components show great variability of shapes, sizes, intensities and textures. An inaccurate segmentation conditions the ulterior quantification a...

Fil: Torres, Liliana Gabriela. Universidad Nacional del Nordeste; Argentina. En el marco de la Maestría de Ambiente y Desarrollo Sustentable de la Universidad Nacional de Quilmes realizada entre los años 2013 y 2016, p...

Fil: Carrapizo, Verónica Noemí. Instituto Nacional de Tecnología Agropecuaria. Coordinación Nacional de Transferencia y Extensión; Argentina. Históricamente, en el ámbito de los estudios agrarios, ha surgido una p...

Deep learning has revolutionized many machine learning tasks in recent years, ranging from image classification and video processing to speech recognition and natural language understanding. The data in these tasks are t...

Both convolutional and recurrent operations are building blocks that process one local neighborhood at a time. In this paper, we present non-local operations as a generic family of building blocks for capturing long-rang...

Materias / palabras clave: computer vision, object recognition, image understanding, feature extraction, artificial intelligence, pattern recognition; Medicine: Medicine (General): Computer applications to medicine. Medical informatics; Science: M...