Buscar recursos académicos

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...

Materias / palabras clave: Computer science; Suite; Neuroimaging; Software; Variety (cybernetics); Open source; Software suite; Human brain; Artificial intelligence; Software package; Pattern recognition (psychology); Neuroscience

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...

Materias / palabras clave: Classifier (UML); Gene; Computer science; Feature selection; Redundancy (engineering); Gene selection; Support vector machine; Computational biology; sort; Artificial intelligence; Pattern recognition (psychology); Data ...

We propose a deep convolutional neural network architecture codenamed Inception that achieves the new state of the art for classification and detection in the ImageNet Large-Scale Visual Recognition Challenge 2014 (ILSVR...

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...

We trained a large, deep convolutional neural network to classify the 1.2 million high-resolution images in the ImageNet LSVRC-2010 contest into the 1000 different classes. On the test data, we achieved top-1 and top-5 e...

Materias / palabras clave: Independent component analysis; Principal component analysis; Representation (politics); Computer science; Algorithm; Gaussian; Artificial intelligence; Projection (relational algebra); Pattern recognition (psychology); ...

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...

We propose a simple, yet effective approach for spatiotemporal feature learning using deep 3-dimensional convolutional networks (3D ConvNets) trained on a large scale supervised video dataset. Our findings are three-fold...

Materias / palabras clave: Non-negative matrix factorization; Matrix decomposition; Computer science; Sign (mathematics); Artificial intelligence; Perception; Factorization; Matrix (chemical analysis); Representation (politics); Pattern recognitio...

We present Momentum Contrast (MoCo) for unsupervised visual representation learning. From a perspective on contrastive learning as dictionary look-up, we build a dynamic dictionary with a queue and a moving-averaged enco...

We propose a novel approach for solving the perceptual grouping problem in vision. Rather than focusing on local features and their consistencies in the image data, our approach aims at extracting the global impression o...

We describe an object detection system based on mixtures of multiscale deformable part models. Our system is able to represent highly variable object classes and achieves state-of-the-art results in the PASCAL object det...

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...

Materias / palabras clave: Computer science; Artificial intelligence; Convolutional neural network; Image (mathematics); Pixel; Perception; Transformation (genetics); Ground truth; Transfer (computing); Computer vision; Pattern recognition (psycho...

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...

Introduction * Properties of Population Principal Components * Properties of Sample Principal Components * Interpreting Principal Components: Examples * Graphical Representation of Data Using Principal Components * Choos...

High-dimensional data can be converted to low-dimensional codes by training a multilayer neural network with a small central layer to reconstruct high-dimensional input vectors. Gradient descent can be used for fine-tuni...

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 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...

Computer vision applications have come to rely increasingly on superpixels in recent years, but it is not always clear what constitutes a good superpixel algorithm. In an effort to understand the benefits and drawbacks o...

Materias / palabras clave: Computer science; Robustness (evolution); Artificial intelligence; Hessian matrix; Detector; Computer vision; Invariant (physics); Pattern recognition (psychology); Mathematics; Gene; Telecommunications; Biochemistry