Results 261 to 270 of about 3,038,089 (290)
Some of the next articles are maybe not open access.
Adaptive RD Optimal Sparse Coding With Quantization for Image Compression
IEEE transactions on multimedia, 2019In image and video compression for many multimedia applications, an image/frame is divided into component blocks or patches and is then encoded using some type of transform. Traditional transforms use a complete dictionary of basis functions.
M. Kalluri +4 more
semanticscholar +1 more source
2014 IEEE Conference on Computer Vision and Pattern Recognition, 2014
Sparse coding is a widely involved technique in computer vision. However, the expensive computational cost can hamper its applications, typically when the codebook size must be limited due to concerns on running time. In this paper, we study a special case of sparse coding in which the codebook is a Cartesian product of two subcodebooks.
Tiezheng Ge, Kaiming He, Jian Sun
openaire +1 more source
Sparse coding is a widely involved technique in computer vision. However, the expensive computational cost can hamper its applications, typically when the codebook size must be limited due to concerns on running time. In this paper, we study a special case of sparse coding in which the codebook is a Cartesian product of two subcodebooks.
Tiezheng Ge, Kaiming He, Jian Sun
openaire +1 more source
Kernel Regularized Nonlinear Dictionary Learning for Sparse Coding
IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2019For most sparse coding methods, data samples are first encoded as hand-crafted features, followed by another separate learning step that generates dictionary and sparse codes. However, such feature representations may not be optimally compatible with the
Huaping Liu, He Liu, F. Sun, Bin Fang
semanticscholar +1 more source
2008
Prior work has shown that features which appear to be biologically plausible as well as empirically useful can be found by sparse coding with a prior such as a laplacian (L1 ) that promotes sparsity. We show how smoother priors can preserve the benefits of these sparse priors while adding stability to the Maximum A-Posteriori (MAP) estimate that makes ...
Bradley, David M., J. Andrew Bagnell
openaire +1 more source
Prior work has shown that features which appear to be biologically plausible as well as empirically useful can be found by sparse coding with a prior such as a laplacian (L1 ) that promotes sparsity. We show how smoother priors can preserve the benefits of these sparse priors while adding stability to the Maximum A-Posteriori (MAP) estimate that makes ...
Bradley, David M., J. Andrew Bagnell
openaire +1 more source
2012
We study a novel sparse coding model with discrete and symmetric prior distribution. Instead of using continuous latent variables distributed according to heavy tail distributions, the latent variables of our approach are discrete. In contrast to approaches using binary latents, we use latents with three states (-1, 0, and 1) following a symmetric and ...
Georgios Exarchakis +3 more
openaire +1 more source
We study a novel sparse coding model with discrete and symmetric prior distribution. Instead of using continuous latent variables distributed according to heavy tail distributions, the latent variables of our approach are discrete. In contrast to approaches using binary latents, we use latents with three states (-1, 0, and 1) following a symmetric and ...
Georgios Exarchakis +3 more
openaire +1 more source
SC2Net: Sparse LSTMs for Sparse Coding
Proceedings of the AAAI Conference on Artificial Intelligence, 2018The iterative hard-thresholding algorithm (ISTA) is one of the most popular optimization solvers to achieve sparse codes. However, ISTA suffers from following problems: 1) ISTA employs non-adaptive updating strategy to learn the parameters on each dimension with a fixed learning rate. Such a strategy may lead to inferior performance due
Joey Tianyi Zhou +9 more
openaire +1 more source
Light Field Super-Resolution via LFBM5D Sparse Coding
International Conference on Information Photonics, 2018In this paper, we propose a spatial super-resolution method for light fields, which combines the SR-BM3D single image super-resolution filter and the recently introduced LFBM5D light field denoising filter.
Martin Alain, A. Smolic
semanticscholar +1 more source
Sparse Topical Coding with Sparse Groups
2016Learning a latent semantic representing from a large number of short text corpora makes a profound practical significance in research and engineering. However, it is difficult to use standard topic models in microblogging environments since microblogs have short length, large amount, snarled noise and irregular modality characters, which prevent topic ...
Min Peng +6 more
openaire +1 more source
Sparse coding of sensory inputs
Current Opinion in Neurobiology, 2004Several theoretical, computational, and experimental studies suggest that neurons encode sensory information using a small number of active neurons at any given point in time. This strategy, referred to as 'sparse coding', could possibly confer several advantages. First, it allows for increased storage capacity in associative memories; second, it makes
Bruno A, Olshausen, David J, Field
openaire +2 more sources
Sparse Coding with Anomaly Detection
Journal of Signal Processing Systems, 2013We consider the problem of simultaneous sparse coding and anomaly detection in a collection of data vectors. The majority of the data vectors are assumed to conform with a sparse representation model, whereas the anomaly is caused by an unknown subset of the data vectors - the outliers - which significantly deviate from this model.
Amir Adler +3 more
openaire +1 more source