Sparse and Redundant Representations - From Theory to Applications in Signal and Image Processing

By Michael Elad. 2010

2,974 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/cc9c23f426119642bdd2e0e36590439672d067e9

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Mechanics

In Computer Vision and Pattern Recognition

Citations in the corpus

Exact Recovery of Sparsely Used Overcomplete Dictionaries (2013, background): “Moreover, in the context of blind source separation (BSS) of audio, image or video signals, the dictionary learning problem is typically overcomplete, since there are more sources than observations [14].”
Real-Time Single Image and Video Super-Resolution Using an Efficient Sub-Pixel Convolutional Neural Network (2016, background): “This transform domain is usually a dictionary of image atoms [25, 10], which can be learnt through a training process that tries to discover the correspondence between LR and HR patches.”
Complete dictionary recovery over the sphere (2015, background): “Its applications span classical image processing, visual recognition, compressive signal acquisition, as well as recent deep architectures for signal classification [2, 3].”
Going deeper into action recognition: A survey (2016, background): “2 AGGREGATION WITH SPATIOTEMPORAL DICTIONARY LEARNING AND SPARSE CODING Sparse coding has become a popular choice in neuroscience, information theory, signal processing, and other related areas (Olshausen and Field, 1997; Candès et al., 2006; Donoho, 2006; Elad, 2010) in the last decade.”
Dualize, Split, Randomize: Fast Nonsmooth Optimization Algorithms (2020, background): “In the age of ‘big data’, with the explosion in size and complexity of the data to process, it is increasingly challenging to solve these optimization problems, whose solutions live in very high dimensional spaces [7–10].”
Sparse Modeling for Image and Vision Processing (2014, methodology): “The first baseline considered by Elad and Aharon [2006] uses a fixed overcomplete discrete cosine transform (DCT) dictionary, which was presented earlier in Figure 2.”
TROIKA: A General Framework for Heart Rate Monitoring Using Wrist-Type Photoplethysmographic Signals During Intensive Physical Exercise (2014, background): “The limitations of conventional nonparametric spectrum estimation and high-resolution line spectrum estimation motivate us to use SSR [19]–[21].”
Exponentially vanishing sub-optimal local minima in multilayer neural networks (2017, background): “There are many relatively simple extensions of these results: the Gaussian assumption could be relaxed to other near-isotropic distributions ( e.g. , sparse-land model, (Elad, 2010, Section 9.2)) and other convex loss functions are possible instead of the quadratic loss.”