Sparse Representation for Computer Vision and Pattern Recognition

By John Wright, Yi Ma, Julien Mairal, Guillermo Sapiro, Thomas S. Huang, Shuicheng Yan. 2010

1,948 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Representation & Self-Supervised Learning

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

In Representation & Self-Supervised Learning

Citations in the corpus

Deep Generative Image Models using a Laplacian Pyramid of Adversarial Networks (2015, background): “Very large Gaussian mixture models [34] and sparse coding models of image patches [31] can also be used but suffer the same problem.”
Cross-Stitch Networks for Multi-task Learning (2016, background): “and their widespread applications in other fields, such as genomics [38], natural language processing [7, 8, 35] and computer vision [3, 10, 30, 31, 40, 51, 53, 58].”
Normalization Propagation: A Parametric Technique for Removing Internal Covariate Shift in Deep Networks (2016, background): “On the other hand, it is generally observed that useful ﬁlters that constitute a good representation of real world data are roughly incoherent (Wright et al., 2010; Makhzani & Frey, 2013); thus ensuring the R.H.S is small thereby minimizing the error bound.”
HCP: A Flexible CNN Framework for Multi-Label Image Classification (2014, methodology): “ti-label image classiﬁcation. LBP [32] are ﬁrstly extracted on dense grids or sparse interest points and then quantized by different coding schemes, e.g., Vector Quantization (VQ), Sparse Coding (SC) [44] and Gaussian Mixture Models (GMM). These encoded features are ﬁnally pooled by feature aggregat”
Recent Advances in Open Set Recognition: A Survey (2018, background): “Sparse Representation-based: In recent years, the sparse representation-based techniques have been widely used in computer vision and image processing fields [97]–[99].”
Patch Group Based Nonlocal Self-Similarity Prior Learning for Image Denoising (2015, methodology): “The seminal work of K-SVD [8, 22] has demonstrated promising denoising performance by dictionary learning, which has yet been extended and successfully used in various image processing and computer vision applications [23, 24, 25].”
Saliency-Guided Unsupervised Feature Learning for Scene Classification (2015, background): “Hinton and Salakhutdinov [12] used deep neural networks to learn low-dimensional feature representations to reduce the dimensionality of the data.”
Attribute feedback (2012, methodology): “Particularly, due to the success of 1-norm in signal representation [28] and image annotation [30, 31], we use the 1-norm regression model as the preliminary classifiers to learn sparse parameters.”
Sparse coding with memristor networks. (2017, methodology): “…ﬁ cient digital approach shows that an integrated memristor system based on devices similar to the prototype system can already offer signi ﬁ cant energy advantages when performing data-intensive tasks such as real-time video analysis (Supplementary Figs 22 – 25 and Supplementary Tables 1 and 2).”
Half-Quadratic-Based Iterative Minimization for Robust Sparse Representation (2014, background): “Although several robust sparse models have been proposed and promising results have been obtained, they are either for error correction or for error detection, and learning a general framework that systematically unifies these two aspects and explores their relation is still an open problem.”
Improving Human Action Recognition Using Fusion of Depth Camera and Inertial Sensors (2015, background): “One cannot directly solve for α since (1) is typically under-determined [21].”
Domain Adaptive Dictionary Learning (2012, background): “In recent years, sparse and redundant modeling of signals has received a lot of attention from the vision community [1].”
Real-time human action recognition based on depth motion maps (2013, background): “From a practical standpoint, one cannot directly solve for a since (2) is typically under-determined [17].”
Fast L1-Minimization Algorithms For Robust Face Recognition (2010, neutral): “The sparsity-seeking property of 1 -min optimization has been shown to have applications in many areas such as geophysics, speech recognition [7], image compression, processing, and enhancement [4], [8], sensor networks [9], [10], and computer vision [11].”
A Two-Phase Test Sample Sparse Representation Method for Use With Face Recognition (2011, methodology): “In this section, we first present the sparse representation method proposed in [22] and [23].”
Non-negative low rank and sparse graph for semi-supervised learning (2012, methodology): “Among current methods, graph based SSL is particularly appealing due to its empirical success in practice and its computational efficiency.”
Classification and clustering via dictionary learning with structured incoherence and shared features (2010, methodology): “One could think of using the whole training datasets as dictionariesforeachclassaswiththeapproachesmentioned in the introduction [8, 24, 33 ].”
Hyperspectral image classification via kernel sparse representation (2011, background): “Recently, sparse representation [18], [19] has also been proposed to solve many computer vision tasks [20]–[25], where the usage of sparsity as a prior often leads to state-of-theart performance.”