Discriminative K-SVD for dictionary learning in face recognition

By Qiang Zhang, Baoxin Li. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition, 2010

1,316 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition, Media Technology

View Paper: https://www.semanticscholar.org/paper/9f70088ae0c839455f4da91f44a1783f6d3c6c9e

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 Media Technology

Citations in the corpus

Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification (2014, methodology): “We also report the running time of shared dictionary learning method DKSVD (Zhang and Li 2010), class-specific dictionary learning method DLSI (Ramirez et al. 2010), and hybrid dictionary learning method COPAR (Kong and Wang 2012).”
Convolutional Neural Networks Analyzed via Convolutional Sparse Coding (2016, background): “…is the sparse representation concept, being one of the most popular choices for a prior in the signal and image processing communities, and leading to exceptional results in various applications (Elad and Aharon, 2006; Dong et al., 2011; Zhang and Li, 2010; Jiang et al., 2011; Mairal et al., 2014).”
Robust and Discriminative Self-Taught Learning (2013, neutral): “…determined by the learned patterns in A k (0 ≤ k ≤ K), we still need to pre-specify the size of D, same as in existing related works (Raina et al., 2007; Raina, 2009; Bengio et al., 2009; Lee et al., 2007; Mairal et al., 2009; 2008; Zhang & Li, 2010; Pham & Venkatesh, 2008; Mairal et al., 2010).”
Active Lifelong Learning With "Watchdog" (2018, methodology): “2009), K-SVD (Aharon, Elad, and Bruckstein 2006), LC-KSVD1 and LC-KSVD2 (Jiang, Lin, and Davis 2013), D-KSVD (Zhang and Li 2010) and ORDL (Lu, Shi, and Jia 2013).”
Fisher Discrimination Dictionary Learning for sparse representation (2011, methodology): “Recently sparse representation techniques have also led to promising results in image classification, e.g. face recognition (FR) [5] [6] [7] [10] [31], digit and texture classification [8] [9] [11] [12], etc.”
Sparse Modeling for Image and Vision Processing (2014, methodology): “12: Illustration of the hierarchical sparsity of Zhao et al. [2009], which generalizes the zero-tree coding scheme of Shapiro [1993].”
Group Sparsity and Geometry Constrained Dictionary Learning for Action Recognition from Depth Maps (2013, methodology): “For example, Zhang and Li [25] proposed a discriminative K-SVD method by incorporating classification error into the objective function and learned the classifier together with the dictionary.”
State-of-the-Art Deep Learning: Evolving Machine Intelligence Toward Tomorrow’s Intelligent Network Traffic Control Systems (2017, background): “On the other hand, the work in [12] presented a novel deep learning based sparse coding with forced incoherent dictionary atoms [190]–[192] for conducting origin ﬂow prediction.”
Removing Rain from a Single Image via Discriminative Sparse Coding (2015, methodology): “[13, 18, 27]) for sparse coding based image classiﬁcation, we propose a discriminative sparse coding method to regularize the image de-raining process under over learned dictionary with mutual exclusivity property.”
Sparse coding based visual tracking: Review and experimental comparison (2013, methodology): “For dictionary learning, there are some effective discriminative dictionary methods [65,66] proposed in object recognition, which could be modiﬁed to be used in visual tracking.”
A Deep Generative Deconvolutional Image Model (2015, methodology): “We start by relating our model to optimization-based dictionary learning and DN, the work of (Mairal et al., 2008; Zhang and Li, 2010) and (Ciresan et al., 2012; Zeiler and Fergus, 2014; Zeiler et al., 2010), respectively.”
Semi-supervised Robust Dictionary Learning via Efficient l-Norms Minimization (2013, background): “Recent researches [1, 8] have shown that the linear decomposition of a signal using a few atoms of a learned dictionary, instead of a predefined one, usually leads to stateof-the-art results in a number of computer vision applications, such as image annotation [3], face recognition [18], texture cla”