Robust Face Recognition via Sparse Representation

By John Wright, Allen Yuqing Yang, Arvind Ganesh, S. Sastry, Yi Ma. 2009

9,783 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Mechanics, Computer Vision and Pattern Recognition

How researchers see this paper

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

In Artificial Intelligence

1. Dacheng Tao
2. Trevor Darrell
3. Yoshua Bengio
4. Luc Van Gool
5. Bernt Schiele
6. Yi Yang
7. Qiang Yang
8. Jiashi Feng

In Computational Mechanics

1. Lei Zhang
2. Julien Mairal
3. Francis R. Bach
4. David Dapeng Zhang
5. Ming-Hsuan Yang
6. Xiangchu Feng
7. Dacheng Tao
8. Wangmeng Zuo

In Computer Vision and Pattern Recognition

1. Luc Van Gool
2. Dacheng Tao
3. Ming-Hsuan Yang
4. Xiaogang Wang
5. Yi Yang
6. Lei Zhang
7. Trevor Darrell
8. Andrew Zisserman

Citations in the corpus

• Discovering governing equations from data by sparse identification of nonlinear dynamical systems (2015, methodology): “ly few incoherent random measurements [12, 8, 9, 7, 2, 43]. The sparse solution ˘ to Eq. 1 may also be used for sparse classification schemes, such as the sparse representation for classification (SRC) [44]. Importantly, the compressive sensing and sparse representation architectures are convex and sc”
• Human Action Recognition Using Factorized Spatio-Temporal Convolutional Networks (2015, methodology): “Table 2 tells that our proposed data augmentation scheme by sampling video clips, and also the SCI based score fusion scheme effectively improve the recognition performance.”
• Beyond frontal faces: Improving Person Recognition using multiple cues (2015, background): “Some other works [36, 5] have addressed robust face recognition systems to deal with varying illumination, occlusion and disguise.”
• Optimization with Sparsity-Inducing Penalties (2011, methodology): “This is is also suggested by work such as [149, 154].”
• Understanding how image quality affects deep neural networks (2016, background): “These two notions of image quality may not be directly comparable as the computer may be fooled by images that are perceived by humans to be identical [1], or in some cases the computer can recognize images that are indistinguishable from noise by a human observer [2].”
• Robust Regression via Hard Thresholding (2015, background): “Owing to the wide-applicability of regression, RLSR features as a critical component of several important realworld applications in a variety of domains such as signal processing [1], economics [2], computer vision [3, 4], and astronomy [2].”
• Robust Lasso With Missing and Grossly Corrupted Observations (2011, background): “We notice that when the error fraction is O(n/ log n), only Ω(k log(p − k)) samples are sufficient to recover the exact signed supports of both the regression and sparse error vectors.”
• Recent Advances in Open Set Recognition: A Survey (2018, positive): “The SRC method and its variants are essentially still under a closed set assumption, so in order to adapt the SRC to an open environment, Zhang and Patel [55] presented the sparse representation-based open set recognition model, briefly called SROSR.”
• Deeply learned face representations are sparse, selective, and robust (2014, background): “Face recognition achieved great progress thanks to extensive research effort devoted to this area [31, 33, 6, 24, 37, 27, 25, 23, 38].”
• Exemplar-Based Sparse Representation Features: From TIMIT to LVCSR (2011, methodology): “Thus, the probabilities are generated in an ad-hoc methodology and cannot easily be compared across frames.”
• Gabor Feature Based Sparse Representation for Face Recognition with Gabor Occlusion Dictionary (2010, methodology): “Although the SRC based FR scheme proposed in [12] is very creative and effective, there are two issues to be further addressed.”
• Recent Advances on Spectral–Spatial Hyperspectral Image Classification: An Overview and New Guidelines (2018, result): “As in [33] and [127], the central assumption in our approach is”
• Learning Discriminant Face Descriptor (2014, background): “Recently, Ma et al. [6] propose a sparse representation classifier (SRC), which formulates the probe image as a linear combination of gallery images.”
• Facial Expression Analysis under Partial Occlusion (2018, methodology): “The sparse representation approach was firstly proposed for face recognition tasks in [Wright et al. 2009], and later applied into FEA, especially from occluded faces [Cotter 2010a],[Cotter 2010b],[Cotter 2011],[Zhang, et al. 2012].”
• Robust object tracking via sparsity-based collaborative model (2012, methodology): “In [27], the authors employ the reconstruction error on the target (positive) templates.”
• Convolutional Sparse Coding for Image Super-Resolution (2015, background): “By far, sparse representation has achieved state-of-the-art results in various computer vision tasks [15, 24, 30].”
• Robust arbitrary view gait recognition based on parametric 3D human body reconstruction and virtual posture synthesis (2016, background): “[40] exploited the discriminative nature of sparse 434 representation for classification.”
• Discriminant Correlation Analysis: Real-Time Feature Level Fusion for Multimodal Biometric Recognition (2016, background): “Most recently, sparse representation has attracted the interest of many researchers, both for reconstructive and discriminative tasks [18]–[20].”