Sparse representation or collaborative representation: Which helps face recognition?

By Lei Zhang, Meng Yang, Xiangchu Feng. Vision, 2011

2,080 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Human-Computer Interaction

View Paper: https://www.semanticscholar.org/paper/1a1a60fd4dc88a14c016b95789385801c6b80574

How researchers see this paper

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

In Computer Vision and Pattern Recognition

In Human-Computer Interaction

Citations in the corpus

Sparse Representation Based Fisher Discrimination Dictionary Learning for Image Classification (2014, methodology): “It is indicated in (Zhang et al. 2011) that the l1-norm sparsity penalty on the representation coefficients may not be critical in the SRC classifier.”
Partial Face Recognition: Alignment-Free Approach (2013, methodology): “3) We extend the MKD-SRC method for partial face verification, which is effective on the LFW database.”
Projective dictionary pair learning for pattern classification (2014, methodology): “When the minimization process converges, a balance between the discrimination and representation power of the model can be achieved.”
Fusion of depth, skeleton, and inertial data for human action recognition (2016, methodology): “Hence, for a test action sample y , three CRC classifiers are used, each handling one type of features.”
Fast L1-Minimization Algorithms For Robust Face Recognition (2010, neutral): “We refer the interested reader to discussions in [35], [36].”
A Training-free Classification Framework for Textures, Writers, and Materials (2012, methodology): “Lately, sparse and collaborative representation based classifiers performed best at various tasks such as face recognition [34, 40] or traffic sign recognition [28].”
A Survey of Sparse Representation: Algorithms and Applications (2015, methodology): “Thus, in terms of the diff erent norms used in optimizers, the sparse representation method s can be roughly grouped into five general categories: sparse representation with the l0-norm minimization [36, 37], sparse representation with thelp-norm (0<p<1) minimization [38– 40], sparse representation ”
Half-Quadratic-Based Iterative Minimization for Robust Sparse Representation (2014, methodology): “In addition, HQSA and HQSM perform slightly better than LRC and CRC. Fig.”
Pose-based human action recognition via sparse representation in dissimilarity space (2014, background): “in [32,33] raised the question of whether it is useful to perform pose estimation for the action recognition task or it is better to extract low-level appearance features directly from video data.”
Deep Spatial Feature Reconstruction for Partial Person Re-identification: Alignment-free Approach (2018, background): “Further studies [4, 27, 24, 23] on face recognition with SRC have also been conducted.”
UTD-MHAD: A multimodal dataset for human action recognition utilizing a depth camera and a wearable inertial sensor (2015, methodology): “For action recognition, the collaborative representation classifier (CRC) described in [20] was utilized to evaluate the effectiveness of the fusion approach.”
A Comprehensive Study on Center Loss for Deep Face Recognition (2019, background): “Sparse representation based clas-siﬁcation (Wright et al. 2009) and its variants (Zhang et al. 2011) encode faces over the subspace of template images.”