Kernel Sparse Representation for Image Classification and Face Recognition

By Shenghua Gao, Ivor Wai-Hung Tsang, Liang-Tien Chia. European Conference on Computer Vision, 2010

386 citations recorded by the source corpus.

Subfields: Computational Mechanics, Computer Vision and Pattern Recognition

View Paper: https://www.semanticscholar.org/paper/2126109a919edb04cf45efa9cfc6dff708136d16

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

1. Lei Zhang
2. Xiangchu Feng
3. Dacheng Tao
4. Meng Yang
5. Yong Rui
6. Jun Yu
7. Shenghua Gao
8. Lahiru Jayasinghe

In Computer Vision and Pattern Recognition

1. Dacheng Tao
2. Lei Zhang
3. Luc Van Gool
4. Ming-Hsuan Yang
5. Xiaogang Wang
6. Jun Yu
7. Trevor Darrell
8. Ling Shao

Citations in the corpus

• Feature Learning and Analysis for Cleanliness Classification in Restrooms (2019, methodology): “coding related methods such as [11] and [12], and Bof feature pooling could be performed using Spatial Pyramid Matching (SPM) or max-pooling [13], [14].”
• Real-time human action recognition based on depth motion maps (2013, background): “Sparse representation (or sparse coding) has been an active research area in the machine learning community due to its success in face recognition [15–18] and image classification [18, 19].”
• Hyperspectral image classification via kernel sparse representation (2011, background): “Moreover, the spatial coherency across neighboring pixels is also incorporated through a kernelized joint sparsity model, where all of the pixels within a small neighborhood are jointly represented in the feature space by selecting a few common training samples.”
• Kernel Sparse Representation-Based Classifier (2012, methodology): “In the following, we give the classification based on KSRC in the kernel feature space.”
• 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.”
• Sparse representation or collaborative representation: Which helps face recognition? (2011, methodology): “Gao et al. [9] proposed the kernel sparse representation for FR, while Yang and Zhang [10] used the Gabor features for SRC with a learned Gabor occlusion dictionary to reduce the computational cost.”
• Hand-Crafted Features or Machine Learnt Features? Together They Improve RGB-D Object Recognition (2014, methodology): “The commonly used feature encoding includes the sparse coding based feature encoding and its variance, for example, sparse coding [22], LLC [26], kernel sparse representation[14], [31].”
• Click Prediction for Web Image Reranking Using Multimodal Sparse Coding (2014, methodology): “It has been widely used in many different applications, such as image classification [14], face recognition [15], image annotation [17], and image restoration [13].”
• Pose-based human action recognition via sparse representation in dissimilarity space (2014, background): “Also, recent advances reported in [13] regarding to kernel generalizati ons of sparse representationbased classification schemes, indicate the efficiency of sparse representation techniqu es in collaboratio n with proximity representat ions on classification tasks.”
• Laplacian Sparse Coding, Hypergraph Laplacian Sparse Coding, and Applications (2013, methodology): “In the computer vision area, the signals studied usually are image feature or image instance, and sparse coding is usually used as an efficient technique for feature/image reconstruction [8], [9], [10] and similarity measurement [11], [12].”