Sparse Representation-based Classification

8 papers with code • 1 benchmarks • 1 datasets

Sparse Representation-based Classification is the task based on the description of the data as a linear combination of few building blocks - atoms - taken from a pre-defined dictionary of such fundamental elements.


Most implemented papers

Linear Disentangled Representation Learning for Facial Actions

eglxiang/icassp15_emotion 11 Jan 2017

Limited annotated data available for the recognition of facial expression and action units embarrasses the training of deep networks, which can learn disentangled invariant features.

Hierarchical Sparse and Collaborative Low-Rank Representation for Emotion Recognition

eglxiang/icassp15_emotion 7 Oct 2014

In this paper, we design a Collaborative-Hierarchical Sparse and Low-Rank (C-HiSLR) model that is natural for recognizing human emotion in visual data.

Sparse Representation-based Open Set Recognition

hezhangsprinter/SROSR 6 May 2017

We propose a generalized Sparse Representation- based Classification (SRC) algorithm for open set recognition where not all classes presented during testing are known during training.

Classifying Multi-channel UWB SAR Imagery via Tensor Sparsity Learning Techniques

tiepvupsu/tensorsparsity 4 Oct 2018

Using low-frequency (UHF to L-band) ultra-wideband (UWB) synthetic aperture radar (SAR) technology for detecting buried and obscured targets, e. g. bomb or mine, has been successfully demonstrated recently.

Deep Sparse Representation-based Classification

mahdiabavisani/DSRC 24 Apr 2019

The proposed network consists of a convolutional autoencoder along with a fully-connected layer.

Multiplication fusion of sparse and collaborative-competitive representation for image classification

li-zi-qi/SCCRC 20 Jan 2020

Firstly, the coefficients of the test sample are obtained by SRC and CCRC, respectively.

A Personalized Zero-Shot ECG Arrhythmia Monitoring System: From Sparse Representation Based Domain Adaption to Energy Efficient Abnormal Beat Detection for Practical ECG Surveillance

mertduman/zero-shot-ecg 14 Jul 2022

An extensive set of experiments performed on the benchmark MIT-BIH ECG dataset shows that when this domain adaptation-based training data generator is used with a simple 1-D CNN classifier, the method outperforms the prior work by a significant margin.

SparseFormer: Sparse Visual Recognition via Limited Latent Tokens

showlab/sparseformer 7 Apr 2023

In this paper, we challenge this dense paradigm and present a new method, coined SparseFormer, to imitate human's sparse visual recognition in an end-to-end manner.