Hessian Regularized Sparse Coding for Human Action Recognition

Liu, Weifeng; Zhen, Wang; Tao, Dapeng; Yu, Jun

doi:10.1007/978-3-319-14442-9_55

Cited by 12 publications

(3 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Sparse representation aims to learn the sparse weights wi of each example xi simultaneously with a dictionary D. In the following, the data matrix of examples is denoted as = { 1 , 2 , ⋯ , } ∈ ℜ × , (here X is same as S) For a given sparse representation dictionary = { 1 , 2 , ⋯ , } ∈ ℜ × , the sparse representation coefficients matrix M is denoted as = { 1 , 2 , ⋯ , } ∈ ℜ × . Then, the Lp-norm based sparse representation [16] can be expressed as:…”

Section: Arsr Frameworkmentioning

confidence: 99%

See 1 more Smart Citation

Adaptive Lp-Norm Regularized Sparse Representation for Human Activity Recognition in Coal Mines

Wang¹,

Geng²

2020

JESA

View full text Add to dashboard Cite

This paper aims to overcome the lack of in-depth exploration into the intrinsic geometry of human activities. For this purpose, a generalized adaptive Lp-norm regularized sparse representation (ARSR) approach was proposed for human activity recognition, which preserves the model adaptability through the adaptive Lp-norm regularization. In essence, the proposed method applies sparse representation to human activity recognition, turning it into a new optimization problem. In addition, the problem was solved by the iterative-shrinkage-thresholding algorithm. Specifically, the sparse representation learned by the ARSR algorithm was introduced into the support vector machine (SVM) classifier. Then, several experiments were conducted on coal-mining datasets for human activity identification. The experimental results revealed that the proposed algorithm is superior to the current sparse representation algorithms like the standard L1-norm regularized sparse representation algorithm. The research findings shed new light on the human activity recognition in coal mines.

show abstract

Section: Arsr Frameworkmentioning

confidence: 99%

“…The hierarchical-layer strategies recognize high-level human activities often represented by sequential concatenating and ranking of simple human actions. The typical hierarchical-layer strategies include Markov chain Monte Carlo (MCMC) [13] with Bayesian Networks [14], as well as Laplacian [12,15] and Hessian [16] regularized approaches.…”

Section: Introductionmentioning

confidence: 99%

Adaptive Lp-Norm Regularized Sparse Representation for Human Activity Recognition in Coal Mines

Wang¹,

Geng²

2020

JESA

View full text Add to dashboard Cite

show abstract

“…22,23 Amongst alternate approaches that focus on Sparse coding, Qiu et al 24 reports a sparse dictionary-based representation for action. Liu et al 25 proposes a Hessian regularized sparse coding method for action recognition. Lu et al 26 proposed the idea of slicing frame to patches in different scales and using patches to train dictionaries.…”

Section: Dictionary Learningmentioning

confidence: 99%

Discriminative Dictionary Design for Action Classification in Still Images

Roy

Banerjee

Murino

2017

Image Analysis and Processing - ICIAP 2017

View full text Add to dashboard Cite

In this paper, we address the problem of action recognition from still images and videos. Traditional local features such as SIFT, STIP etc. invariably pose two potential problems: 1) they are not evenly distributed in different entities of a given category and 2) many of such features are not exclusive of the visual concept the entities represent. In order to generate a dictionary taking the aforementioned issues into account, we propose a novel discriminative method for identifying robust and category specific local features which maximize the class separability to a greater extent. Specifically, we pose the selection of potent local descriptors as filtering based feature selection problem which ranks the local features per category based on a novel measure of distinctiveness. The underlying visual entities are subsequently represented based on the learned dictionary and this stage is followed by action classification using the random forest model followed by label propagation refinement. The framework is validated on the action recognition datasets based on still images (Stanford-40) as well as videos (UCF-50) and exhibits superior performances than the representative methods from the literature.

show abstract

A Strict Pyramidal Deep Neural Network for Action Recognition

Ullah

Petrosino

2015

Image Analysis and Processing — ICIAP 2015

View full text Add to dashboard Cite

Hessian Regularized Sparse Coding for Human Action Recognition

Cited by 12 publications

References 24 publications

Adaptive Lp-Norm Regularized Sparse Representation for Human Activity Recognition in Coal Mines

Adaptive Lp-Norm Regularized Sparse Representation for Human Activity Recognition in Coal Mines

Discriminative Dictionary Design for Action Classification in Still Images

A Strict Pyramidal Deep Neural Network for Action Recognition

Contact Info

Product

Resources

About