Human Action Recognition Using Hybrid Centroid Canonical Correlation Analysis

2015 ◽  
Author(s):  
Nour El Din El Madany ◽  
Yifeng He ◽  
Ling Guan
Keyword(s):  
Correlation Analysis ◽  
Action Recognition ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Human Action Recognition ◽  
Human Action

scholarly journals Multimodal Information Fusion for Human Action Recognition

2021 ◽  
Author(s):  
Nour Elmadany
Keyword(s):  
Deep Learning ◽  
Correlation Analysis ◽  
Action Recognition ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Human Action Recognition ◽  
Human Action ◽  
Local Network ◽  
Accelerometer Data ◽  
Fusion Technique

This thesis presents three frameworks of human action recognition to facilitate better recognition performance. The first framework fuses handcrafted features from four different modalities including RGB, depth, skeleton, and accelerometer data. In addition, a new descriptor for skeleton data is proposed that provides a discriminative representation for the poses of an action. Since the goal of the first framework is to find a more discriminative subspace, a generalized fusion technique Multimodal Hybrid Centroid Canonical Correlation Analysis (MHCCCA) is proposed for two or more sets of features or modalities. The second framework fuses handcrafted and deep learning features from three modalities including RGB, depth, and skeleton. In this framework a new depth representation is introduced that extracts the final representation using Deep ConvNet. The proposed fusion technique forms the backbone of the framework: Multiset Globality Locality Preserving Canonical Correlation Analysis (MGLPCCA) for two or more sets of features or modalities. MGLPCCA aims to preserve the local and global structures of data while maximizing the correlation among different modalities or sets. The third framework uses the deep learning techniques to improve the long term temporal modelling through two proposed techniques: Temporal Relational Network (TRN) and Temporal Second Order Pooling Based Network (T-SOPN). Additionally, Global-Local Network (GLN) and Fuse-Inception Network (FIN) are proposed to encourage the network to learn complementary information about the action and scene itself. Qualitative and quantitative experiments are conducted on nine different datasets demonstrating the effectiveness of the proposed framework over state-of-the-art methods.

scholarly journals Multimodal Information Fusion for Human Action Recognition

2021 ◽  
Author(s):  
Nour Elmadany
Keyword(s):  
Deep Learning ◽  
Correlation Analysis ◽  
Action Recognition ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Human Action Recognition ◽  
Human Action ◽  
Local Network ◽  
Accelerometer Data ◽  
Fusion Technique

This thesis presents three frameworks of human action recognition to facilitate better recognition performance. The first framework fuses handcrafted features from four different modalities including RGB, depth, skeleton, and accelerometer data. In addition, a new descriptor for skeleton data is proposed that provides a discriminative representation for the poses of an action. Since the goal of the first framework is to find a more discriminative subspace, a generalized fusion technique Multimodal Hybrid Centroid Canonical Correlation Analysis (MHCCCA) is proposed for two or more sets of features or modalities. The second framework fuses handcrafted and deep learning features from three modalities including RGB, depth, and skeleton. In this framework a new depth representation is introduced that extracts the final representation using Deep ConvNet. The proposed fusion technique forms the backbone of the framework: Multiset Globality Locality Preserving Canonical Correlation Analysis (MGLPCCA) for two or more sets of features or modalities. MGLPCCA aims to preserve the local and global structures of data while maximizing the correlation among different modalities or sets. The third framework uses the deep learning techniques to improve the long term temporal modelling through two proposed techniques: Temporal Relational Network (TRN) and Temporal Second Order Pooling Based Network (T-SOPN). Additionally, Global-Local Network (GLN) and Fuse-Inception Network (FIN) are proposed to encourage the network to learn complementary information about the action and scene itself. Qualitative and quantitative experiments are conducted on nine different datasets demonstrating the effectiveness of the proposed framework over state-of-the-art methods.

Analysis of Maximum Expiratory Flow Volume Curves Using Canonical Correlation Analysis

1985 ◽  
Vol 24 (02) ◽  
pp. 91-100 ◽  
Author(s):  
W. van Pelt ◽  
Ph. H. Quanjer ◽  
M. E. Wise ◽  
E. van der Burg ◽  
R. van der Lende
Keyword(s):  
Correlation Analysis ◽  
Canonical Correlation Analysis ◽  
Canonical Correlation ◽  
Flow Volume ◽  
Non Linear ◽  
Maximum Expiratory Flow ◽  
Expiratory Flow ◽  
Relationship Of ◽  
The Relationship ◽  
Age And Sex

SummaryAs part of a population study on chronic lung disease in the Netherlands, an investigation is made of the relationship of both age and sex with indices describing the maximum expiratory flow-volume (MEFV) curve. To determine the relationship, non-linear canonical correlation was used as realized in the computer program CANALS, a combination of ordinary canonical correlation analysis (CCA) and non-linear transformations of the variables. This method enhances the generality of the relationship to be found and has the advantage of showing the relative importance of categories or ranges within a variable with respect to that relationship. The above is exemplified by describing the relationship of age and sex with variables concerning respiratory symptoms and smoking habits. The analysis of age and sex with MEFV curve indices shows that non-linear canonical correlation analysis is an efficient tool in analysing size and shape of the MEFV curve and can be used to derive parameters concerning the whole curve.

Sign in / Sign up

Export Citation Format

Share Document