Effective fusing the factored matrices in dual tensors for action recognition

Hsieh, Chung-Yang; Lin, Wei-Yang

doi:10.1109/mva.2015.7153210

Cited by 3 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tensor canonical correlation analysis (TCCA) was introduced by Kim et al 4,5 It was a generalization of CCA of multidimensional arrays (Tensor), which can be applied to motion/gesture classification in videos. Hsieh and Lin 6,7 introduced the method of calculating the similarity between tensors. The core idea was to consider each expansion matrix in the tensor as an individual to estimate the similarity between two tensors, which can effectively use each characteristic of the expansion matrix.…”

Section: Introductionmentioning

confidence: 99%

Tensor mutual information and its applications

Ren

Cui

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

Correlation analysis has long been a question of great interest in measuring the relationship among different variables and has been applied in many fields, such as dimension reduction, classification, and so on. However, current methods of correlation analysis take into account the linear relationship between multiple variables and only few works on nonlinear interaction of two variables have been considered. In this article, we first present a nonlinear analysis method of multiple (two or more) variables based on mutual information for tensor analysis (MITA). In addition, we extend the mutual-information matrix analysis directly to MITA and show the multivariable mutual information formula based on Venn diagram. Experiments on multiview dimension reduction, including attacking internet traffic prediction, advertisement classification, and biometric structure prediction illustrate the effectiveness of the proposed method, especially in the case of low-dimensional subspace.

show abstract

Section: Introductionmentioning

confidence: 99%

Tensor mutual information and its applications

Ren

Cui

et al. 2020

Concurrency and Computation

View full text Add to dashboard Cite

show abstract

Low-Rank Tensor Subspace Learning for RGB-D Action Recognition

Jia

2016

IEEE Trans. on Image Process.

View full text Add to dashboard Cite

RGB-D action data inherently equip with extra depth information to improve performance of action recognition compared with RGB data, and many works represent the RGB-D data as a third-order tensor containing a spatiotemporal structure and find a subspace with lower dimension. However, there are two main challenges of these methods. First, the dimension of subspace is usually fixed manually, which may not describe the samples well in the subspace. Second, preserving local information by finding the intra-class and inter-class neighbors from a manifold is highly time-consuming. In this paper, we learn a tensor subspace, whose dimension is learned automatically by low-rank learning, for RGB-D action recognition. Particularly, the tensor samples are factorized to obtain three projection matrices (PMs) by Tucker Decomposition, where all the PMs are performed by nuclear norm in a close-form to obtain the tensor ranks, which are used as tensor subspace dimension. In addition, we extract the discriminant and local information from a manifold using a graph constraint. This graph preserves the local knowledge inherently, which is faster than the previous way of calculating both the intra-class and inter-class neighbors of each sample. We evaluate the proposed method on four widely used RGB-D action datasets including MSRDailyActivity3D, MSRActionPairs, MSRActionPairs skeleton, and UTKinect-Action3D datasets, and the experimental results show higher accuracy and efficiency of the proposed method.

show abstract

Mutual Information on Tensors for Measuring the Nonlinear Correlations in Network Security

Ren

Cui

et al. 2019

2019 18th IEEE International Conference on Trust, Security and Privacy in Computing and Communications/13th IEEE International

View full text Add to dashboard Cite

Effective fusing the factored matrices in dual tensors for action recognition

Cited by 3 publications

References 20 publications

Tensor mutual information and its applications

Tensor mutual information and its applications

Low-Rank Tensor Subspace Learning for RGB-D Action Recognition

Mutual Information on Tensors for Measuring the Nonlinear Correlations in Network Security

Contact Info

Product

Resources

About