Hybrid Euclidean-and-Riemannian Metric Learning for Image Set Classification

@inproceedings{Huang2014HybridEM,
  title={Hybrid Euclidean-and-Riemannian Metric Learning for Image Set Classification},
  author={Zhiwu Huang and Ruiping Wang and S. Shan and Xilin Chen},
  booktitle={ACCV},
  year={2014}
}
We propose a novel hybrid metric learning approach to combine multiple heterogenous statistics for robust image set classification. Specifically, we represent each set with multiple statistics – mean, covariance matrix and Gaussian distribution, which generally complement each other for set modeling. However, it is not trivial to fuse them since the mean vector with \(d\)-dimension often lies in Euclidean space \(\mathbb {R}^d\), whereas the covariance matrix typically resides on Riemannian… 
Multiple Manifolds Metric Learning with Application to Image Set Classification
TLDR
A novel algorithm which combines multiple manifolds as the features of the original image sets, and a metric Learning method has been devised to embed these kernel spaces into a lower dimensional common subspace for classification.
Statistical Adaptive Metric Learning for Action Feature Set Recognition in the Wild
TLDR
In the proposed method, multiple statistics, include means, covariance matrices and Gaussian distributions, are explicitly mapped or generated in the Riemannian manifolds and the deviation of principle elements is analyzed.
Covariances in Computer Vision and Machine Learning
TLDR
This book begins by presenting an overview of the finite-dimensional covariance matrix representation approach of images, along with its statistical interpretation, and discusses the various distances and divergences that arise from the intrinsic geometrical structures of the set of Symmetric Positive Definite matrices, namely Riemannian manifold and convex cone structures.
Bidirectional Covariance Matrices: A Compact and Efficient Data Descriptor for Image Set Classification
TLDR
Bidirectional covariance matrices are proposed to be used as a data descriptor to model image sets both from the row and column directions of images and they are proved to be compact and efficient.
Mixture Statistic Metric Learning for Robust Human Action and Expression Recognition
  • Shuanglu Dai, H. Man
  • Computer Science
    IEEE Transactions on Circuits and Systems for Video Technology
  • 2018
TLDR
A mixture statistic metric learning method for recognizing human actions and facial expressions in realistic “in the wild” scenarios and is compared with various state-of-the-art methods.
A statistic manifold kernel with graph embedding discriminant analysis for action and expression recognition
  • Shuanglu Dai, H. Man
  • Computer Science
    2017 IEEE International Conference on Image Processing (ICIP)
  • 2017
TLDR
This paper proposes a statistic manifold kernel for visual modeling that can achieve effective computation with the proposed kernel for action and expression recognition by exploiting the geometrical structure of the input data.
...
...

References

SHOWING 1-10 OF 40 REFERENCES
Covariance discriminative learning: A natural and efficient approach to image set classification
TLDR
A novel discriminative learning approach to image set classification by modeling the image set with its natural second-order statistic, i.e. covariance matrix, which shows the superiority of this method over state-of-the-art ones in both accuracy and efficiency, but also its stability to two real challenges: noisy set data and varying set size.
Learning Euclidean-to-Riemannian Metric for Point-to-Set Classification
TLDR
This paper proposes a novel Euclidean-to-Riemannian metric learning framework, which is first embedded into a high dimensional Hilbert space to reduce the gaps between the heterogeneous spaces and meanwhile respect the Riemanni geometry of the manifold.
Kernel Learning for Extrinsic Classification of Manifold Features
TLDR
This paper proposes two criteria for jointly learning the kernel and the classifier using a single optimization problem for the SVM classifier and formulate the problem of learning a good kernel-classifier combination as a convex optimization problem and solve it efficiently following the multiple kernel learning approach.
Kernel Methods on the Riemannian Manifold of Symmetric Positive Definite Matrices
TLDR
To encode the geometry of the manifold in the mapping, a family of provably positive definite kernels on the Riemannian manifold of SPD matrices is introduced, derived from the Gaussian kernel, but exploit different metrics on the manifold.
A Riemannian Framework for Tensor Computing
TLDR
This paper proposes to endow the tensor space with an affine-invariant Riemannian metric and demonstrates that it leads to strong theoretical properties: the cone of positive definite symmetric matrices is replaced by a regular and complete manifold without boundaries, the geodesic between two tensors and the mean of a set of tensors are uniquely defined.
Combining Multiple Manifold-Valued Descriptors for Improved Object Recognition
TLDR
This work proposes a feature combination and selection method that optimally combines descriptors lying on different manifolds while respecting the Riemannian geometry of each underlying manifold.
Graph embedding discriminant analysis on Grassmannian manifolds for improved image set matching
TLDR
It is shown that by introducing within-class and between-class similarity graphs to characterise intra-class compactness and inter-class separability, the geometrical structure of data can be exploited.
Grassmann discriminant analysis: a unifying view on subspace-based learning
TLDR
This paper proposes a discriminant learning framework for problems in which data consist of linear subspaces instead of vectors, and treats each sub-space as a point in the Grassmann space, and performs feature extraction and classification in the same space.
Multivariate Normal Distributions Parametrized as a Riemannian Symmetric Space
The construction of a distance function between probability distributions is of importance in mathematical statistics and its applications. The distance function based on the Fisher information
Discriminative Learning and Recognition of Image Set Classes Using Canonical Correlations
TLDR
A novel discriminative learning method over sets is proposed for set classification that maximizes the canonical correlations of within-class sets and minimizes thecanon correlations of between- class sets.
...
...