Graph-based classification of multiple observation sets

@article{Kokiopoulou2008GraphbasedCO,
  title={Graph-based classification of multiple observation sets},
  author={Effrosini Kokiopoulou and Pascal Frossard},
  journal={Pattern Recognit.},
  year={2008},
  volume={43},
  pages={3988-3997}
}

Distributed classification of multiple observations by consensus

A graph-based problem formulation whose objective function captures the smoothness of candidate labels on the data manifold is presented, and a distributed average consensus algorithm for estimating the unknown object class is designed by computing the value of the above smoothness objective function for different class hypotheses.

Multi-observation face recognition in videos based on label propagation

A novel approach for efficient and adaptive graph construction, based on a two-phase scheme: the first phase is used to adaptively find the neighbors of a sample and also to find the adequate weights for the minimization function of the second phase.

Efficient Graph Construction for Label Propagation Based Multi-observation Face Recognition

A novel approach for efficient and adaptive graph construction that can be used for multi-observation face recognition as well as for other recognition problems is proposed.

Recognizing multiple observations using adaptive graph based label propagation

A performance study of the proposed robust and adaptive method for constructing sparse graphs shows that in addition to its superiority over competing graph construction methods, the proposed method can easily solve the label inference of multiple observations and can work with several types of image descriptors and scenes.

Mixed-norm sparse representation for multi view face recognition

Alignment of uncalibrated images for multi-view classification

The results on multi-view image classification suggest that the proposed alignment method can be effectively used in graph-based classification algorithms for the computation of pairwise distances where it achieves significant improvements over distance computation without prior alignment.

Joint dynamic sparse learning and its application to multi-view face recognition

An efficient learning algorithm for the joint dynamic sparsity using the accelerated proximal gradient descent is developed and the experimental results on the public CMU Multi-PIE dataset verify its effectiveness.

Multiview Automatic Target Recognition for Infrared Imagery Using Collaborative Sparse Priors

A novel multitask extension of the widely used sparse-representation-classification method is proposed in both single and multiview set-ups, and a joint prior and sparse coefficient estimation method (JPCEM) is proposed for the first time in this article in order to alleviate the need to handpick prior parameters required before classification.

References

SHOWING 1-10 OF 37 REFERENCES

Graph-based classification for multiple observations of transformed patterns

This work builds on graph-based methods for semi-supervised learning and optimize the graph construction in order to exploit the special structure of the problem of classification when multiple observations of a pattern are available.

Manifold-Manifold Distance with application to face recognition based on image set

The proposed MMD method outperforms the competing methods on the task of Face Recognition based on Image Set, and a novel manifold learning approach is proposed, which expresses a manifold by a collection of local linear models, each depicted by a subspace.

Video-based face recognition using probabilistic appearance manifolds

A maximum a posteriori formulation is presented for face recognition in test video sequences by integrating the likelihood that the input image comes from a particular pose manifold and the transition probability to this pose manifold from the previous frame.

Face Recognition from Long-Term Observations

This work addresses the problem of face recognition from a large set of images obtained over time - a task arising in many surveillance and authentication applications and proposes an information-theoretic algorithm that classifies sets of images using the relative entropy between the estimated density of the input set and that of stored collections of images for each class.

Orthogonal Neighborhood Preserving Projections: A Projection-Based Dimensionality Reduction Technique

  • E. KokiopoulouY. Saad
  • Computer Science
    IEEE Transactions on Pattern Analysis and Machine Intelligence
  • 2007
This paper proposes a method, named orthogonal neighborhood preserving projections, which works by first building an "affinity" graph for the data in a way that is similar to the method of locally linear embedding (LLE); in contrast with the standard LLE, ONPP employs an explicit linear mapping between the input and the reduced spaces.

Graph-based transformation manifolds for invariant pattern recognition with kernel methods

The approach is based on building a kernel function on the graph modeling the graphs of data transformation manifolds for invariant learning with kernel methods, providing state-of-the-art performance on harder problem settings.

Graph-based transformation manifolds for invariant pattern recognition with kernel methods

The approach is based on building a kernel function on the graph modeling the graphs of data transformation manifolds for invariant learning with kernel methods, providing state-of-the-art performance on harder problem settings.

Minimally-supervised classification using multiple observation sets

  • C. Stauffer
  • Computer Science
    Proceedings Ninth IEEE International Conference on Computer Vision
  • 2003
This method uses the Naive Bayes estimate of how often the two observations did result from the same observed process to generalize complex classification models from single labeled observations.

Face recognition with image sets using manifold density divergence

A flexible, semi-parametric model for learning probability densities confined to highly non-linear but intrinsically low-dimensional manifolds is proposed, which leads to a statistical formulation of the recognition problem in terms of minimizing the divergence between densities estimated on these manifolds.