Towards a unified framework for graph-based multi-view clustering.

Recently, clustering data collected from various sources has become a hot topic in real-world applications. The most common methods for multi-view clustering can be divided into several categories: Spectral clustering algorithms, subspace multi-view clustering algorithms, matrix factorization approaches, and kernel methods. Despite the high performance of these methods, they directly fuse all similarity matrices of all views and separate the affinity learning process from the multiview clustering process. The performance of these algorithms can be affected by noisy affinity matrices. To overcome this drawback, this paper presents a novel method called One Step Multi-view Clustering via Consensus Graph Learning and Nonnegative Embedding (OSMGNE). Instead of directly merging the similarity matrices of different views, which may contain noise, a step of learning a consensus similarity matrix is performed. This step forces the similarity matrices of different views to be too similar, which eliminates the problem of noisy data. Moreover, the use of the nonnegative embedding matrix (soft cluster assignment matrix makes it possible to directly obtain the final clustering result without any extra step. The proposed method can solve five subtasks simultaneously. It jointly estimates the similarity matrix of all views, the similarity matrix of each view, the corresponding spectral projection matrix, the unified clustering indicator matrix, and automatically gives the weight of each view without the use of hyper-parameters. In addition, another version of our method is also studied in this paper. This method differs from the first one by using a consensus spectral projection matrix and a consensus Laplacian matrix over all views. An iterative algorithm is proposed to solve the optimization problem of these two methods. The two proposed methods are tested on several real datasets, which prove their superiority.

Spatiotemporal CNN with Pyramid Bottleneck Blocks: Application to eye blinking detection.

Eye blink detection is a challenging problem that many researchers are working on because it has the potential to solve many facial analysis tasks, such as face anti-spoofing, driver drowsiness detection, and some health disorders. There have been few attempts to detect blinking in the wild scenario, while most of the work has been done under controlled conditions. Moreover, current learning approaches are designed to process sequences that contain only a single blink ignoring the case of the presence of multiple eye blinks. In this work, we propose a fast framework for eye blink detection and eye blink verification that can effectively extract multiple blinks from image sequences considering several challenges such as lighting changes, variety of poses, and change in appearance. The proposed framework employs fast landmarks detector to extract multiple facial key points including the ones that identify the eye regions. Then, an SVD-based method is proposed to extract the potential eye blinks in a moving time window that is updated with new images every second. Finally, the detected blink candidates are verified using a 2D Pyramidal Bottleneck Block Network (PBBN). We also propose an alternative approach that uses a sequence of frames instead of an image as input and employs a continuous 3D PBBN that follows most of the state-of-the-art approaches schemes. Experimental results show the better performance of the proposed approach compared to the state-of-the-art approaches.

Knowledge-based tensor subspace analysis system for kinship verification.

Most existing automatic kinship verification methods focus on learning the optimal distance metrics between family members. However, learning facial features and kinship features simultaneously may cause the proposed models to be too weak. In this work, we explore the possibility of bridging this gap by developing knowledge-based tensor models based on pre-trained multi-view models. We propose an effective knowledge-based tensor similarity extraction framework for automatic facial kinship verification using four pre-trained networks (i.e., VGG-Face, VGG-F, VGG-M, and VGG-S). Therefore, knowledge-based deep face and general features (such as identity, age, gender, ethnicity, expression, lighting, pose, contour, edges, corners, shape, etc.) were successfully fused by our tensor design to understand the kinship cue. Multiple effective representations are learned for kinship verification statements (children and parents) using a margin maximization learning scheme based on Tensor Cross-view Quadratic Exponential Discriminant Analysis. Through the exponential learning process, the large gap between distributions of the same family can be reduced to the maximum, while the small gap between distributions of different families is simultaneously increased. The WCCN metric successfully reduces the intra-class variability problem caused by deep features. The explanation of black-box models and the problems of ubiquitous face recognition are considered in our system. The extensive experiments on four challenging datasets show that our system performs very well compared to state-of-the-art approaches.

An enhanced approach to the robust discriminant analysis and class sparsity based embedding.

In recent times, feature extraction attracted much attention in machine learning and pattern recognition fields. This paper extends and improves a scheme for linear feature extraction that can be used in supervised multi-class classification problems. Inspired by recent frameworks for robust sparse LDA and Inter-class sparsity, we propose a unifying criterion able to retain the advantages of these two powerful linear discriminant methods. We introduce an iterative alternating minimization scheme in order to estimate the linear transformation and the orthogonal matrix. The linear transformation is efficiently updated via the steepest descent gradient technique. The proposed framework is generic in the sense that it allows the combination and tuning of other linear discriminant embedding methods. We used our proposed method to fine tune the linear solutions delivered by two recent linear methods: RSLDA and RDA_FSIS. Experiments have been conducted on public image datasets of different types including objects, faces, and digits. The proposed framework compared favorably with several competing methods.

Feature fusion via Deep Random Forest for facial age estimation.

In the last few years, human age estimation from face images attracted the attention of many researchers in computer vision and machine learning fields. This is due to its numerous applications. In this paper, we propose a new architecture for age estimation based on facial images. It is mainly based on a cascade of classification trees ensembles, which are known recently as a Deep Random Forest. Our architecture is composed of two types of DRF. The first type extends and enhances the feature representation of a given facial descriptor. The second type operates on the fused form of all enhanced representations in order to provide a prediction for the age while taking into account the fuzziness property of the human age. While the proposed methodology is able to work with all kinds of image features, the face descriptors adopted in this work used off-the-shelf deep features allowing to retain both the rich deep features and the powerful enhancement and decision provided by the proposed architecture. Experiments conducted on six public databases prove the superiority of the proposed architecture over other state-of-the-art methods.

Linear embedding by joint Robust Discriminant Analysis and Inter-class Sparsity.

Linear Discriminant Analysis (LDA) and its variants are widely used as feature extraction methods. They have been used for different classification tasks. However, these methods have some limitations that need to be overcome. The main limitation is that the projection obtained by LDA does not provide a good interpretability for the features. In this paper, we propose a novel supervised method used for multi-class classification that simultaneously performs feature selection and extraction. The targeted projection transformation focuses on the most discriminant original features, and at the same time, makes sure that the transformed features (extracted features) belonging to each class have common sparsity. Our proposed method is called Robust Discriminant Analysis with Feature Selection and Inter-class Sparsity (RDA_FSIS). The corresponding model integrates two types of sparsity. The first type is obtained by imposing the ℓ2,1 constraint on the projection matrix in order to perform feature selection. The second type of sparsity is obtained by imposing the inter-class sparsity constraint used for ensuring a common sparsity structure in each class. An orthogonal matrix is also introduced in our model in order to guarantee that the extracted features can retain the main variance of the original data and thus improve the robustness to noise. The proposed method retrieves the LDA transformation by taking into account the two types of sparsity. Various experiments are conducted on several image datasets including faces, objects and digits. The projected features are used for multi-class classification. Obtained results show that the proposed method outperforms other competing methods by learning a more compact and discriminative transformation.

Graph Convolution Networks with manifold regularization for semi-supervised learning.

In recent times, Graph Convolution Networks (GCN) have been proposed as a powerful tool for graph-based semi-supervised learning. In this paper, we introduce a model that enhances label propagation of Graph Convolution Networks (GCN). More precisely, we propose GCNs with Manifold Regularization (GCNMR). The objective function of the proposed GCNMR is composed by a supervised term and an unsupervised term. The supervised term enforces the fitting term between the predicted labels and the known labels. The unsupervised term imposes the smoothness of the predicted labels of the whole data samples. By learning a Graph Convolution Network with the proposed objective function, we are able to derive a more powerful semi-supervised learning. The proposed model retains the advantages of the classic GCN, yet it can improve it with no increase in time complexity. Experiments on three public image datasets show that the proposed model is superior to the GCN and several competing existing graph-based semi-supervised learning methods.

Joint sparse graph and flexible embedding for graph-based semi-supervised learning.

This letter introduces a framework for graph-based semi-supervised learning by estimating a flexible non-linear projection and its linear regression model. Unlike existing works, the proposed framework jointly estimates the graph structure, the non-linear projection, and the linear regression model. By adopting this joint estimation an overall optimality can be reached. A series of experiments are conducted on five image datasets in order to compare the proposed method with some state-of-art semi-supervised methods. This evaluation demonstrates the effectiveness of the proposed embedding method. These experiments show the superiority of the proposed framework over the joint estimation of the graph and soft labels.

Efficient dynamic graph construction for inductive semi-supervised learning.

Most of graph construction techniques assume a transductive setting in which the whole data collection is available at construction time. Addressing graph construction for inductive setting, in which data are coming sequentially, has received much less attention. For inductive settings, constructing the graph from scratch can be very time consuming. This paper introduces a generic framework that is able to make any graph construction method incremental. This framework yields an efficient and dynamic graph construction method that adds new samples (labeled or unlabeled) to a previously constructed graph. As a case study, we use the recently proposed Two Phase Weighted Regularized Least Square (TPWRLS) graph construction method. The paper has two main contributions. First, we use the TPWRLS coding scheme to represent new sample(s) with respect to an existing database. The representative coefficients are then used to update the graph affinity matrix. The proposed method not only appends the new samples to the graph but also updates the whole graph structure by discovering which nodes are affected by the introduction of new samples and by updating their edge weights. The second contribution of the article is the application of the proposed framework to the problem of graph-based label propagation using multiple observations for vision-based recognition tasks. Experiments on several image databases show that, without any significant loss in the accuracy of the final classification, the proposed dynamic graph construction is more efficient than the batch graph construction.

Fast and reliable active appearance model search for 3-D face tracking.

This paper addresses the three-dimensional (3-D) tracking of pose and animation of the human face in monocular image sequences using active appearance models. The major problem of the classical appearance-based adaptation is the high computational time resulting from the inclusion of a synthesis step in the iterative optimization. Whenever the dimension of the face space is large, a real-time performance cannot be achieved. In this paper, we aim at designing a fast and stable active appearance model search for 3-D face tracking. The main contribution is a search algorithm whose CPU-time is not dependent on the dimension of the face space. Using this algorithm, we show that both the CPU-time and the likelihood of a nonaccurate tracking are reduced. Experiments evaluating the effectiveness of the proposed algorithm are reported, as well as method comparison and tracking synthetic and real image sequences.

Stereo geometry from 3D ego-motion streams.

This paper addresses the problem of geometry determination of a stereo rig that undergoes general rigid motions. Neither known reference objects nor stereo correspondence are required. With almost no exception, all existing online solutions attempt to recover stereo geometry by first establishing stereo correspondences. We first describe a mathematical framework that allows us to solve for stereo geometry, i.e., the rotation and translation between the two cameras, using only motion correspondence that is far easier to acquire than stereo correspondence. Second, we show how to recover the rotation and present two linear methods, as well as a nonlinear one to solve for the translation. Third, we perform a stability study for the developed methods in the presence of image noise, camera parameter noise, and ego-motion noise. We also address accuracy issues. Experiments with real image data are presented. The work allows the concept of online calibration to be broadened, as it is no longer true that only single cameras can exploit structure-from-motion strategies; even the extrinsic parameters of a stereo rig of cameras can do so without solving stereo correspondence. The developed framework is applicable for estimating the relative three-dimensional (3D) geometry associated with a wide variety of mounted devices used in vision and robotics, by exploiting their scaled ego-motion streams.