where A represents the magnetic vector potential, is an integral of the hydromagnetic equations. This -integral made it possible to formulate a variational principle for the force-free magnetic fields. The integral expresses the fact that motions cannot transform a given field in an entirely arbitrary different field, if the conductivity of the medium isconsidered infinite. In this paper we shall show that the full set of hydromagnetic equations admit five more integrals, besides the energy integral, if dissipative processes are absent. These integrals, as we shall presently verify, are I2 =fbHvdV, (2)

Proceedings of the National Academy of Sciences

Submission information at the series homepage and springer.com/authors Order online at springer.com ▶ or for the Americas call (toll free) 1-800-SPRINGER ▶ or email us at: customerservice@springer.com. ▶ For outside the Americas call +49 (0) 6221-345-4301 ▶ or email us at: customerservice@springer.com. Statistics and Computing Series Ed.: W.K. Härdle Statistics and Computing (SC) includes monographs and advanced texts on statistical computing and statistical packages.

Statistics and Computing

An important underlying assumption that guides the success of the existing multiview learning algorithms is the full observation of the multiview data. However, such rigorous precondition clearly violates the common-sense knowledge in practical applications, where in most cases, only incomplete fractions of the multiview data are given. The presence of the incomplete settings generally disables the conventional multiview clustering methods. In this article, we propose a simple but effective incomplete multiview clustering (IMC) framework, which simultaneously considers the local geometric information and the unbalanced discriminating powers of these incomplete multiview observations. Specifically, a novel graph-regularized matrix factorization model, on the one hand, is developed to preserve the local geometric similarities of the learned common representations from different views. On the other hand, the semantic consistency constraint is introduced to stimulate these view-specific representations toward a unified discriminative representation. Moreover, the importance of different views is adaptively determined to reduce the negative influence of the unbalanced incomplete views. Furthermore, an efficient learning algorithm is proposed to solve the resulting optimization problem. Extensive experimental results performed on several incomplete multiview datasets demonstrate that the proposed method can achieve superior clustering performance in comparison with some state-of-the-art multiview learning methods.

Generalized Incomplete Multiview Clustering With Flexible Locality Structure Diffusion

In recent years, unsupervised feature learning based on a neural network architecture has become a hot new topic for research [1]-[4]. The revival of interest in such deep networks can be attributed to the development of efficient optimization skills, by which the model parameters can be optimally estimated [5]. The milestone work done by Hinton and Salakhutdinov [6] proposes to initialize the weights that allow deep autoencoder networks to learn lowdimensional codes. The encoding trick introduced works much better than principal component analysis (PCA) in terms of dimension reduction.

A Review of the Autoencoder and Its Variants: A Comparative Perspective from Target Recognition in Synthetic-Aperture Radar Images

In this paper, we focus on fine-grained recognition of vehicles mainly in traffic surveillance applications. We propose an approach that is orthogonal to recent advancements in fine-grained recognition (automatic part discovery and bilinear pooling). In addition, in contrast to other methods focused on fine-grained recognition of vehicles, we do not limit ourselves to a frontal/rear viewpoint, but allow the vehicles to be seen from any viewpoint. Our approach is based on 3-D bounding boxes built around the vehicles. The bounding box can be automatically constructed from traffic surveillance data. For scenarios where it is not possible to use precise construction, we propose a method for an estimation of the 3-D bounding box. The 3-D bounding box is used to normalize the image viewpoint by “unpacking” the image into a plane. We also propose to randomly alter the color of the image and add a rectangle with random noise to a random position in the image during the training of convolutional neural networks (CNNs). We have collected a large fine-grained vehicle data set BoxCars116k, with 116k images of vehicles from various viewpoints taken by numerous surveillance cameras. We performed a number of experiments, which show that our proposed method significantly improves CNN classification accuracy (the accuracy is increased by up to 12% points and the error is reduced by up to 50% compared with CNNs without the proposed modifications). We also show that our method outperforms the state-of-the-art methods for fine-grained recognition.

BoxCars: Improving Fine-Grained Recognition of Vehicles Using 3-D Bounding Boxes in Traffic Surveillance

Facial attribute analysis has received considerable attention when deep learning techniques made remarkable breakthroughs in this field over the past few years. Deep learning based facial attribute analysis consists of two basic sub-issues: facial attribute estimation (FAE), which recognizes whether facial attributes are present in given images, and facial attribute manipulation (FAM), which synthesizes or removes desired facial attributes. In this paper, we provide a comprehensive survey of deep facial attribute analysis from the perspectives of both estimation and manipulation. First, we summarize a general pipeline that deep facial attribute analysis follows, which comprises two stages: data preprocessing and model construction. Additionally, we introduce the underlying theories of this two-stage pipeline for both FAE and FAM. Second, the datasets and performance metrics commonly used in facial attribute analysis are presented. Third, we create a taxonomy of state-of-the-art methods and review deep FAE and FAM algorithms in detail. Furthermore, several additional facial attribute related issues are introduced, as well as relevant real-world applications. Finally, we discuss possible challenges and promising future research directions.

A Survey of Deep Facial Attribute Analysis

Considering that traditional image steganography technologies suffer from the potential risk of failure under lossy channels, an enhanced adaptive steganography with multiple robustness against image processing attacks is proposed, while maintaining good detection resistance. First, a robust domain constructing method is proposed utilizing robust element extraction and optimal element modification, which can be applied to both spatial and JPEG images. Then, a robust steganography is proposed based on “Robust Domain Constructing + RS-STC Codes,” combined with cover selection, robust cover extraction, message coding, and embedding with minimized costs. In addition, to provide a theoretical basis for message extraction integrity, the fault tolerance of the proposed algorithm is deduced using error model based on burst errors and decoding damage. Finally, on the basis of parameter discussion about robust domain construction, performance experiments are conducted, and the recommended coding parameters are given for lossy channels with different attacks using the analytic results for fault tolerance. A series of experimental results demonstrate that the proposed algorithm can extract embedded messages with significantly higher accuracy after different attacks, such as compression, noising, scaling and other attacks, compared with the state-of-the-art adaptive steganography, and robust watermarking algorithms, while maintaining good detection resistant performance.

Multiple Robustness Enhancements for Image Adaptive Steganography in Lossy Channels

For many real-world multimedia applications, data are often described by multiple views. Therefore, multi-view learning researches are of great significance. Traditional multi-view clustering methods assume that each view has complete data. However, missing data or partial data are more common in real tasks, which results in partial multi-view learning. Therefore, we propose a novel multi-view clustering method, called Partial Multi-view Subspace Clustering (PMSC), to address the partial multi-view problem. Unlike most existing partial multi-view clustering methods that only learn a new representation of the original data, our method seeks the latent space and performs data reconstruction simultaneously to learn the subspace representation. The learned subspace representation can reveal the underlying subspace structure embedded in original data, leading to a more comprehensive data description. In addition, we enforce the subspace representation to be non-negative, yielding an intuitive weight interpretation among different data. The proposed method can be optimized by the Augmented Lagrange Multiplier (ALM) algorithm. Experiments on one synthetic dataset and four benchmark datasets validate the effectiveness of PMSC under the partial multi-view scenario.

Partial Multi-view Subspace Clustering

Synthesis linear classifier based analysis dictionary learning for pattern classification

Dictionary learning (DL) plays an important role in pattern classification. However, learning a discriminative dictionary has not been well addressed in analysis dictionary learning (ADL). This letter proposes a Class-aware Analysis Dictionary Learning (CADL) model to improve the classification performance of conventional ADL. The objective function of CADL mainly includes two parts to promote the discriminability. The first part aims to learn a discriminative analysis subdictionary for each class instead of a global dictionary for all classes. The learned analysis dictionary is class-aware, generating a block-diagonal coding coefficient matrix. The second part aims to enhance the discrimination of coding coefficients by integrating a max-margin regularization term into our proposed framework. This term ensures the coefficients of different classes to be separated by a max-margin, which boosts the confidence of classification. A theoretical analysis is also given to support the max-margin regularization term from the perspective of preserving the pairwise relations of samples in coding space. We employ an alternating minimization algorithm to iteratively find the convergent solution. By evaluating our method on four pattern classification datasets, we demonstrate the superiority of our CADL method to the state-of-the-art DL methods.

Yanqing Guo

Papers

A Survey of Deep Facial Attribute Analysis

Multiple Robustness Enhancements for Image Adaptive Steganography in Lossy Channels

Partial Multi-view Subspace Clustering

Synthesis linear classifier based analysis dictionary learning for pattern classification

Class-Aware Analysis Dictionary Learning for Pattern Classification