Search

Hyperspectral unmixing is an essential research topic for spectral data analysis due to the existence of mixed pixels. Recently, many methods based on sparse nonnegative matrix factorization (NMF) have been widely used for unmixing by incorporating similarity preserving. However, most of them conduct the similarity learning and unmixing by using two separate steps, which may lead to the case that the learned similarity matrix is not the optimal one for unmixing. Thus, the performance of unmixing would be influenced and become undesirable. To alleviate this problem, we propose an adaptive relationship preserving-based sparse NMF (ARP-NMF) for hyperspectral unmixing. Typically, we regard similarity learning and unmixing as an alternative optimization process. During this process, the learned similarity weights and unmixing results can be mutually improved. Thus, our proposed method can learn the optimal similarity weights for unmixing and obtain better generalization ability for different hyperspectral images than traditional methods. Moreover, by using the spectral and spatial local structure, our ARP-NMF method effectively preserves structure consistency between pixels and abundances. Experimental results both on the synthetic data and the real data reveal that our proposed method outperforms several representative sparse NMF-based methods. [ABSTRACT FROM AUTHOR]

Hyperspectral unmixing (HU) is regarded as an indispensable preprocessing procedure for many field of spectral data analysis because of the existence of mixed pixels. However, the unmixing algorithms are implemented under the presupposition of special mixing models. In other words, any unmixing algorithm only works on a special mixing model of the spectra. This leads to low generalization performance of most unmixing algorithms. To mitigate this problem, a robust unmixing method is proposed, which exploits dual views with adaptive weights for HU (AwDvHU). The proposed method utilizes multi-kernel learning to construct a high-dimensional space that can reflect the nonlinear interaction between spectra optimally. Then, through fusing the unmixing object of original data and the mapped high-dimensional features, the AwDvHU method takes full advantage of the complementary characteristics of features in dual views. Moreover, the AwDvHU method automatically learns the weights for dual views according to the importance of different feature spaces. Its effectiveness in unmixing is verified by experimental results both on the synthetic and real data. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF) is one of the most popular data representation methods in the field of computer vision and pattern recognition. High-dimension data are usually assumed to be sampled from the submanifold embedded in the original high-dimension space. To preserve the locality geometric structure of the data, k-nearest neighbor (k-NN) graph is often constructed to encode the near-neighbor layout structure. However, k-NN graph is based on Euclidean distance, which is sensitive to noise and outliers. In this article, we propose a refined-graph regularized nonnegative matrix factorization by employing a manifold regularized least-squares regression (MRLSR) method to compute the refined graph. In particular, each sample is represented by the whole dataset regularized with ℓ2-norm and Laplacian regularizer. Then a MRLSR graph is constructed based on the representative coefficients of each sample. Moreover, we present two optimization schemes to generate refined-graphs by employing a hard-thresholding technique. We further propose two refined-graph regularized nonnegative matrix factorization methods and use them to perform image clustering. Experimental results on several image datasets reveal that they outperform 11 representative methods. [ABSTRACT FROM AUTHOR]

Nonnegative matrix factorization (NMF) is one of the most popular data representation methods in the field of computer vision and pattern recognition. High-dimension data are usually assumed to be sampled from the submanifold embedded in the original high-dimension space. To preserve the locality geometric structure of the data, k-nearest neighbor (k-NN) graph is often constructed to encode the near-neighbor layout structure. However, k-NN graph is based on Euclidean distance, which is sensitive to noise and outliers. In this article, we propose a refined-graph regularized nonnegative matrix factorization by employing a manifold regularized least-squares regression (MRLSR) method to compute the refined graph. In particular, each sample is represented by the whole dataset regularized with ℓ2-norm and Laplacian regularizer. Then a MRLSR graph is constructed based on the representative coefficients of each sample. Moreover, we present two optimization schemes to generate refined-graphs by employing a hard-thresholding technique. We further propose two refined-graph regularized nonnegative matrix factorization methods and use them to perform image clustering. Experimental results on several image datasets reveal that they outperform 11 representative methods. [ABSTRACT FROM AUTHOR]

Abstract: For image analysis, an important extension to principal component analysis (PCA) is to treat an image as multiple samples, which helps alleviate the small sample size problem. Various schemes of transforming an image to multiple samples have been proposed. Although having been shown effective in practice, the schemes are mainly based on heuristics and experience. In this paper, we propose a probabilistic PCA model, in which we explicitly represent the transformation scheme and incorporate the scheme as a stochastic component of the model. Therefore fitting the model automatically learns the transformation. Moreover, the learned model allows us to distinguish regions that can be well described by the PCA model from those that need further treatment. Experiments on synthetic images and face data sets demonstrate the properties and utility of the proposed model. [Copyright &y& Elsevier]

Prior to pattern recognition, feature selection is often used to identify relevant features and discard irrelevant ones for obtaining improved analysis results. In this paper, we aim to develop an unsupervised feature ranking algorithm that evaluates features using discovered local coherent patterns, which are known as biclusters. The biclusters (viewed as submatrices) are discovered from a data matrix. These submatrices are used for scoring relevant features from two aspects, i.e., the interdependence of features and the separability of instances. The features are thereby ranked with respect to their accumulated scores from the total discovered biclusters before the pattern classification. Experimental results show that this proposed method can yield comparable or even better performance in comparison with the well-known Fisher score, Laplacian score, and variance score using three UCI data sets, well improve the results of gene expression data analysis using gene ontology annotation, and finally demonstrate its advantage of unsupervised feature ranking for high-dimensional data. [ABSTRACT FROM AUTHOR]

Low Rank Regularization (LRR), in essence, involves introducing a low rank or approximately low rank assumption to target we aim to learn, which has achieved great success in many data analysis tasks. Over the last decade, much progress has been made in theories and applications. Nevertheless, the intersection between these two lines is rare. In order to construct a bridge between practical applications and theoretical studies, in this paper we provide a comprehensive survey for LRR. Specifically, we first review the recent advances in two issues that all LRR models are faced with: (1) rank-norm relaxation, which seeks to find a relaxation to replace the rank minimization problem; (2) model optimization, which seeks to use an efficient optimization algorithm to solve the relaxed LRR models. For the first issue, we provide a detailed summarization for various relaxation functions and conclude that the non-convex relaxations can alleviate the punishment bias problem compared with the convex relaxations. For the second issue, we summarize the representative optimization algorithms used in previous studies, and analyze their advantages and disadvantages. As the main goal of this paper is to promote the application of non-convex relaxations, we conduct extensive experiments to compare different relaxation functions. The experimental results demonstrate that the non-convex relaxations generally provide a large advantage over the convex relaxations. Such a result is inspiring for further improving the performance of existing LRR models. [ABSTRACT FROM AUTHOR]

As one of the most widely used clustering techniques, the fuzzy $k$ -means (FKM) assigns every data point to each cluster with a certain degree of membership. However, conventional FKM approach relies on the square data fitting term, which is sensitive to the outliers with ignoring the prior information. In this paper, we develop a novel and robust fuzzy $k$ -means clustering algorithm, namely, joint learning of fuzzy $k$ -means and nonnegative spectral clustering with side information. The proposed method combines fuzzy $k$ -means and nonnegative spectral clustering into a unified model, which can further exploit the prior knowledge of data pairs such that both the quality of affinity graph and the clustering performance can be improved. In addition, for the purpose of enhancing the robustness, the adaptive loss function is adopted in the objective function, since it smoothly interpolates between $\ell _{1}$ -norm and $\ell _{2}$ -norm. Finally, experimental results on benchmark datasets verify the effectiveness and the superiority of our clustering method. [ABSTRACT FROM AUTHOR]

Sufficient training examples are the fundamental requirement for most of the learning tasks. However, collecting well-labelled training examples is costly. Inspired by Zero-shot Learning (ZSL) that can make use of visual attributes or natural language semantics as an intermediate level clue to associate low-level features with high-level classes, in a novel extension of this idea, we aim to synthesise training data for novel classes using only semantic attributes. Despite the simplicity of this idea, there are several challenges. First, how to prevent the synthesised data from over-fitting to training classes? Second, how to guarantee the synthesised data is discriminative for ZSL tasks? Third, we observe that only a few dimensions of the learnt features gain high variances whereas most of the remaining dimensions are not informative. Thus, the question is how to make the concentrated information diffuse to most of the dimensions of synthesised data. To address the above issues, we propose a novel embedding algorithm named Unseen Visual Data Synthesis (UVDS) that projects semantic features to the high-dimensional visual feature space. Two main techniques are introduced in our proposed algorithm. (1) We introduce a latent embedding space which aims to reconcile the structural difference between the visual and semantic spaces, meanwhile preserve the local structure. (2) We propose a novel Diffusion Regularisation (DR) that explicitly forces the variances to diffuse over most dimensions of the synthesised data. By an orthogonal rotation (more precisely, an orthogonal transformation), DR can remove the redundant correlated attributes and further alleviate the over-fitting problem. On four benchmark datasets, we demonstrate the benefit of using synthesised unseen data for zero-shot learning. Extensive experimental results suggest that our proposed approach significantly outperforms the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The TV experience is being transformed with online social networks. TV audiences are sharing their opinions (i.e., social response) about video programs on OSNs (e.g., Twitter and Sina Weibo), thus providing a great opportunity for mining these data for stakeholders in TV value chains. This new paradigm is touted as social TV analytics, integrating the emerging big data research into TV. In this article, we envision and develop a unified big data platform for social TV analytics, extracting valuable insights from TV social response in a real-time manner. Such a platform presents tremendous challenges in networking architecture for our big data platform. We propose to build a cloud-centric platform with SDN support, providing on-demand virtual machines and reconfigurable networks. The architecture of our system consists of three key components, including a robust data crawler system, an SDN-enabled big data processing system, and a social media analytics system. The data crawler system adopts a distributed architecture to circumvent the access constraints of OSNs to crawl sufficient data about each TV program of interest; the SDN-enabled big data processing system integrates SDN and Hadoop, and exploits the SDN benefit to transfer intermediate data between different processing units to accelerate the data processing rate; and the social media analytics system extracts the public perception and knowledge related to TV programs based on microblog data. We have built a proof-of-concept demo over a private cloud at Nanyang Technological University. Feature verification and performance comparisons demonstrate the feasibility and effectiveness of the system. [ABSTRACT FROM PUBLISHER]

Realistic action recognition has been one of the most challenging research topics in computer vision. The existing methods are commonly based on non-probabilistic classification, predicting category labels but not providing an estimation of uncertainty. In this paper, we propose a probabilistic framework using Gaussian processes (GPs), which can tackle regression problems with explicit uncertain models, for action recognition. A major challenge for GPs when applied to large-scale realistic data is that a large covariance matrix needs to be inverted during inference. Additionally, from the manifold perspective, the intrinsic structure of the data space is only constrained by a local neighborhood and data relationships with far-distance usually can be ignored. Thus, we design our GPs covariance matrix via the proposed ℓ 1 construction and a local approximation (LA) covariance weight updating method, which are demonstrated to be robust to data noise, automatically sparse and adaptive to the neighborhood. Extensive experiments on four realistic datasets, i.e., UCF YouTube, UCF Sports, Hollywood2 and HMDB51, show the competitive results of ℓ 1 -GPs compared with state-of-the-art methods on action recognition tasks. [ABSTRACT FROM AUTHOR]