Search

Causal discovery reveals the true causal relationships behind data and discovering causal relationships from observed data is a particularly challenging problem, especially in large-scale datasets. The functional causal model is an effective method for causal discovery, but its time efficiency cannot be guaranteed. How to efficiently apply it to massive data still needs to be solved. In this paper, we propose a coreset construction for the additive noise model to accelerate causal discovery. According to the asymmetry characteristic of causality, samples were assigned different weights to construct the coreset. With the constructed coreset, we propose a Fast causal discovery algorithm based on the Additive Noise Model (FANM) to improve the time efficiency of the functional causal model while ensuring the result performance of causal discovery. Experiments on synthetic data and real-world data show that our proposed algorithm is much more time-efficient than the methods based on the functional causal model, and the runtime of FANM remains consistent as sample size increases while maintaining or exceeding the accuracy of the original nonlinear additive noise model. • New coresets proposed for the additive noise model greatly reduces the data size for causal discovery. • A time-efficient algorithm, FANM, is proposed for causal discovery based on the coresets. • The coreset construction is applied to causal graph learning algorithm, CDCSG, to show its effectiveness. • The proposed FANM is verified by both synthetic data and real-world data. [ABSTRACT FROM AUTHOR]

Deep learning techniques have made significant advancements in reference-based colorization by training on large-scale datasets. However, directly applying these methods to the task of colorizing old photos is challenging due to the lack of ground truth and the notorious domain gap between natural gray images and old photos. To address this issue, we propose a novel CNN-based algorithm called SFAC, i. e., S tructure-preserving F eature A lignment C olorizer. SFAC is trained on only two images for old photo colorization, eliminating the reliance on big data and allowing direct processing of the old photo itself to overcome the domain gap problem. Our primary objective is to establish semantic correspondence between the two images, ensuring that semantically related objects have similar colors. We achieve this through a feature distribution alignment loss that remains robust to different metric choices. However, utilizing robust semantic correspondence to transfer color from the reference to the old photo can result in inevitable structure distortions. To mitigate this, we introduce a structure-preserving mechanism that incorporates a perceptual constraint at the feature level and a frozen-updated pyramid at the pixel level. Extensive experiments demonstrate the effectiveness of our method for old photo colorization, as confirmed by qualitative and quantitative metrics. • This paper proposes SFAC to address reference-based old photo colorization on only two images. • Our SFAC progressively integrates FDA for color transfer and SPM for content preservation. • Extensive experiments demonstrate the effectiveness and superiority of our method. [ABSTRACT FROM AUTHOR]

• The paper proposes a novel and efficient network framework dedicated to unseen congestion detection. • An adaptive context module similar to valve control is proposed to obtain contextual information that balances foreground and background features. • The paper demonstrates that balanced features on multi-level network prediction maps have a prevailing impact on the accuracy of object detection. • Accurate detection results are realized through the proposed anti-congestion model for flexible regional mapping. Object detection is advancing rapidly with the development of deep learning solutions and big data dimensions. This paper takes the challenging recognition task as the core work and proposes a novel and efficient network framework dedicated to unseen congestion detection. To guarantee the accuracy as well as the speed of inference, the detector utilizes the advanced You Only Look Once v4 (YOLOv4) as the backbone and agglutinates the four proposed strategies, called YOLO-Anti. Our model mainly consists of three modules: First, an adaptive context module similar to valve control is proposed to obtain contextual information that balances foreground and background features. Second, to solve the problem that the imbalance between feature levels weakens the detection performance, a balanced prediction layer method is developed. Finally, we propose an anti-congestion network to selectively expand the local domain to achieve finer-grained detection. Besides, in the training procedure, a designed heterogeneous cross-entropy loss is utilized to strengthen the detector's discrimination of similar targets in different categories. Extensive experiments were conducted on the PASCAL VOC, COCO, and UA-DETRAC data sets. The state-of-the-art results were achieved on UA-DETRAC and the leading performance on PASCAL VOC and COCO. Also, compared with baseline YOLOv4, the proposed method brings significant accuracy improvement and negligible time consumption. [ABSTRACT FROM AUTHOR]

In this paper, a novel robust one-class support vector machine (OCSVM) based on the rescaled hinge loss function is proposed to enhance the robustness of the conventional OCSVM against outliers. The optimization problem of the proposed robust OCSVM can be iteratively solved by the half-quadratic optimization technique. Compared to OCSVM, robust OCSVM may achieve higher generalization performance from the theoretical analysis. Moreover, the robustness of robust OCSVM against outliers is explained from the weighted viewpoint. Experimental results on the synthetic and benchmark data sets demonstrate that the proposed robust OCSVM is superior to the conventional OCSVM and the other two related approaches. [ABSTRACT FROM AUTHOR]

Relief-like algorithms have been widely used as feature selection to reduce the dimension of high-dimensional data which involves thousands of irrelevant variables because of their low computational cost and high accuracy. Classical Relief algorithms have not exactly shown the dynamic procedure that updates weight iteratively. This paper proposes an innovative feature weight estimation method, called dynamic representation and neighbor sparse reconstruction-based Relief (DRNSR-Relief). Similar to the classical Relief algorithms, the goal of DRNSR-Relief is to maximize the expected margin in the weighted feature space. A dynamic representation framework is introduced to show the dynamic relationship between the expected margin vector and the weight vector. To achieve better neighbor reconstruction, DRNSR-Relief decomposes a nonlinear problem into a set of locally linear ones through local hyperplane with l 1 regularization and then estimates feature weights in a large margin framework. With the help of gradient ascent method, we can guarantee the convergence of DRNSR-Relief. To demonstrate the validity and the effectiveness of our formulation for feature selection in supervised learning, we perform extensive experiments on synthetic and real-world datasets. Experimental results indicate that DRNSR-Relief is very promising. [ABSTRACT FROM AUTHOR]

Distance metric learning has motivated a great deal of research over the last years due to its robustness for many pattern recognition problems. In this paper, we develop a supervised distance metric learning method that aims to improve the performance of nearest-neighbor classification. Our method is inspired by the large-margin principle, resulting in an objective function based on a sum of margin violations to be minimized. Due to the use of the ramp loss function, the corresponding objective function is nonconvex, making it more challenging. To overcome this limitation, we formulate our distance metric learning problem as an instance of difference of convex functions (DC) programming. This allows us to design a more robust method than when using standard optimization techniques. The effectiveness of this method is empirically demonstrated through extensive experiments on several standard benchmark data sets. [ABSTRACT FROM AUTHOR]

• A novel k -means clustering algorithm based on Lévy flight trajectory (Lk-means) is proposed. • The defects of Xk-means clustering algorithm are analyzed. • Experiments are conducted to compare it with the baseline model on 10 open source data sets. Tradition K -means clustering algorithm is easy to fall into local optimum, poor clustering effect on large capacity data and uneven distribution of clustering centroids. To solve these problems, a novel k -means clustering algorithm based on Lévy flight trajectory (Lk-means) is proposed in the paper. In the iterative process of LK-means algorithm, Lévy flight is used to search new positions to avoid premature convergence in clustering. It is also applied to increase the diversity of the cluster, strengthen the global search ability of K -means algorithm, and avoid falling into the local optimal value too early. Nevertheless, the complexity of hybrid algorithm is not increased in the process of Lévy flight optimization. To verify the data clustering effect of LK-means algorithm, experiments are conducted to compare it with the k -means algorithm, XK-means algorithm, DDKmeans algorithm and Canopyk-means algorithm on 10 open source data sets. The results show that LK-means algorithm has better search results and more evenly distributed cluster centroids, which greatly improves the global search ability, big data processing ability and uneven distribution centroids of cluster of K -means algorithm. [ABSTRACT FROM AUTHOR]

In this paper, a new random subspace based ensemble sparse representation (RS_ESR) algorithm is proposed, where the random subspace is introduced into sparse representation model. For high-dimensional data, the random subspace method can not only reduce dimension of data but also make full use of effective information of data. It is not like traditional dimensionality reduction methods that may lose some information of original data. Additionally, a joint sparse representation model is emloyed to obtain the sparse representation of a sample set in the low dimensional random subspace. Then the sparse representations in multiple random subspaces are integrated as an ensemble sparse representation. Moreover, the obtained RS_ESR is applied in classical clustering and semi-supervised classification. The experimental results on different real-world data sets show the superiority of RS_ESR over traditional methods. [ABSTRACT FROM AUTHOR]

Extreme Learning Machine (ELM) is a popular machine learning method which can flexibly simulate the relationships of real-world classification applications. When facing problems ( i.e. , data sets) with a smaller number of samples ( i.e. , instances), ELM may often result in the overfitting trouble. In this paper, we propose a new Instance Cloned Extreme Learning Machine (IC-ELM for short) which can handle numerous different classification problems. IC-ELM uses an instance cloning method to balance the input data’s distribution and extend the training data set, which alleviates the overfitting issue and enhances the testing classification accuracy. Experiments and comparisons on 20 UCI data sets, and validations on image and text classification applications, demonstrate that IC-ELM is able to achieve superior results compared to the original ELM algorithm and its variants, as well as several other classical machine learning algorithms. [ABSTRACT FROM AUTHOR]

In this paper, a novel approach is developed to learn a tree of multi-task sparse metrics hierarchically over a visual tree to achieve a fast solution to large-scale image classification, where an enhanced visual tree is first learned to organize large numbers of image categories hierarchically in a coarse-to-fine fashion. Over the visual tree, a tree of multi-task sparse metrics is learned hierarchically by: (a) performing multi-task sparse metric learning over the sibling child nodes under the same parent node to explicitly separate their commonly-shared metric from their node-specific metrics; and (b) propagating the node-specific metric for the parent node to its sibling child nodes (at the next level of the visual tree), so that more discriminative metrics can be learned for controlling inter-level error propagation effectively. We have evaluated our hierarchical multi-task sparse metric learning algorithm over three different image sets and the experimental results demonstrated that our hierarchical multi-task sparse metric learning algorithm can obtain better performance than the state-of-the-art algorithms on large-scale image classification. [ABSTRACT FROM AUTHOR]

Multi-label feature selection involves the selection of relevant features from multi-labeled datasets, resulting in a potential improvement of multi-label learning accuracy. In conventional multi-label feature selection methods, the final feature subset is obtained by identifying the features of high relevance with low redundancy. Thus, accurate score evaluation is a key factor for obtaining an effective feature subset. However, conventional methods suffer from inaccurate conditional relevance evaluation when a large number of labels are involved. As a result, irrelevant features can be a member of the final feature subset, leading to low multi-label learning accuracy. In this paper, we propose a new multi-label feature selection method. Using a scalable relevance evaluation process that evaluates conditional relevance more accurately, the proposed method significantly improves multi-label learning accuracy compared with conventional multi-label feature selection methods. [ABSTRACT FROM AUTHOR]

Unsupervised feature selection (UFS) aims to reduce the time complexity and storage burden, improve the generalization ability of learning machines by removing the redundant, irrelevant and noisy features. Due to the lack of training labels, most existing UFS methods generate the pseudo labels by spectral clustering, matrix factorization or dictionary learning, and convert UFS to a supervised problem. The learned clustering labels reflect the data distribution with respect to classes and therefore are vital to the UFS performance. In this paper, we proposed a novel subspace clustering guided unsupervised feature selection (SCUFS) method. The clustering labels of the training samples are learned by representation based subspace clustering, and features that can well preserve the cluster labels are selected. SCUFS can well learn the data distribution in that it uncovers the underlying multi-subspace structure of the data and iteratively learns the similarity matrix and clustering labels. Experimental results on benchmark datasets for unsupervised feature selection show that SCUFS outperforms the state-of-the-art UFS methods. [ABSTRACT FROM AUTHOR]

Due to the short duration and low intensity of micro-expressions, the recognition of micro-expression is still a challenging problem. In this paper, we develop a novel multi-task mid-level feature learning method to enhance the discrimination ability of extracted low-level features by learning a set of class-specific feature mappings, which would be used for generating our mid-level feature representation. Moreover, two weighting schemes are employed to concatenate different mid-level features. We also construct a new mobile micro-expression set to evaluate the performance of the proposed mid-level feature learning framework. The experimental results on two widely used non-mobile micro-expression datasets and one mobile micro-expression set demonstrate that the proposed method can generally improve the performance of the low-level features, and achieve comparable results with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Several dimensionality reduction methods based on the max-min idea have been proposed in recent years and can obtain good classification performance. In this paper, inspired by the idea, we develop max-min linear discriminant analysis (MMLDA), which maximizes the minimum ratio of each two-class scatter measure to the within-class scatter measure. However, the method ignores equal emphasis on the distances between class centers and there may be room to improve the classification performance. We then propose regularized max-min linear discriminant analysis (RMMLDA), which introduces the Shannon entropy and the corresponding distance difference regularization terms based on MMLDA. The changing trends of distances between class centers can be precisely controlled in optimization and the separation between classes can be emphasized approximately equally. As a result, RMMLDA may obtain better classification performance. Experiments on synthetic data sets and three publicly available data sets demonstrate its effectiveness. [ABSTRACT FROM AUTHOR]

In this paper, we propose an efficient method for salient region detection. First, the image is decomposed by using superpixel segmentation which groups similar pixels and generates compact regions. Based upon the generated superpixels, similarity between the regions is calculated by benefiting from color, location, histogram, intensity, and area information of each region as well as community identification via complex networks theory in the over-segmented image. Then, contrast, distribution and complex networks based saliency maps are generated by using the mentioned features. These saliency maps are used to create a final saliency map. The applicability, effectiveness and consistency of the proposed approach are illustrated by conducting some experiments using publicly available datasets. The tests have been used to compare the proposed method with some state-of-the-art methods. The reported results cover qualitative and quantitative assessments which demonstrate that our approach outputs high quality saliency maps and mostly achieves the highest precision rate compared to the other methods. [ABSTRACT FROM AUTHOR]

A popular procedure for identifying which one of two classification algorithms has a better performance is to test them on multiple data sets, and the accuracies resulting from k-fold cross validation are aggregated to draw a conclusion. Several nonparametric methods have been proposed for this purpose, while parametric methods will be a better choice to determine the superior algorithm when the assumptions for deriving sampling distributions can be satisfied. In this paper, we consider every accuracy estimate resulting from the instances in a fold or a data set as a point estimator instead of a fixed value to derive the sampling distribution of the point estimator for comparing the performance of two classification algorithms. The test statistics for both data-set and fold averaging levels are proposed, and the ways to calculate their degrees of freedom are also presented. Twelve data sets are chosen to demonstrate that our parametric methods can be used to effectively compare the performance of two classification algorithms on multiple data sets. Several critical issues in using our parametric methods and the nonparametric ones proposed in a previous study are then discussed. [ABSTRACT FROM AUTHOR]

Nonlinear methods such as Deep Neural Networks (DNNs) are the gold standard for various challenging machine learning problems such as image recognition. Although these methods perform impressively well, they have a significant disadvantage, the lack of transparency, limiting the interpretability of the solution and thus the scope of application in practice. Especially DNNs act as black boxes due to their multilayer nonlinear structure. In this paper we introduce a novel methodology for interpreting generic multilayer neural networks by decomposing the network classification decision into contributions of its input elements. Although our focus is on image classification, the method is applicable to a broad set of input data, learning tasks and network architectures. Our method called deep Taylor decomposition efficiently utilizes the structure of the network by backpropagating the explanations from the output to the input layer. We evaluate the proposed method empirically on the MNIST and ILSVRC data sets. [ABSTRACT FROM AUTHOR]

Dissimilarity space embedding (DSE) presents a method of representing data as vectors of dissimilarities. This representation is interesting for its ability to use a dissimilarity measure to embed various patterns (e.g. graph patterns with different topology and temporal patterns with different lengths) into a vector space. The method proposed in this paper uses a dynamic time warping (DTW) based DSE for the purpose of the classification of massive sets of temporal patterns. However, using large data sets introduces the problem of requiring a high computational cost. To address this, we consider a prototype selection approach. A vector space created by DSE offers us the ability to treat its independent dimensions as features allowing for the use of feature selection. The proposed method exploits this and reduces the number of prototypes required for accurate classification. To validate the proposed method we use two-class classification on a data set of handwritten on-line numerical digits. We show that by using DSE with ensemble classification, high accuracy classification is possible with very few prototypes. [ABSTRACT FROM AUTHOR]

Kernel Fisher discriminant analysis (KFDA) is a very popular learning method for the purpose of classification. In this paper, we propose a novel learning algorithm to improve KFDA and make it very suitable for dealing with the large-scale and high-dimensional data sets. The proposed algorithm is termed individualized KFDA (IKFDA). IKFDA is based on individualized learning , i.e., a strategy to learn and classify the individual test samples one by one. Our approach seeks to find the appropriate training subset, referred to as learning area , for each individual test sample, and then employ the learning area to construct the KFDA model for the test sample. For each individual test sample, IKFDA exploits some types of similarity measures to determine a learning area that consists of the training samples that are most similar to the test sample. Compared with the traditional learning algorithms that often exploit the whole training set to construct the learning models without considering the distribution property of the test samples, IKFDA can adaptively learn the individual test samples. It is a powerful tool to deal with the real-world complicated data sets that are often very large-scale and high-dimensional, and are usually drawn from the different distributions. Extensive experiments show that the proposed algorithm can obtain good classification results. [ABSTRACT FROM AUTHOR]

Canonical machine learning algorithms assume that the number of objects in the considered classes are roughly similar. However, in many real-life situations the distribution of examples is skewed since the examples of some of the classes appear much more frequently. This poses a difficulty to learning algorithms, as they will be biased towards the majority classes. In recent years many solutions have been proposed to tackle imbalanced classification, yet they mainly concentrate on binary scenarios. Multi-class imbalanced problems are far more difficult as the relationships between the classes are no longer straightforward. Additionally, one should analyze not only the imbalance ratio but also the characteristics of the objects within each class. In this paper we present a study on oversampling for multi-class imbalanced datasets that focuses on the analysis of the class characteristics. We detect subsets of specific examples in each class and fix the oversampling for each of them independently. Thus, we are able to use information about the class structure and boost the more difficult and important objects. We carry an extensive experimental analysis, which is backed-up with statistical analysis, in order to check when the preprocessing of some types of examples within a class may improve the indiscriminate preprocessing of all the examples in all the classes. The results obtained show that oversampling concrete types of examples may lead to a significant improvement over standard multi-class preprocessing that do not consider the importance of example types. [ABSTRACT FROM AUTHOR]

This paper presents an online frame-based clustering algorithm (OFC) for unsupervised classification applications in which data are received in a streaming manner as time passes by with the number of clusters being unknown. This algorithm consists of a number of steps including density-based outlier removal, new cluster generation, and cluster update. It is designed for applications when data samples are received in an online manner in frames. Such frames are first passed through an outlier removal step to generate denoised frames with consistent data samples during transitions times between clusters. A classification step is then applied to find whether frames belong to any of existing clusters. When frames do not get matched to any of existing clusters and certain criteria are met, a new cluster is created in real time and in an on-the-fly manner by using support vector domain descriptors. Experiments involving four synthetic and two real datasets are conducted to show the performance of the introduced clustering algorithm in terms of cluster purity and normalized mutual information. Comparison results with similar clustering algorithms designed for streaming data are also reported exhibiting the effectiveness of the introduced online frame-based clustering algorithm. [ABSTRACT FROM AUTHOR]

An unsupervised learning algorithm with density information considered is proposed for congested scene classification. Though many works have been proposed to address general scene classification during the past years, congested scene classification is not adequately studied yet. In this paper, an efficient unsupervised feature learning approach with density information encoded is proposed to solve this problem. Based on spherical k -means, a feature selection process is proposed to eliminate the learned noisy features. Then, local density information which better reflects the crowdedness of a scene is encoded by a novel feature pooling strategy. The proposed method is evaluated on the assembled congested scene data set and UIUC-sports data set, and intensive comparative experiments justify the effectiveness of the proposed approach. [ABSTRACT FROM AUTHOR]

The problem we address in this paper is how to learn joint representation from data lying on multiple manifolds. We are given multiple data sets, and there is an underlying common manifold among the different data sets. Each data set is considered to be an instance of this common manifold. The goal is to achieve an embedding of all the points on all the manifolds in a way that preserves the local structure of each manifold and that, at the same time, collapses all the different manifolds into one manifold in the embedding space while preserving the implicit correspondences between the points across different data sets. We propose a framework to learn embedding of such data, which can preserve the intra-manifolds' local geometric structure and the inter-manifolds' correspondence structure. The proposed solution works as extensions to current state-of-the-art spectral-embedding approaches to handling multiple manifolds. [ABSTRACT FROM AUTHOR]

The large-scale images and videos are one kind of the main source of big data. Dynamic texture (DT) is essential for understanding the video sequences with spatio-temporal similarities. This paper presents a powerful tool called dynamic fractal analysis to DT description and classification, which integrates rich description of DT with strong robustness to environmental changes. The proposed dynamic fractal spectrum (DFS) for DT sequences is composed of two components. The first one is a volumetric dynamic fractal spectrum component (V-DFS) that captures the stochastic self-similarities of DT sequences by treating them as 3D volumes; the second one is a multi-slice dynamic fractal spectrum component (S-DFS) that encodes fractal structures of repetitive DT patterns on 2D slices along different views of the 3D volume. To fully exploit various types of dynamic patterns in DT, five measurements of DT pixels are collected for the analysis on DT sequences from different perspectives. We evaluated our method on four publicly available benchmark datasets. All the experimental results have demonstrated the excellent performance of our method in comparison with state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

In this paper, a new clustering algorithm, neutrosophic c -means (NCM), is introduced for uncertain data clustering, which is inspired from fuzzy c -means and the neutrosophic set framework. To derive such a structure, a novel suitable objective function is defined and minimized, and the clustering problem is formulated as a constrained minimization problem, whose solution depends on the objective function. In the objective function, two new types of rejection have been introduced: the ambiguity rejection which concerns the patterns lying near the cluster boundaries, and the distance rejection dealing with patterns that are far away from all the clusters. These measures are able to manage uncertainty due to imprecise and/or incomplete definition of the clusters. We conducted several experiments with synthetic and real data sets. The results are encouraging and compared favorably with results from other methods as FCM, PCM and FPCM algorithms on the same data sets. Finally, the proposed method was applied into image segmentation algorithm. The experimental results show that the proposed algorithm can be considered as a promising tool for data clustering and image processing. [ABSTRACT FROM AUTHOR]

• Take probabilistic prediction of BN as knowledge reasoning (case retrieval) method. • Propose probability calculation based feature selection method—WRPCSP algorithm. • Propose GO algorithm to assign the computing task of big data. Under big data, large number of features as well as their complex data types makes traditional feature selection and knowledge reasoning in CBR system not adapt to new condition. To solve these problems, first, this paper proposes Weighted Relative Probability Change of Solution Parameters (WRPCSP) algorithm to execute feature selection. Then, this paper integrates Bayesian network (BN) with CBR system for knowledge reasoning. Based on probability calculation and reasoning, WRPCSP algorithm together with BN allows the proposed CBR system to well work under big data. In addition, to overcome the efficiency problem caused by large number of features, this paper also proposes Group-Outside (GO) algorithm to assign the computing task of big data for parallel data processing. GO algorithm can make the computing capacity of Hadoop fully utilized to gain the least time costing for parallel data processing. Finally, lots of experiments are performed to validate the proposed method. [ABSTRACT FROM AUTHOR]

Feature selection is an important part of classifier design. There are many possible methods for searching and evaluating feature subsets, but little consensus on which methods are best. This paper examines a number of filter-based feature subset evaluation measures with the goal of assessing their performance with respect to specific classifiers. This work tests 16 common filter measures for use with K -nearest neighbors and support vector machine classifiers. The measures are tested on 20 real and 20 artificial data sets, which are designed to probe for specific challenges. The strengths and weaknesses of each measure are discussed with respect to the specific challenges and correlation with classifier accuracy. The results highlight several challenging problems with a number of common filter measures. The results indicate that the best filter measure is classifier-specific. K -nearest neighbors classifiers work well with subset-based RELIEF, correlation feature selection or conditional mutual information maximization, whereas Fisher׳s interclass separability criterion and conditional mutual information maximization work better for support vector machines. Despite the large number and variety of feature selection measures proposed in the literature, no single measure is guaranteed to outperform the others, even within a single classifier, and the overall performance of a feature selection method cannot be characterized independently of the subsequent classifier. [ABSTRACT FROM AUTHOR]

The “Big Data” era has arisen, driven by the increasing availability of data from multiple sources such as social media, online transactions, network sensors or mobile devices. This is currently a focus of interest among public and private organizations, governments, research institutes and companies operating in diverse fields as health, security, commercial recommendations, detection of anomalies and future trends among others. In this problem, the main objective is to recognize and extract meaningful information (patterns, structure, underlying relationships, etc.) from huge amounts of heterogeneous data. This task is complicated by new, significant storage and processing requirements due to unprecedented volumes of data. In this scenario, new algorithms in Pattern Recognition and related fields are being devised, while well known techniques are revisited and adapted to these new challenges. Latin American research in the “Big Data” problem is still incipient, but there is a significant body of recent works in the subjects of Pattern Recognition and related fields that indirectly addresses the problem. This paper reviews Latin American contributions in Pattern Recognition and related fields in the last lustrum. The focus is set on—but not restricted to—applications in the fields of Computer Vision and Image Analysis with large scale characteristics. [ABSTRACT FROM AUTHOR]

• This paper reveals the problem of unbalanced semantic information of different feature representations in cross-modal retrieval and explores the semantic augmentation for cross-modal retrieval. • A semantic augmentation strategy based on the intermediate semantic space is proposed to augment the semantic information of the modality data with weak semantics. • Extensive experiments on four datasets using typical cross-modal hashing methods, as well as real-valued, partial-paired, semi-paired, and completely unpaired cross-modal retrieval approaches are conducted to evaluate the effectiveness of semantic augmentation, and the results show that the gap between cross-modal retrieval results can be decreased substantially. Hashing methods for cross-modal retrieval has drawn increasing research interests and has been widely studied in recent years due to the explosive growth of multimedia big data. However, a significant phenomenon which has been ignored is that there is a large gap between the results of cross-modal hashing in most cases. For example, the results of Text-to-Image frequently outperform that of Image-to-Text with a large margin. In this paper, we propose a strategy named semantic augmentation to improve and balance the results of cross-modal hashing. An intermediate semantic space is constructed to re-align the feature representations that embedded with weak semantic information. By using the intermediate semantic space, the semantic information of visual features can be further augmented before being sent to cross-modal hashing algorithms. Extensive experiments are carried out on four datasets via seven state-of-the-art cross-modal hashing methods. Compared against the results without semantic augmentation, the Image-to-Text results of these methods with semantic augmentation are improved considerably, which demonstrates the effectiveness of the proposed semantic augmentation strategy in bridging the gap between the results of cross-modal retrieval. Additional experiments are conducted on the real-valued, semi-supervised, semi-paired, partial-paired, and unpaired cross-modal retrieval methods, the results further indicates the effectiveness of our strategy in improving performance of cross-modal retrieval. [ABSTRACT FROM AUTHOR]

• We propose a framework for person search that utilizes GAN-generated images in a novel deep network, which solves the typical problem of low numbers of samples in big data and can adapt to images of various types of pedestrians. • We propose a deep complementary classifier for pedestrian detection to leverage complementary object regions for pedestrian/non-pedestrian classification that can improve the overall performance of the person search model. • We propose a new loss function, named the center-constrained triplet loss, that combines the advantages of both center loss and triplet loss to minimize intraperson variations and maximize interperson variations. In addition, the center-constrained triplet loss can avoid the disadvan- tages of the triplet loss's careful selection of the required triplets for training. • We conduct experiments on the large-scale CUHK-SYSU and PRW datasets and find that a newly synthesized image from the original image helps improve the performance of the model. Our proposed loss achieves significant improvements over the compared approach in both mAP and top-1 evaluation protocols. This paper addresses the person search task, which is a computer vision technology that finds the location of a pedestrian and retrieves it in a video taken by a single camera or multiple cameras. This task is much more challenging than the conventional settings for person re-identification or pedestrian detection since the search is susceptible to factors such as different resolutions, similar pedestrians, lighting, viewing angles and occlusion. Moreover, the person search task is a typical big data-small sample problem because each pedestrian only has a few images. It is difficult for the model to learn the discriminant features of pedestrians with a small quantity of pedestrian data. This paper proposes a framework for person search that uses the original training set without collecting extra data by implementing a generative adversarial network (GAN) to generate unlabeled samples. We propose a deep complementary classifier for pedestrian detection to leverage complementary object regions for pedestrian/non-pedestrian classification. In the re-identification section, we propose a center-constrained triplet loss that avoids the complicated triplet selection of the triplet loss and simultaneously pushes away all the distances of rather similar negative centers and the positive center. Experiments show that the GAN-generated data can effectively help to improve the discriminating ability of the CNN model. On the two large-scale datasets, CUHK-SYSU and PRW, we achieve a performance improvement over the baseline CNN. We additionally apply the proposed center-constrained triplet loss and complementary classifiers in the training model, and we achieve mAP improvements over the original method of +1.9% on CUHK-SYSU and +2.5% on PRW. [ABSTRACT FROM AUTHOR]

• Feature Selection (FS) plays an important role in learning and classification tasks. • Large-scale online feature selection problems with big data. • Intelligent online feature selection system; Analysis step in a pattern recognition system. • Exploring the recent advances of online machine learning techniques and a conflict resolution technique (Automated Negotiation). • Enhancing the classification performance of ultra-high dimensional databases. Feature Selection (FS) plays an important role in learning and classification tasks. Its objective is to select the relevant and non-redundant features. Considering the huge number of features in real-world applications, FS methods using batch learning technique cannot resolve big data problems especially when data arrive sequentially. In this paper, we proposed an online feature selection system which resolves this problem. The proposed OFS system called MOANOFS (Multi-Objective Automated Negotiation based Online Feature Selection) explore the recent advances of online machine learning techniques and a conflict resolution technique (Automated Negotiation) for the purpose of enhancing the classification performance of ultra-high dimensional databases. MOANOFS uses two decision levels. In the first level, we decided which k(s) among the learners (or OFS methods) are the trustful ones (with high confidence or trust value). These elected k learners would participate in the second level where we integrated our proposed Multilateral Automated Negotiation based OFS (MANOFS) method. This would enable us to finally decide which features are the most relevant. We showed that MOANOFS system achieves high accuracy with several real text classification datasets as 20Newsgroups, RCV1. [ABSTRACT FROM AUTHOR]

• The very first survey of multi-view video summarization. • Coverage of full literature of multi-view video summarization from 2010 till date. • Major challenges of multi-view video summarization in the light of surveyed literature. • Coverage and investigation of benchmark datasets for multi-view video summarization. • Detailed recommendations for future research. There has been an exponential growth in the amount of visual data on a daily basis acquired from single or multi-view surveillance camera networks. This massive amount of data requires efficient mechanisms such as video summarization to ensure that only significant data are reported and the redundancy is reduced. Multi-view video summarization (MVS) is a less redundant and more concise way of providing information from the video content of all the cameras in the form of either keyframes or video segments. This paper presents an overview of the existing strategies proposed for MVS, including their advantages and drawbacks. Our survey covers the genericsteps in MVS, such as the pre-processing of video data, feature extraction, and post-processing followed by summary generation. We also describe the datasets that are available for the evaluation of MVS. Finally, we examine the major current issues related to MVS and put forward the recommendations for future research 1 [1] https://github.com/tanveer-hussain/MVS-Survey. [ABSTRACT FROM AUTHOR]

• This paper presents an efficient distributed associative classifier (CARs-Lands). • In CARs-Lands, local association rules lead to more accurate prediction, because each test instance is classified by the association rules of their nearest neighbors in the training datasets. • The proposed approach is evaluated in terms of accuracy on six real-world large-scale datasets against four other recent and well-known methods. • The experiment results show that the proposed classification method has a high prediction accuracy and is highly competitive when compared to other classification methods. Associative classifiers are one of the most efficient classifiers for large datasets. However, they are unsuitable to be directly used in large-scale data problems. Associative classifiers discover frequent/rare rules or both in order to produce an efficient classifier. Discovery rules need to explore a large solution space in a well-organized manner; hence, learning of the associative classification methods of large datasets is not suitable on large-scale datasets because of memory and time-complexity constraints. The proposed method, CARs-Lands, presents an efficient distributed associative classifier. In CARs-Lands, first, a modified dataset is generated. This new dataset has sub-datasets that are completely appropriate to produce classification association rules (CARs) in a parallel manner. The produced dataset by CARs-Lands contains two types of instances: main instances and neighbor instances. Main instances can be either real instances of training dataset or meta-instances, which are not in the training dataset; each main instance has several neighbor instances from the training dataset, which together form a sub-dataset. These sub-datasets are used for parallel local association rule mining. In CARs-Lands, local association rules lead to more accurate prediction, because each test instance is classified by the association rules of their nearest neighbors in the training datasets. The proposed approach is evaluated in terms of accuracy on six real-world large-scale datasets against five recent and well-known methods. Experiment results show that the proposed classification method has high prediction accuracy and is highly competitive when compared to other classification methods. [ABSTRACT FROM AUTHOR]

• Ensemble learning improves the performance of object detection and achieves the mAP of state-of-the-art detectors. • The combination of context modeling and dilated convolution ensures the detection speed. • The proposed multi-scale feature fusion module confers a clear improvement to the detector. • The proposed ensemble modes demonstrate the effectiveness of ensemble learning in the field of object detection. Due to the development of deep learning networks and big data dimensionality, research on ensemble deep learning is receiving an increasing amount of attention. This paper takes the object detection task as the research domain and proposes an object detection framework based on ensemble deep learning. To guarantee the accuracy as well as real-time detection, the detector uses a Single Shot MultiBox Detector (SSD) as the backbone and combines ensemble learning with context modeling and multi-scale feature representation. Two modes were designed in order to achieve ensemble learning: NMS Ensembling and Feature Ensembling. In addition, to obtain contextual information, we used dilated convolution to expand the receptive field of the network. Compared with state-of-the-art detectors, our detector achieves superior performance on the PASCAL VOC set and the MS COCO set. [ABSTRACT FROM AUTHOR]

• We propose an original method for attribute reduction based on stripped quotient sets. • The proposed method has solid theoretical background and algorithms. • The proposed method reports the superior results when compared to the state-of-the-art methods. Attribute reduction is a key problem in many areas such as data mining, pattern recognition, machine learning. The problems of finding all reducts as well as finding a minimal reduct in a given data table have been proved to be NP-hard. Therefore, to overcome this difficulty, many heuristic attribute reduction methods have been developed in recent years. In the process of heuristic attribute reduction, accelerating calculation of attribute significance is very important, especially for big data cases. In this paper, we firstly propose attribute significance measures based on stripped quotient sets. Then, by using these measures, we design efficient algorithms for calculating core and reduct, in which the time complexity will be considered in detail. Additionally, we will also give properties directly related to efficiently computing the attribute significance and significantly reducing the data size in the process of calculation. By theoretical and experimental views, we will show that our method can perform efficiently for large-scale data sets. [ABSTRACT FROM AUTHOR]