Traditional linear dimension reduction methods such as Principal component analysis (PCA) and linear discriminant analysis (LDA) have been used in many application areas due to simplicity and high performance. However, in data streams where data instances are generated continuously over time, it is difficult to apply traditional PCA or LDA. Moreover, data streams can have drifting concepts over time

Aiming at traditional spectral clustering method still suffers from the following issues: 1) unable to handle the incomplete data, 2) two-step clustering strategies tend to perform poorly due to the heterogeneity between the similarity matrix learning model and the clustering model, 3) constructing the affinity matrix from original data which often contains noises and outliers. To address these issues

Deep convolutional neural network (CNN) with considerable number of parameters is one of the promising methods for image recognition. There, however, is generally difficult in applying deep CNNs to resource constrained devices due to the heavy computational burden. For reducing computational cost of CNNs while retaining the classification performance, it is effective to apply pruning methods that remove

In many computer vision applications, one acquires images of planar surfaces from two different vantage points. One can use a projective transformation to map pixel coordinates associated with a particular planar surface from one image to another. The transformation, called a homography, can be represented by a unique, to within a scale factor, 3 × 3 matrix. One requires a different homography matrix

Data Subset selection for training learning models for a variety of tasks, has been widely studied in the literature of batch mode active learning. Recent works attempt to utilize the model specific signals in the deep learning context for computer vision tasks. Companies, in their bid to create safe autonomous driving models, train and test their models on billions of miles of driving data; not all

Nowadays, there is a great variety of visual features available for image retrieval tasks. While fusion strategies have been established as a promising alternative, an inherent difficulty in unsupervised scenarios is the task of selecting the features to combine. In this paper, a Graph-based Selective Rank Fusion is proposed. The graph is used to represent the effectiveness estimation of features and

Magnetic Resonance Images (MRI) are often contaminated by rician noise at the acquisition time. This type of noise typically deteriorates the performance of disease diagnosis by a human observer or an automated system. Thus, it is necessary to remove the rician noise from MRI scans as a preprocessing step. In this letter, we propose a novel Convolutional Neural Network (CNN), viz. CNN-DMRI, for denoising

Local feature detection is a fundamental problem in computer vision. Recently, the research of local feature detection has been switched from handcrafted methods to learning based ones, especially deep learning based ones. A recent successful deep learning based feature detector is the covariant local feature detector that conducts keypoint detection by predicting the transformation of keypoints from

Recent advancements in Generative Adversarial Networks (GANs) have led to significant improvements in various image generation tasks including image synthesis based on text descriptions. In this paper, we present an enhanced Attentional Generative Adversarial Network (e-AttnGAN) with improved training stability for text-to-image synthesis. e-AttnGAN’s integrated attention module utilizes both sentence

Breast thermography images are a new type of data that has been analyzed in recent years in order to detect abnormalities, which can lead to a future breast cancer. This paper proposes a methodology for breast thermal image classification, which is useful in Computer-Aided Detection Systems. The main contribution is an automatic method to segment the region of interest (ROI) based on local operations

We address the question to what extent origin of folk songs can be predicted, and construct a song similarity network. For this we use feature selection and train a random forest classifier on extracted melody n-grams and rhythm grams of songs from 7 different groups of origin, 80 from each. We use its importances to reduce the feature space dimension for the construction of an informative network

Ancient paintings are valuable culture legacy which can help archaeologists and culture researchers to study history and humanity. Most ancient artworks have damage problems, such as degradation, flaking and cracking. This work presents a novel controllable image inpainting framework with capability of incorporating suggestions from experts, which can help artists envisage how the ancient painting

Visible Thermal Person Re-Identification (VTReID) is essentially a cross-modality problem and widely encountered in real night-time surveillance scenarios, which is still in need of vigorous performance improvement. In this work, we design a simple but effective Hard Modality Alignment Network (HMAN) framework to learn modality-robust features. Since current VTReID works do not consider the cross-modality

In the research of computer-aided diagnosis, the shortage of disease feature dimension curse and the imbalance of medical samples have always been the focus of research on diagnostic decision support systems. For these two problems, we propose a feature selection algorithm based on association rules and an integrated classification algorithm based on random equilibrium sampling. We extracted and cleaned

This special issue proposes a space for researchers to discuss the challenges of bridging pattern recognition and cognitive assistants. This bridge was travelled in both sides. From one side, how pattern recognition methods can help intelligent systems to become more cognitive. And from the other side, how cognitive models can improve pattern recognition methods so that the final system can better

Graph matching is the task of finding the similarity between the two graphs. Error-tolerant graph matching is the process of computing the similarity between the two graphs, where some flexibility to noise or error is allowed to approximate the value of graph matching. In this paper, we present a framework for graph matching by utilizing the centrality measures to ignore the least central nodes of

3D scene parsing has always been a hot topic and point clouds are efficient data format to represent scenes. The semantic segmentation of point clouds is critical to the 3D scene, which is a challenging problem due to the unordered structure of point clouds. The max-pooling operation is typically used to obtain the order invariant features, while the point-wise features are destroyed after the max-pooling

Recent breakthroughs in representation learning of unseen classes and examples have been made in deep metric learning by training at the same time the image representations and a corresponding metric with deep networks. Recent contributions mostly address the training part (loss functions, sampling strategies, etc.), while a few works focus on improving the discriminative power of the image representation

Stream cipher system seems to be one of the best alternatives in order to provide confidentiality and security in an on line and high-speed transmission. Cryptography is required to secure the secret information transmitting over the communication channel. Day by day the importance of security increases due to increase of online transaction processing and e-commerce. As well as encryption / decryption

The build-up of beta-amyloid and rapid spread of tau proteins in the brain cause the death of neurons, leading to Alzheimer's disease (AD). AD is a form of dementia, and the symptoms include memory loss and decision-making difficulties. Current advanced diagnostic modalities are costly or unable to detect the histopathological features of AD. Hence a computational intelligence tool (CIT) for AD diagnosis

Video understanding is a challenging problem and it attracts a lot of research attention. Lately, a new task called movie fill in the blank (MovieFIB) is proposed. In this task, given a movie clip and a description which has one blank, we need to predict the word in the blank accurately. Previous studies make many contributions to tackling this problem. However, some of them do not utilize the relationship

With the rapid growth of the big data, many approaches in the representation of text for sentiment classification have been successfully proposed in natural language processing. However, these approaches remedy this problem based on single-task supervised objectives learning and do not consider their relative of multiple tasks. Based on these defects, in this work, we consider these tasks are relative

Previous feature selection methods equivalently consider the samples to select important features. However, the samples are often diverse. For example, the outliers should have small or even zero weights while the important samples should have large weights. In this paper, we add a self-paced regularization in the sparse feature selection model to reduce the impact of outliers for conducting feature

Graph matching algorithms are gaining more and more interest in the last years from different scientific communities; indeed, they allow comparing any kind of objects represented using their intrinsic structure, represented in terms of attributed relational graphs. The challenge is to make these algorithms able to provide solutions over huge graphs, with many thousands of nodes, and in a time that

In unsupervised circumstances, multi-view learning seeks a shared latent representation by taking the consensus and complementary principles into account. However, most existing multi-view unsupervised learning approaches do not explicitly lay stress on the predictability of the latent space. In this paper, we propose a novel multi-view predictive latent space learning (MVP) model and apply it to multi-view

In this paper, we propose two novel local-global nested graph kernels, namely the nested aligned kernel and the nested reproducing kernel, drawing on depth-based complexity traces. Both of the nested kernels gauge the nested depth complexity trace through a family of K-layer expansion subgraphs rooted at the centroid vertex, i.e., the vertex with minimum shortest path length variance to the remaining

An efficient filtering algorithm is required to remove noise and simultaneously protect fine details and important features in the medical images. In this paper, a noise adaptive information set based switching median (NAISM) filter is proposed for the removal of impulse noise. NAISM filter is inspired from fuzzy switching median filter and works on the concept of information sets. Information sets

Among all the biological signals, gait signal is one of the better features to detect movement disorders caused by a malfunction in parts of the brain and nervous system. Usually, identifying and evaluating movement disorders caused due to neurodegenerative diseases solely depends on a physicians experience. Different diseases having gait abnormalities generate a unique gait characteristic. Traditionally

The k-nearest neighbors classifier has been widely used to classify graphs in pattern recognition. An unknown graph is classified by comparing it to all the graphs in the training set and then assigning it the class to which the majority of the nearest neighbors belong. When the size of the database is large, the search of k-nearest neighbors can be very time consuming. On this basis, researchers proposed

The graph edit distance is a widely used distance measure for labelled graph. However, A★−GED, the standard approach for its exact computation, suffers from huge runtime and memory requirements. Recently, three better performing algorithms have been proposed: The general algorithms DF−GED and BIP−GED, and the algorithm CSI−GED, which only works for uniform edit costs. All newly proposed algorithms

Nom is an ancient script used in Vietnam until the current Latin-based Vietnamese alphabet became common, and a large number of ancient Nom documents are in existence. Due to the gradual degradation of Nom documents and a decrease in the number of scholars who can understand them, a system to digitalize Nom documents is urgently necessary. This paper presents a segmentation-based method for digitalizing

Computer vision and machine learning can be used in cultural heritage to augment the experience of visitors during the exploration of the cultural site, as well as to assist its management. To achieve such goals, two fundamental tasks should be addressed, i.e., localizing visitors and recognizing the observed artworks. Wearable cameras offer a convenient setting to address both tasks through the analysis

Text-to-image is a process of generating an image from the input text. It has a variety of applications in art generation, computer-aided design, and data synthesis. In this paper, we propose a new framework which leverages mask anchor points to incorporate two major steps in the image synthesis. In the first step, the mask image is generated from the input text and the mask dataset. In the second

Coronary artery disease (CAD) is a leading cause of death worldwide and is associated with high healthcare expenditure. Researchers are motivated to apply machine learning (ML) for quick and accurate detection of CAD. The performance of the automated systems depends on the quality of features used. Clinical CAD datasets contain different features with varying degrees of association with CAD. To extract

In this work, we study the problem of deep representation learning on a large face dataset with long-tail distribution. Training convolutional neural networks on such dataset with conventional strategy suffers from imbalance problem which results in biased classification boundary, and the few-shot classes lying in tail parts further make the model prone to overfitting. Aiming to learn more discriminative

This paper describes the validation of a deep learning model for Internet of Things (IoT) based health care applications. As such, the deep learning model was created to detect episodes of Atrial Fibrillation (AF) using Heart Rate (HR) signals. The initial Long Short-Term Memory (LSTM) model was developed using 20 data sets, from distinct subjects, obtained from the AFDB database on PhysioNet. This

Panoramic video is a sort of video recorded at the same point of view to record the full scene. With the development of video surveillance and the requirement for 3D converged video surveillance in smart cities, CPU and GPU are required to possess strong processing abilities to make panoramic video. The traditional panoramic products depend on post processing, which results in high power consumption

Despite the great progress achieved, image-to-video person re-identification is still challenging in the cross-modal scenario. Currently, state-of-the-art approaches mainly concentrate on the task-specific data, neglecting the extra information from the different but related tasks. In this paper, we propose an end-to-end neural network framework for image-to-video person re-identification with cross-modal

Ultrasonography is an acceptable modality to evaluate median nerve (MN) in patients with carpal tunnel syndrome (CTS). Additional investigations are needed to evaluate sonographic parameters and compare their performances with artificial intelligence (AI) methods. The aim of this study is to compare the performance of shear wave elastography, morphometry, and AI techniques to predict MN entrapment

This paper describes a permutational-based Differential Evolution algorithm implemented in a wrapper scheme to find a feature subset to be applied in the construction of a near-optimal classifier. In this approach, the relevance of a feature chosen to build a better classifier is represented through its relative position in an integer-valued vector, and by using a permutational-based mutation operator

Label propagation (LP) is one of the state-of-the-art graph based semi-supervised learning (GSSL) algorithm. Probability transition matrix (PTM) is the key for LP to propagate label information among samples. Conventionally, PTM is calculated based on the graph constructed in advance, and graph construction independent of PTM calculation. It leads to complex steps for acquiring PTM, and more importantly

The application of Machine Learning (ML) to Cultural Heritage (CH) has evolved since basic statistical approaches such as Linear Regression to complex Deep Learning models. The question remains how much of this actively improves on the underlying algorithm versus using it within a ‘black box’ setting. We survey across ML and CH literature to identify the theoretical changes which contribute to the

Recent studies have shown that extended nearest neighbor (ENN) method is able to improve the classification performance over traditional k-nearest neighbor (KNN) methods, due to its novel “two-way communication” decision making process. The ENN method classifies a test data sample by maximizing the intra-class coherence gain over the whole data set. However, the original ENN method, like KNN, is a

This work exploits a connection between optimal transport theory and the physics of image propagation to yield a locally low-dimensional model of turbulence-corrupted imagery. Optimal transport produces an invertible, pixel-wise linear trajectories to approximate the globally nonlinear turbulence between a clean and turbulence corrupted image pair. We use the low-dimensional model to fit subsets of

The diurnal cycle of tropical cyclones (TCs) is a daily cycle in clouds that appears in satellite images and may have implications for TC structure and intensity. The diurnal pattern can be seen in infrared (IR) satellite imagery as cyclical pulses in the cloud field that propagate radially outward from the center of nearly all Atlantic-basin TCs. These diurnal pulses, a distinguishing characteristic

Over-segmentation into superpixels is a very effective dimensionality reduction strategy, enabling fast dense image processing. The main issue of this approach is the inherent irregularity of the image decomposition compared to standard hierarchical multi-resolution schemes, especially when searching for similar neighboring patterns. Several works have attended to overcome this issue by taking into

A hierarchical image segmentation is a set of image segmentations at different detail levels. However, objects (or even parts of the same object) may appear at different scales due to their size differences or to their distinct distances from the camera. One possible solution to cope with that is to realign the hierarchy such that every region containing an object (or its parts) is at the same level

Multiple Instance Learning is a weakly supervised learning technique which is particularly well suited for medical data analysis as the class labels are often not available at desired granularity. Multiple Instance Learning through Deep Neural Networks is relatively a new paradigm in machine learning. The most important part of Multiple Instance Learning through Deep Neural Networks is designing a

Epilepsy is a neural disorder that is associated with the central nervous system (CNS) in which the brain activity sometimes becomes abnormal, which may lead to seizures, loss of awareness, unusual sensations, and behavior. Electroencephalograms (EEG) are widely used to detect epilepsy accurately. However, the interpretation of a particular type of abnormality using the EEG signal is a subjective affair

Since many machine learning algorithms require a distance metric to capture dis/similarities between data points, metric learning has received much attention during the past decade. Surprisingly, very few methods have focused on learning a metric in an imbalanced scenario where the number of positive examples is much smaller than the negatives, and even fewer derived theoretical guarantees in this

Gliomas are characterized by high morbidity and high mortality in primary tumors. The identification of glioma type is helpful for radiologists to facilitate correct medical judgments and better prognosis for patients. In order to avoid harm to patients caused by a biopsy, radiologists attempt to classify Magnetic Resonance Images(MRI) using deep learning methods. In the present paper, we propose a

Identification of EEG signals is currently an open problem where performance analysis in terms of accuracy is relevant in several fields, such as biomedicine and brain computer interfaces. Nevertheless, performance depends on the feature extraction phase, where the aim is to find relevant patterns related to different mental activities. Thus, in this work, an approach to extract features from EEG signals

Automatically describing video content with natural language has been attracting much attention in computer vision and natural language processing communities. Most existing methods predict one word at a time, and by feeding the last generated word back as input at the next time, while the other generated words are not fully exploited. Furthermore, traditional methods optimize the model using all the