Eye movement abnormalities have been effective biomarkers that provide the possibility of distinguishing patients with schizophrenia from healthy controls. The existing methods for measuring eye movement abnormalities mostly focus on synchronic parameters, such as fixation duration and saccade amplitude, which can be directly obtained from eye movement data, while lack of considering more thorough

In the last few years there have been important advancements in disentangling latent representations using generative models, with the two dominant approaches being Generative Adversarial Networks (GANs) and Variational Autoencoders (VAEs). However, standard Autoencoders (AEs) and closely related structures have remained popular because they are easy to train and adapt to different tasks. An interesting

Live video hosted by streamers is being sought after by an increasing number of Internet users. Some streamers mix pornographic content with live video for profit and popularity, but this greatly harms the network environment. To effectively identify porn streamers, a multilevel fusion method of multimodal deep features for porn streamer recognition in live video is proposed in this paper. (1) Visual

Precise segmentation of the visual pathway is significant in preoperative planning to prevent the surgeon from touching it during the operation. Manual segmentation is time consuming and tedious. Thus, automatic segmentation strategies are necessary to assist clinical evaluation. However, the low contrast and blurred boundary between the target and the background in the image make automatic segmentation

In this paper, we investigate 3D hand pose estimation using single depth images. On the one hand, accurate hand localization is a crucial factor for pose estimation. On the other hand, multi-task learning methods have achieved great success in visual recognition tasks. Therefore, in this paper we proposed to simultaneously detect the hand location and estimate its 3D pose in a multi-task learning framework

Most of the recent successful approaches for video object segmentation are highly complex, heavily rely on fine-tuning of the first frame, are slow, and henceforth, are of constrained practical use. In this work, we introduce a novel approach of video object segmentation using unsupervised learning. The complete process is divided into two phases where base frame and current frame are considered for

Obtaining data with meaningful labels is often costly and error-prone. In this situation, semi-supervised learning (SSL) approaches are interesting, as they leverage assumptions about the unlabeled data to make up for the limited amount of labels. However, in real-world situations, we cannot assume that the labeling process is infallible, and the accuracy of many SSL classifiers decreases significantly

Tracking pedestrian targets over a thermal infrared (TIR) image sequence is a hot topic in visual tracking. The imagery characteristics of TIR targets such as low target-background contrast and far imaging distance make TIR object tracking very difficult. In this paper, based on a convolutional neural network (CNN) and the siamese region proposal network (SiamRPN), we design an improved TIR pedestrian

Chest X-Rays are the most common type of biomedical radiologic exam, being widely adopted for the diagnosis of a myriad of illnesses in the thoracic region. Computed Tomography – even though being more expensive and rare – is also a useful tool for the detection of several illnesses and surgery planning, providing volumetric information. This paper proposes a methodology aiming to leverage the larger

Surveillance video anomaly detection is to detect events that rarely or never happened in a certain scene. The generation error (GE)-based methods exhibit excellent performances on this task. They firstly train a generative neural network (GNN) to generate normal samples, then judge the samples with large GEs as anomalies. Almost all the GE-based methods utilize frame-level GEs to detect anomalies

Estimation of probability density functions is an essential component of various applications. Nonparametric techniques have been widely used for this task owing to the difficulty in parameterization of data. In particular, certain kernel density estimation methods have been developed. However, they are either incapable of maximum likelihood estimation or require the maintenance of a training set to

Recently, face alignment plays a significant role in lots of computer vision tasks. Due to the various head poses, diverse expressions and partial occlusions, face alignment has still been a great challenge. In this paper, we propose a new Deep Shape Constrained Network (DSCN) for robust face alignment. Specifically, our DSCN consists of a Shape Initialization Network (SIN) and a series of Shape Refinement

Recently, classification and dimensionality reduction (DR) have become important issues of hyperspectral image (HSI) analysis. Especially, HSI classification is a challenging task due to the high-dimensional feature space, with a large number of spectral bands, and a low number of labeled samples. In this paper, we propose a new HSI classification approach, which is called fused 3-D spectral-spatial

Image segmentation and superpixel generation have been studied for many years, and they are still active research topics in computer vision. Although many advanced computer vision algorithms have been used for image segmentation and superpixel generation, there is no end-to-end trainable algorithm that generates superpixels and segment images simultaneously. We propose an end-to-end trainable network

Recently, automatic pain assessment technology, in particular automatically detecting pain from facial expressions, has been developed to improve the quality of pain management, and has attracted increasing attention. In this paper, we propose self-supervised learning for automatic yet efficient pain assessment, in order to reduce the cost of collecting large amount of labeled data. To achieve this

While linear discriminant analysis (LDA) is a widely used classification method, it is highly affected by outliers which commonly occur in various real datasets. Therefore, several robust LDA methods have been proposed. However, they either rely on robust estimation of the sample means and covariance matrix which may have noninvertible Hessians or can only handle binary classes or low dimensional cases

Restoring artworks seriously damaged or completely destroyed is a challenging task. In particular, the reconstruction of frescoes has to deal with problems such as very small fragments, irregular shapes and missing pieces. Several attempts have been done to develop new techniques for helping restorers in the matching process, starting from traditional image processing methods to the more recent deep

Freezing of gait (FoG) is a motor symptom of Parkinson's disease (PD) that frequently occurs in the long-term sufferers of the disease. FoG may result to nursing home admission as it can lead to falls, and therefore, it impacts negatively on the quality of life. The focus of this study is the systematic evaluation of machine learning techniques in conjunction with varying size time windows and time/frequency

Novel Coronavirus disease (COVID-19) has abruptly and undoubtedly changed the world as we know it at the end of the 2nd decade of the 21st century. COVID-19 is extremely contagious and quickly spreading globally making its early diagnosis of paramount importance. Early diagnosis of COVID-19 enables health care professionals and government authorities to break the chain of transition and flatten the

Person re-identification (ReID) has achieved significant improvement under the setting of matching two holistic person images. However, persons are easily occluded by the various objects and other persons in real-world scenarios, making Person ReID a challenging task. In this paper, we propose a novel method named Pose-Driven Visibility Model (PDVM) to effectively solve the degradation of recognition

Scalable similarity search in metric spaces relies on using the mathematical properties of the space in order to allow efficient querying. Most important in this context is the triangle inequality property, which can allow the majority of individual similarity comparisons to be avoided for a given query. However many important metric spaces, typically those with high dimensionality, are not amenable

In recent years, Convolutional Neural Networks (CNNs) have shown promising performance on image hashing retrieval. However, due to the information-discarded nature of CNN, some meaningful information can not be further extracted into a deep level and embedded into hash codes. To solve the problem, this study attempts to design an invertible CNN feature extractor to fully maintain input information

In comparison with the conventional one-class support vector machine (OCSVM), least squares OCSVM (LS-OCSVM) can describe similarity between a new-coming sample and training set more accurately. However, LS-OCSVM is very sensitive to outliers in training set. The main reason lies that the values of square error function for outliers are relatively large, which makes LS-OCSVM put more emphasis on these

Most existing person re-identification methods are mainly based on human part partition with horizontal stripes or human body semantic segmentation. In this paper, we propose a method called MDRS (Multi-scale Discriminative network with Region Segmentation) to integrate multi-scale discriminative feature learning, horizontal stripe partition and semantic segmentation in a single framework, in which

In order to address the clustering problem of intelligent medical data, the data sets were not preprocessed using the traditional method, leading to a large amount of calculation, low efficiency, and large data cluster center offset distance. We proposed a balanced clustering algorithm for intelligent medical heterogeneous big data set using deep learning. Firstly, a deep neural network model based

In this paper, targeting image translation between the thermal and visible domains, we propose a novel framework to enhance the edge and boundary features during translation. We tackle the unsupervised training task where sample image pairs from two domains are randomly chosen so the image content does not match, but we also take advantage of paired feature maps during the feature disentanglement process

With the major adoption of automation for cities security, person re-identification (Re-ID) has been extensively studied recently. In this paper, we argue that the current way of studying person re-identification, i.e. by trying to re-identify a person within already detected and pre-cropped images of people, is not sufficient to implement practical security applications, where the inputs to the system

This work aims to freely translate an input face to an aging face with robust identity preservation, satisfying aging effect and authentic visual appearance. Witnessing the success of GAN in image synthesis, researchers employ GAN to address the problem of face aging synthesis. However, most GAN-based methods hold that the aging changing of all facial regions is equal, which ignores the fact that different

In this work, we introduce a novel framework based on Generative Adversarial Networks to control the pose, expression and facial features of a given face image using another face image. It can then be used for data augmentation, pose invariant face identification, face verification, and lightweight image editing. Generating new realistic face images with controllable poses, facial features, and expressions

This paper presents a Cyber-Physical System (CPS) based on Multi-Agent System (MAS) technology to implement an intelligent Demand-Side Management system (DSM). This system has been applied to optimize the power consumption of a public building (a University Facility) powered by a photovoltaic plant with the purpose of maintaining the same comfort level for users. This CPS is composed of a sensor network

With the increased use of digital holography to observe biological events in three dimensions the need for autofocusing becomes essential. We introduced a modified image quality evaluation technique as a focus criterion in the reconstruction of digital holograms. The method employed was initially proposed by [Wang et al. (2008)] to evaluate image inpainting quality from three aspects: luminance, definition

Pooling layers are spatial down-sampling layers used in convolutional neural networks (CNN) to gradually downscale the feature map, increase the receptive field size and reduce the number of the parameters in the model. The use of pooling layers leads to less computing complexity and memory consumption reduction but also introduces invariance to certain filter distortions which may induce subtle detail

In recent years, high spatial resolution remote sensing technology has made significant progress. High-resolution remote sensing satellites provide great convenience for high-quality image acquisition. In order to adapt to changes in the appearance of the target, mainstream tracking algorithms often use pattern recognition methods to build a target appearance model with learning capabilities, and use

Event analysis from news and social networks is a promising way to understand complex social phenomena. Each event consists of different components, which indicate what happened, when, where, and the people and organizations involved. Heterogeneous networks are useful for modeling large event datasets, where we map different types of objects (e.g. events and their components), as well as the different

A major problem in data augmentation is to ensure that the generated new samples cover the search space. This is a challenging problem and requires exploration for data augmentation policies to ensure their effectiveness in covering the search space. In this paper, we propose Greedy AutoAugment as a highly efficient search algorithm to find the best augmentation policies. We use a greedy approach to

As the popularity of iris recognition systems increases, the importance of effective security measures against presentation attacks becomes paramount. This work presents an overview of the most important advances in the area of iris presentation attack detection published in the recent two years. Newly-released, publicly-available datasets for development and evaluation of iris presentation attack

Graph representation learning is a key technology for processing graph-structured data. Graph convolutional networks (GCNs), as a type of currently emerging and commonly used model for graph representation learning, have achieved significant performance improvement. However, GCNs acquire node representations mainly through aggregating their neighbor information, largely ignoring the community structure

Due to the emergence and development of big data, cross-modal hash retrieval has become progressively more important in large-scale multi-modal retrieval tasks depending on its accuracy and efficiency. It completes the retrieval task in a common low-dimensional space by finding a common semantic space for heterogeneous data of different modalities. Recently, many works have concentrated on supervised

The big data generated by Industry 4.0 is expected to increase 20-fold in the next ten years and it has raised various challenges in Industrial Wireless Sensor Networks (IWSNs). Among these challenges, detecting different types of anomalies of industrial electricity consumption in an accurate and timely manner is a priority. If not handled properly, these anomalies could lead to serious consequences

Today, people rely almost full time on digital texts. It is not surprising that handwriting earned a special status, and solutions to mimic real handwriting became attractive. A particular field called handwriting synthesis generates renderings of text which resemble natural writing but are synthesized from actual handwriting samples. The main idea behind samples’ current solutions is to collect enough

The ability to discern lies, more broadly known as deception detection, is an invaluable skill that can strongly influence the outcome of relevant situations such as court trials and police interrogatories. Several devices currently exist and are being used (e.g., magnetic resonance and polygraphs) to ease those tasks; although, due to the subject awareness of such tools, their effectiveness can be

Based on the original text information, this paper converts the users' theme preferences and text sentiment features into attention information and combines different forms with the LSTM (Long Short-Term Memory) model to predict the personality characteristics of social network users. Finally, the experimental results of multiple groups’ show that the Attention-based LSTM model proposed in the paper

Social relationships link everyone in human society. Exploring social relationships in still images promotes researches of behaviors or characteristics among persons. Previous literature has discovered that face and body attributes can provide effective semantic information for social relationship recognition. However, they ignore that attributes contribute much differently to the recognition accuracy

Virtually recomposing destroyed frescoes is of great importance for heritage conservation. Given a digitized fresco image and a digitized set of fragments, such a problem is challenging due to the potentially large number of fragments, their irregular shape, uniqueness and non-overlapping constraints, the possible absence of fragments and the possible presence of small, homogeneous, eroded and/or spurious

Capsule network (CapsNet) is a novel architecture that takes into account the hierarchical pose relationships between object parts, which had achieved desirable results on image classification. EM-Routing (EM-R) used in CapsNet is the process of assigning child capsules (parts) to each parent capsule (objects) based on a level of agreement, which is similar to the fuzzy clustering process. However

Image illumination correction has been a long standing topic for research in the Computer Vision problem. However, all previous literature on this topic has either been statistical in nature in the sense that a specified algorithm has been developed for approaching a particular case of illumination normalization, or involves extremely complex deep learning methods for illumination correction of either

Combining features of different scales to learn a more discriminative model is an essential solution for person re-identification (Re-ID) tasks. Most existing multi-scale methods are based on the fusion of features from different scales, which cannot exploit information throughly at each scale and cause gradient chaos in optimizing. To address this problem, in this paper we propose an end-to-end multi-scale

Multi-label image recognition is a task that predicts a set of object labels in an image. As the objects co-occur in the physical world, it is desirable to model label dependencies. Previous existing methods resort to either recurrent networks or pre-defined label correlation graphs for this purpose. In this paper, instead of using a pre-defined graph which is inflexible and may be sub-optimal for

An exact algorithm for estimating the dynamic stochastic block model is proposed. This model assumes a hidden Markov chain for the evolution of the social behavior of a group of individuals at repeated time occasions and may be used to assign these individuals to the latent blocks in a dynamic fashion. For the estimation of this model, the proposed exact algorithm maximizes the target function introduced

Multi-focus image fusion, a technique to generate an all-in-focus image from two or more partially-focused source images, can benefit many computer vision tasks. However, currently there is no large and realistic dataset to perform convincing evaluation and comparison of algorithms in multi-focus image fusion. Moreover, it is difficult to train a deep neural network for multi-focus image fusion without

Person re-identification (Re-ID) is the task of retrieving a person of interest taken from different cameras or from the same camera in different occasions. To address this challenging task, a large amount of labelled data is required both for testing and for learning. Such high quality annotated data is still rare for many Re-ID applications. In this paper, we introduce a novel dataset to evaluate

Crowd density estimation is a crucial component in surveillance systems to construct safe and efficient urban environments. Due to perspective distortion, individuals in crowd scenes diminish in size as they converge toward the vanishing point. Hence, there are significant visual variations in individuals’ size and appearance, which may lead to inaccurate estimations of crowd counts. This paper proposes

A smart city is engineered to be a self-sustained ecosystem driven by Internet-of-Things (IoT) devices. Smooth functioning of smart cities is conditioned on seamless communication between users and devices. Smart devices equipped with biometric authentication can offer security as well as personalized experience to the end users. Currently, a number of smart devices employ face, fingerprint, and voice

This paper proposes a weighted hybrid multi-view fusion method for the semi-supervised classification problem. Instead of getting access to the features from different views directly, this method utilizes the square losses of the multi-view classifiers to exploit the between-view relationship, which preserves the privacy of data. Considering the different prediction capability of classifiers on multiple