Recently, the generative adversarial network (GAN) has attracted wide attention for various computer vision tasks. GAN provides a novel concept for image-to-image transformation by means of adversarial learning. In recent years, numerous adversarial-learning-based methods have been proposed, and impressive results have been achieved. Related reviews have mainly focused on the basic GAN model and its

As an ensemble algorithm, network boosting enjoys a powerful classification ability but suffers from the tedious and time-consuming training process. To tackle the problem, in this paper, a broad network gradient boosting system (BNGBS) is developed by integrating gradient boosting machine with broad networks, in which the classification loss caused by a base broad network is learned and eliminated

Motion averaging has recently been introduced as an effective means to tackle the registration of multi-view range scans. This approach can view parts of pair-wise motions with high reliability as an input to estimate the global motions for a multi-view registration. However, reliable pair-wise motions are not easy to confirm in most practical applications without prior knowledge. In this paper, we

A latent factor analysis (LFA)-based model has outstanding performance in extracting desired patterns from High-dimensional and Sparse (HiDS) data for building a recommender systems. However, they mostly fail in acquiring non-linear features from an HiDS matrix. An AutoEncoder (AE)-based model can address this issue efficiently, but it requires filling unknown data of an HiDS matrix with pre-assumptions

Traditional unsupervised feature selection methods usually construct a fixed similarity matrix. This matrix is sensitive to noise and becomes unreliable, which affects the performance of feature selection. The researches have shown that both the global reconstruction information and local structure information are important for feature selection. To solve the above problem effectively and make use

Weakly-supervised multi-label learning has emerged as a hot topic more recently. Most existing methods deal with such problem by learning from the data where the label assignments are incomplete while the feature information is ideal. However, in many real applications, due to the influence of occlusion, illumination and low-resolution, the acquired features are often noisy, which may reduce the robustness

In this study, we focus on understanding and mining user’s preferences and intentions via user-based aggregation in the context of a social network. Understanding preference and intention in microblog texts is more difficult and challenging than understanding such characteristics in the context of standard text. The main reason is that search history and click history are difficult to obtain due to

This paper investigates the problem of disturbance observer-based output feedback control for quadrotor unmanned aerial vehicles with external disturbances, uncertainties and input saturation. Different from the existing results, we propose a novel control algorithm towards attitude system and position system. First, considering that not all signals can be measured directly by sensors, we construct

Inspired by speech recognition, most of the recent state-of-the-art works convert scene text recognition into sequence prediction. Like most speech recognition problems, context modeling is considered as a critical component in these methods for achieving better performance. However, they usually only consider using a holistic or single-scale local sequence context, in a single dimension. Actually

In this paper, a novel control scheme is developed to solve an optimal containment control problem of unknown continuous-time multi-agent systems. Different from traditional adaptive dynamic programming (ADP) algorithms, this paper proposes an internal reinforcement ADP algorithm (IR-ADP), in which the internal reinforcement signals are added in order to facilitate the learning process. Then a distributed

Learning long-term dependencies remains difficult for recurrent neural networks (RNNs) despite their success in sequence modeling recently. In this paper, we propose a novel gated RNN structure, which contains only one gate. Hidden states in the proposed grouped distributor unit (GDU) are partitioned into groups. For each group, the proportion of memory to be overwritten in each state transition is

Extreme Learning Machine (ELM) is a powerful and favorable classifier used in various applications due to its fast speed and good generalization capability. However, when dealing with complex visual tasks, the shallow architecture of ELM makes it infeasible to have good performance when raw image data are directly fed in as input. Therefore, several works tried to make use of deep neural networks (DNNs)

Data often exists in subspaces embedded within a high-dimensional space. Subspace clustering seeks to group data according to the dimensions relevant to each subspace. This requires the estimation of subspaces as well as the clustering of data. Subspace clustering becomes increasingly challenging in high dimensional spaces due to the curse of dimensionality which affects reliable estimations of distances

In many real world scenarios, it is difficult to capture the images in the visible light spectrum (VIS) due to bad lighting conditions. However, the images can be captured in such scenarios using Near-Infrared (NIR) and Thermal (THM) cameras. The NIR and THM images contain the limited details. Thus, there is a need to transform the images from THM/NIR to VIS for better understanding. However, it is

Our propensity to acclimate to new surroundings and flexibly choose an optimal behavior for a maximal reward (i.e., optimal outcome) is natural, for it affects our survival. A line of studies suggested that the anterior cingulate cortex (ACC) could be a potential hub for adaptive behaviors, but its exact functions remain poorly understood. One experimental study suggested that ACC can enable monkeys

Adversarial networks have been used to learn transferable representations in many domain adaptation methods. However, there is no theoretical guarantee that two distributions are identical, even if the discriminator is fully confused. Therefore, a more elaborate domain adversarial method to better align distributions is desirable. In this paper, we propose two groups of multiple adversarial networks

In general, Spiking Neural Networks (SNNs) have a network structure with special methods applied to neuron models and information transmission to mimic humans biologically. However, the existing SNN structures have two problems, such as fixed existing Artificial Neural Network structures and difficulty in learning due to lack of spike information during information transfer. Recently, many approaches

We explored the problem about function approximation error and complex mission adaptability in multi-agent deep reinforcement learning. This paper proposes a new multi-agent deep reinforcement learning algorithm framework named multi-agent time delayed deep deterministic policy gradient. Our work reduces the overestimation error of neural network approximation and variance of estimation result using

Clustering is a difficult but crucial task in pattern recognition and machine learning. Inherently, clustering methods are always subject to the uncertainty of similarities between samples. To weaken the impact of such uncertainty, we develop Deep Clustering with both Adaptive Siamese Loss (ASL) and ReConstruction Loss (RCL) to adaptively consider the similarities and stabilize the clustering process

Blind separation of sources (BSS) is to recover the source signals from the observed mixture signals with no knowledge on the mixing channel. Recently, there has been more and more attention to underdetermined BSS. In the study of underdetermined BSS, it is a challenging problem to separate the source signals efficiently while without knowing the number of sources. On the one hand, the number of sources

We present a novel end-to-end deep neural network model based on graph convolutional networks for simultaneous joint extraction of entities and relations among them. Our model captures context and syntactic information from sentence by stacking a graph convolutional layer over bidirectional sequential LSTM layers. We sequentially concatenate the subject, object and sentence representations for obtaining

Judicial Decision Prediction (JDP) aims to predict legal judgments given the fact description of a criminal case. It consists of multiple subtasks, e.g., law article prediction, charge prediction, and term of penalty prediction. Generally, a fact description contains in-depth semantic information. Besides, there exist complex dependencies among subtasks. For instance, law article prediction could guide

Aiming to improve the model’s generalization performance for nonlinear system modeling, a self-organizing reciprocal modular neural network (SORMNN) is proposed in the present study, which imitates the modular structure with inter-module connections observed in human brains. The inter-module connections in SORMNN are built by inputting the output of each subnetwork to other subnetworks. All subnetworks

Facial expression recognition is a hot research topic and can be applied in many computer vision fields, such as human–computer interaction, affective computing and so on. In this paper, we propose a novel end-to-end network with attention mechanism for automatic facial expression recognition. The new network architecture consists of four parts, i.e., the feature extraction module, the attention module

Missing values widely exist in time-series data owing to sensor or communication failure. It is indispensable to impute the missing data for equipment state monitoring and advanced data analysis. In this study, we propose a deep spatiotemporal time-series missing data imputation model, called LSTM-AEs, to enhance the imputation performance and handle multiple missing patterns. Generally, it is practically

Object detection is a pivotal task for many unmanned aerial vehicle (UAV) applications. Compared to general scenes, the objects in aerial images are typically much smaller. For this reason, most general object detectors suffer from two critical challenges while dealing with aerial images: 1) The widely exploited Feature Pyramid Network works by integrating high-level features to lower levels progressively

Model-free reinforcement learning methods have potentials in ship collision avoidance under unknown environments. To defect the low efficiency problem of the model-free reinforcement learning, a composite learning method is proposed based on an asynchronous advantage actor-critic (A3C) algorithm, a long short-term memory neural network (LSTM) and Q-learning. The proposed method uses Q-learning for

High efficiency video coding (HEVC) greatly outperforms previous standards H.264/AVC in terms of coding bit rate and video quality. However, it does not take into account the human visual system (HVS), that people pay more attention to specific areas and moving objects. In this paper, we present a content-aware rate control scheme for HEVC based on static and dynamic saliency detection. The proposed

In this paper, we proposed an iterative learning control (ILC) update rule to synchronize an array of non-identical time-varying delayed neural network systems in a repetitive environment. Under the identical initial conditions, we employed a distributed D-type ILC update rule that guaranteed synchronization by choosing the appropriate inner coupling matrix. Besides, to accommodate non-identical initial

Though with the rapid development of deep learning, salient object detection methods have achieved increasingly better performance, how to get effective feature representation to predict more accurate saliency maps is still a burning problem we need to consider. To overcome this situation, most previous works tend to focus on skip-based architecture to integrate hierarchical information of different

Video coding effectively reduces the amount of video data while unavoidably producing compression noise. Compression noise can cause significant artifacts in compressed video, such as blocking, ringing, and blurring, which seriously affects the visual quality of videos and the value of videos for content analysis. In compressed video quality enhancement, few methods based on deep learning fully consider

Action recognition is an important and challenging problem in video analysis. Although the past decade has witnessed progress in action recognition with the development of deep learning, such process has been slow in competitive sports content analysis. To promote the research on action recognition from competitive sports video clips, we introduce a Figure Skating Dataset (FSD-10) for fine-grained

In this paper, we investigate different activation functions (AFs) on convergence performance of a gradient-based neural network (GNN) for solving linear matrix equation, AXB+X=C. It is observed that, by employing different AFs, i.e., linear, power-sigmoid, sign-power, and general sign-bi-power functions, the presented GNN model can achieve different convergence performance. More specifically, if linear

Several practical difficulties arise when trying to apply deep learning to image-based industrial inspection tasks: training datasets are difficult to obtain, each image must be inspected in milliseconds, and defects must be detected with 99% or greater accuracy. In this paper we show how, for image-based industrial inspection tasks, transfer learning can be leveraged to address these challenges. Whereas

Image captioning is a task to generate natural descriptions of images. In existing image captioning models, the generated captions usually lack semantic discriminability. Semantic discriminability is difficult as it requires the model to capture detailed differences in images. In this paper, we propose an image captioning framework with semantic-enhanced features and extremely hard negative examples

In recent years, applications of face recognition have increased significantly. Despite the successful application of deep convolutional neural network (DCNN), training such networks is still a challenging task that needs a lot of experience and carefully tuning. Based on the Inception-ResNet network, we propose a novel method to mitigate the difficulty of training such deep convolutional neural network

In generalized zero-shot learning (GZSL), it is imperative to solve the bias problem due to extreme data imbalance between seen and unseen classes, i.e., unseen classes are misclassified as seen classes. We alleviate the bias problem by generating synthetic images of unseen classes. The most challenging part is that existing GAN methods are only focused on producing authentic seen images, so realistic

This paper presents a novel correlation filter-based tracking method for robust visual object tracking in the presence of partial occlusion, large-scale variation and model drift. To do this, first, we develop a correlation filter for predicting the target location based on the distribution of correlation response. In this formulation, the correlation response of the target image follows Gaussian distribution

In the brain, high-order and low-order areas are connected via bottom-up connections (from low-order to high-order areas) and top-down connections (from high-order to low-order areas). While bottom-up signals are thought to be critical in generating perception, functions of top-down signals have not been clearly delineated. One popular theory is that top-down inputs modify the activity of specific

This paper proposes an extension of the type-1 and singleton fuzzy logic system for dealing with multiclass classification problems. The proposed extension enables a fuzzy classifier to generate more than one output, thereby avoiding the use of binary decomposition strategies when multiclass classification problems are considered. Additionally, with the goal of improving classifier performance, the

Age synthesis methods typically take a single image as input and use a specific number to control the age of the generated image. In this paper, we propose a novel framework taking two images as inputs, named dual-reference age synthesis (DRAS), which approaches the task differently; instead of using “hard” age information, i.e. a fixed number, our model determines the target age in a “soft” way, by

Session-based recommendation task attracts more researchers’ attention in recent years. However, previous approaches suffer from limited timeliness since they overlook dynamic features of items and temporal semantic information, which results in inappropriate prediction. In this study, we propose an attention-based model named Timeliness Enhanced Attention Network (TEAN). It first extracts features

This article deals with the set-membership state estimation problem for a class of artificial neural networks subject to time-delays and mixed malicious attacks. Both Denial-of-Service (DoS) and deception attacks are taken into consideration. The objective of the addressed problem is to design the state estimation algorithm for the artificial neural networks under investigation in spite of the existence

Traditional recommender systems help users find items of interest by modeling long-term user profiles, which consist of items the users interacted with in the past. In many real-life applications, however, informative user profiles are not available. Instead, the system recommends by relying on the current user activities within an ongoing session, leading to the emergence of session-based recommendation

Benefiting from the development of convolutional neural networks, salient object detection has yielded a qualitative leap in performance. In recent years, most of deep learning based methods utilize multi-level features and obtain inferred saliency map in a coarse-to-fine manner. However, how to learn and represent powerful features is still a challenge. In this paper, we propose a novel FCN-like approach

This paper focuses on state estimation problem for discrete-time high-order neural networks with time-varying delays. First, the delay-dependent global exponential stability criterion of the error system is derived. Then, the state observer is designed by using the generalized inverse theory of matrices. Last, two numerical examples are given to illustrate the validity of the theoretical results. The

The heart sound signals (Phonocardiogram – PCG) enable the earliest monitoring to detect a potential cardiovascular pathology and have recently become a crucial tool as a diagnostic test in outpatient monitoring to assess heart hemodynamic status. The need for an automated and accurate anomaly detection method for PCG has thus become imminent. To determine the state-of-the-art PCG classification algorithm

Predicting the number and distribution of people in a crowded image is challenging work, due to the scale variations and complex background. In this work, we propose a two-branch fusion model with attention map to deal with the above two problems. Compared with previous works, our method designs a network focusing on fusing density maps which generated from different branches, instead of fusing features

Person re-identification (Re-ID) has attracted more attention in computer vision tasks recently and achieved high accuracy in some public available datasets in a supervised manner. The performance drops significantly when datasets are unlabeled, which limits the scalability of Re-ID algorithms in practical applications. Despite some unsupervised methods are proposed to address the scalability problem

This paper focuses on the construction of strong local features and the effective fusion of image and LiDAR data for 3D object detection. We adopt different modalities of LiDAR data to generate rich features and present an adaptive and azimuth-aware network to aggregate local features from image, bird’s eye view maps and point cloud. Our network mainly consists of three subnetworks: ground plane estimation

Spatial pooling is an important step in computer vision systems like Convolutional Neural Networks or the Bag-of-Words method. The spatial pooling purpose is to combine neighbouring descriptors to obtain a single descriptor for a given region (local or global). The resultant combined vector must be as discriminant as possible, in other words, must contain relevant information, while removing irrelevant

Distance metric learning aims to learn a measure of the pairwise distance between data instances, which is essential for various machine learning algorithms and applications. However, existing linear metric learning methods based on linear transformations fail to capture nonlinear relationships between instances, while most existing kernel-based metric learning algorithms may ignore the correlation

Person reidentification (ReID) refers to the task of verifying the identity of a pedestrian observed from nonoverlapping views in a surveillance camera network. It has recently been validated that reranking can achieve remarkable performance improvements in person ReID systems. However, current reranking approaches either require feedback from users or suffer from burdensome computational costs. In

Traditional screening of cervical cells largely depends on the experience of pathologists, which also has the problem of low accuracy and poor efficiency. Medical image processing combining deep learning and machine learning shows its superiority in the field of cell classification. A new framework based on strong feature Convolutional Neural Networks (CNN)-Support Vector Machine (SVM) model was proposed

Cell segmentation is a critical step in histology images analysis. Recently, Convolutional Neural Network (CNN) has shown outstanding performance for various segmentation problems, however, the segmentation of histology images remains challenging due to the tight arrangement of cells and their weak boundaries. This paper proposes a novel architecture called Attention-based Mixture of Experts (Att-MoE)

In this article, we present an event-triggered scheme for fractional order nonlinear systems under full-state constraints. The neural networks are employed to approximate the continuous nonlinear unknown functions in the system. Moreover, a new adaptive event-triggered strategy is designed under the unified framework of backstepping control method, which can largely reduce the amount of communications

In industrial production, it is difficult to obtain a well-trained surface detection algorithm since the real defect samples are lacking. In this paper, we propose a surface defect segmentation method based on defect sample simulation, which only needs few defect training samples. The entire method includes two modules: a local defect simulation algorithm and a residual-restored-based segmentation

In this paper, we propose a new method for online multiple people tracking, which combines the detection process and the single object tracking process, and establishes the interactions between them. The detector detects objects in the still images which ignores the sequential information. Meantime, the single object tracker does not use the category semantic information during tracking. To take both

This paper discussed the cooperative control problem for swarming systems in unknown dynamic environment. The swarm agents are required to move in a completely distributed manner with the reference trajectory determined by a virtual dynamic leader. In addition to keeping an appropriate distance from neighboring agents, each agent needs to avoid collision with dynamic threats in unknown environment

Multi-scale feature fusion has been proven effective in substantial person re-identification (ReID) works. However, the existing multi-scale feature fusion is based on features of different semantic levels. We propose a novel multi-scale and multi-branch feature representation for person ReID, namely Ms-Mb. It merges the features of the same semantic level and integrates attention modules to learn