The zero-shot semantic segmentation requires models with a strong image understanding ability. The majority of current solutions are based on direct mapping or generation. These schemes are effective in dealing with the zero-shot recognition, but they cannot fully transfer the visual dependence between objects in more complex scenarios of semantic segmentation. More importantly, the predicted results

Applications of Cloud Services are increasing day by day, and so is the difficulty of choosing the best-suited service for a customer. Quality of Service (QoS) parameters can be used for quality assurance and evaluation; further, a service can be recommended based on these QoS parameters’ values. Recommendation systems are getting much attention lately. It has a crucial role in almost all the major

Clustering is a challenging and crucial task in unsupervised learning. Recently, though many clustering algorithms combined with deep learning have been proposed, we observe that the existing deep clustering algorithms do not considerably preserve the clustering structure and information of raw data in the learned latent space. To address this issue, we propose a Generative Adversarial Attention Clustering

The 3D deformable image registration is one of the most challenging tasks in medical image analysis. Due to the large and complex deformation in 3D medical images, many deep neural network based methods have been proposed to improve the image similarity after registration, among which recursive cascading network structure is one of the state-of-the-art. However, most existing works rely on the pixel-level

The human parsing task is dedicated to allocating pixel-level fine-grained semantic labels. However, recent solutions are limited to fully utilize the prior information (poses and edges) and the potential information of the image data, remaining problems with ambiguous boundaries, incomplete human parts, and redundant labels. To solve the above problems, we propose a novel Multi-view Stack Network

As neuron is the fundamental unit of the nervous system, it is one of the main building blocks in the spiking neural networks hardware implementation. To implement hardware that consists of many thousands of neurons and accurately mimics the brain functions, an energy and area-efficient design for the neuron is essential. In this paper, we propose a VLSI circuit for the leaky integrate and fire (LIF)

Text-to-SQL emerges to play an important role in interactive data analysis, which provides a friendly interface for converting natural language into relational database language (i.e., SQL). In order to translate a user’s query into an executable SQL statement, semantic parsing is essential to the transformation process. In particular, existing efforts provide some feasible solutions, and state-of-the-art

Federated learning is an emerging distributed machine learning framework for privacy preservation. However, models trained in federated learning usually have worse performance than those trained in the standard centralized learning mode, especially when the training data are not independent and identically distributed (Non-IID) on the local devices. In this survey, we provide a detailed analysis of

Meta-learning aims to leverage experience from previous tasks to achieve an effective and fast adaptation ability when encountering new tasks. However, it is unclear how the generalization property applies to new tasks. Probably approximately correct (PAC) Bayes bound theory provides a theoretical framework to analyze the generalization performance for meta-learning with an explicit numerical generalization

Exponential stability for neural networks with time-varying delay is considered in this paper. By extending the generalized free-weighting-matrix integral inequality, a novel integral inequality is derived by using weighted orthogonal functions. Then the new inequality is applied to investigate the exponential stability of time delay neural networks via an improved Lyapunov-Krasovskii functional. Numerical

The extraction and prediction of health indicators (HIs) are two vital aspects in remaining useful life (RUL) prediction of lithium-ion batteries (LIBs). Aiming to estimate the RUL precisely, a novel integrated prediction method is proposed for LIBs on the basis of local tangent space alignment (LTSA) feature extraction and adaptive sliding window long short-term memory neural networks (ASW LSTM NN)

Variable selection plays an important role in analyzing high dimensional data and is a fundamental problem in machine learning. When the data possesses certain group structures in which individual variables are also meaningful scientifically, we are naturally interested in selecting important groups as well as important variables within the selected groups. This is referred to as the bi-level variable

Multimodal Sentiment Analysis (MSA) is a challenging research area that investigates sentiment expressed from multiple heterogeneous sources of information. To integrate multimodal information including text, visual and audio modalities, state-of-the-art models focus on developing various fusion strategies, such as attention and outer product. However, the inferior quality of visual and audio features

Remote sensing (RS) images have been widely used in disaster monitoring due to their wide observation and timeliness. Wildfire is a type of destructive disaster, and smoke is an important signal of the occurrence of wildfires; therefore, it is necessary to perform smoke detection in RS images. Smoke-like scenes such as clouds captured by satellites make RS smoke detection a tough task. Differences

Using multimodal Magnetic Resonance Imaging (MRI) is necessary for accurate brain tumor segmentation. The main problem is that not all types of MRIs are always available in clinical exams. Based on the fact that there is a strong correlation between MR modalities of the same patient, in this work, we propose a novel brain tumor segmentation network in the case of missing one or more modalities. The

Dynamic networks are popularly used to describe networks that change with time. Although there have been a large number of research works on understanding dynamic networks using link prediction, node classification and community detection, there is rare work that is specially designed to address the challenge of big network size of dynamic networks. To this end, we study in this paper an emerging and

The distributed discrete-time heterogeneous multi-agent optimization problem with unbounded position constraints and nonconvex velocity constraints was considered in this paper, where the models of agents are described by first- or second- order difference equations, the position constraints are assumed to be unbounded and convex and the velocity constraints are assumed to be bounded, closed and nonconvex

Deep learning models have been demonstrated vulnerable to adversarial attacks even with imperceptible perturbations. As such, the reliability of existing deep neural networks-based autonomous driving systems can suffer. However, deep 3D models have applications in various Cyber-Physical Systems (CPSs) with safety-critical requirements, particularly autonomous driving systems. In this paper, the robustness

In this study, we propose a time-varying neural network (TVNN) for solving the time-varying minimum spanning tree problem with constraints (CTMST), which is a variant of the time-varying network minimum spanning tree problem (TNMSTP), a well-known NP-hard problem. Unlike traditional algorithms that use heuristic search, the proposed TVNN is based on time-varying neurons and can achieve parallel computing

This paper empirically analyses the impact of changes to the set of training examples on the neural network error surface. Specific quantitative characteristics of the error surface related to properties such as ruggedness, modality and structure are measured and visualized as the set of training examples changes. Both the case of random subsampling and active learning from a fixed dataset are examined

This paper proposes a text removal model, Text Remove Network (TRNet), which achieves an unprecedented clearing effect of picture text. The network uses a jump-connected U-net structure to encode and decode the generator, so as to obtain clearer and sharper texture details of the original image. To solve the problem of color distortion, the generator removes the batch normalization layer and uses ELUs

With the goal of developing an accurate and fast image reconstruction algorithm for ultrasound computed tomography (USCT), we combine elements of model- and data- driven approaches and propose a learned method which addresses the disadvantages of both approaches. We design a deep neural network (DNN) which accounts for a nonlinear forward operator and primal dual algorithm by its inherent network architecture

The technology for Visual Odometry (VO) that estimates the position and orientation of the moving object through analyzing the image sequences captured by on-board cameras, has been well investigated with the rising interest in autonomous driving. This paper studies monocular VO from the perspective of Deep Learning (DL). Unlike most current learning-based methods, our approach, called DeepAVO, is

Methods based on Graph Convolutional Networks(GCN) for skeleton-based action recognition have achieved great success due to their ability to exploit graph structural information from skeleton data. Recently, the bone information has attracted considerable attention as an effective modality which complements the more conventional joint information for action recognition. However, most existing GCN-based

In this paper we propose a framework using multi-channel convolutional neural network (MC–CNN) for recognizing the grammatical class (verb or noun) of covertly-spoken words from electroencephalogram (EEG) signals. Our proposed network extracts features by taking into account spatial, temporal, and spectral properties of the EEG signal. Further, sets of signals acquired from different regions of the

Deep learning has achieved a remarkable success in areas such as brain-computer interface systems (BCI). However, electroencephalography (EEG) signals evoked by motor imagery (MI) are sometimes limited in their amount due to invalid data caused by the subjects’ fatigue, leading to a performance degradation. To this end, in this work we extend empirical mode decomposition into multivariate empirical

Accurate estimation of remaining useful life (RUL) of industrial equipment can enable advanced maintenance schedules, increase equipment availability and reduce operational costs. However, existing deep learning methods for RUL prediction are not completely successful due to the following two reasons. First, relying on a single objective function to estimate the RUL will limit the learned representations

Pipeline, joint, and collapsed models are three major approaches to solving End-to-End Aspect-based Sentiment Analysis (E2E-ABSA) task. Prior works found that joint models were consistently surpassed by the other two. To explore the potential of joint model for E2E-ABSA, we propose a hierarchical and parallel joint framework on the basis of exploiting the hierarchical nature of the pre-trained language

Existing state-of-the-art methods for salient object detection mainly achieve significant progress by integrating multi-level features. However, most of them simply resize the multi-level features to the same spatial resolution and aggregate them by channel-wise concatenation or element-wise addition. Thus, they are limited to integrating features of adjacent layers due to large discrepancy between

This article introduces a kind of aperiodically sampled-data intermittent control to investigate the synchronization issue of stochastic multi-links network. Therein, the sampling intervals are variable in the aperiodically intermittent control, while the actuator saturation is taken into consideration. Distinguish from previous control methods, by combining with the advantages of both the sampled-data

Video engagement is important in online advertisements where there is no physical interaction with the consumer. Engagement can be directly measured as the number of seconds after which a consumer skips an advertisement. In this paper, we propose a model to predict video engagement of an advertisement using only a few samples. This allows for early identification of poor quality videos. This can also

Image super-resolution from low-resolution fundus image has valuable applications in clinical practices. The popular methods yield unsatisfactory results when the fundus images are contaminated due to the bleeding or plaques caused by eye diseases. To this end, we propose a style-guided UNet (SGUNet) which incorporates a series of style-guided U-shape block (SUB) for fundus image super-resolution.

Dialogue systems have made massive promising progress contributed by deep learning techniques and have been widely applied in our life. However, existing end-to-end neural models suffer from the problem of tending to generate uninformative and generic responses because they cannot ground dialogue context with background knowledge. In order to solve this problem, many researchers begin to consider combining

Interval-valued data are needed to manage either the uncertainty related to measurements, or the variability inherent to the description of complex objects representing group of individuals. A number of regression methods suitable to interval variables describing variability of complex objects are already available. However, less attention has been given to methods that, simultaneously, take into account

Graph alignment, also known as network alignment has many applications in data mining tasks. It aims to find the node correspondence across disjoint graphs. Recently, various methods like representation learning methods, spectral methods have been proposed to solve the graph alignment problem, but they either only consider the local structure information but ignore the neighborhood similarity, or their

This paper investigates flocking problems with uncertain nonlinear multi-agent systems. Two distributed adaptive event-triggered control algorithms are proposed for leaderless and leader-follower flocking, separately. According to Lyapunov stability theory, under the proposed control protocols, we obtain some sufficient conditions to ensure stable flocking motion and maintain connectivity of network

Unlike the existing change detection approaches based on the multispectral (MS) image and synthetic aperture radar (SAR) image datasets, a novel unsupervised hyperspectral change detection (UHCD) framework is proposed in this paper. The UHCD framework is designed for hyperspectral images with high dimensions and low availability. This framework consists of two modules: the spectral mapping with adversarial

We propose a novel framework to transfer the portrait image into its correspondence with photo-realistic and cartoon style. The existing work on neural style transfer conducts impressive results on artistic style transfer; however, the lack of semantic clues will lead to the color artifacts in photo-realistic style transfer because of the complex background and noise issues. In this work, we re-define

Fuzzy rough set is a theoretical framework of fuzzy uncertainty management, and discernibility matrix offers a mathematical foundation for algorithm construction of feature learning. The approaches of fuzzy rough set and discernibility matrix have been successfully applied in single-label learning. However, few works have been done on investigating the foundation of fuzzy rough discernibility matrix

Adaptive response to the timely constant stimulus is the common feature of real neurons. The circuit of the adaptive neuron model consumes less power and requires less data transmission bandwidth compared to the circuit of the non-adaptive neuron model, especially for encoding time-varying signals. Memristor is a good candidate for mimicking the behavior of neurons so that the simple memristor-based

In person search task, it is hard to retrieve the query persons undergoing large visual changes. To tackle this problem, we propose to exploit the context information to rectify the original individual similarity for better retrieval. To this end, we propose to model a query frame and a gallery frame as a graph pair, and then design the Siamese Residual Graph Convolutional Networks (SR-GCN) to aggregate

Inferring the intended actions of road-sharing users with autonomous ground vehicles in particularly vulnerable ones like cyclists is considered one of the tough tasks facing the wide-spread deployment of autonomous ground vehicles. One of the main reasons for that is the scarcity of the available datasets for that task due to the difficulty in obtaining those datasets in real environments. In this

Synthetic aperture radar (SAR) image recognition is an important stage of SAR image interpretation. The standard convolutional neural network (CNN) has been successfully applied in the SAR image recognition due to its powerful feature extraction capability. Nevertheless, the CNN requires numerous labeled samples for satisfactory recognition performance, while the performance of the CNN decreases greatly

Current deep deblurring methods pay main attention to learning a transferring network to transfer synthetic blurred images to clean ones. Though achieving significant performance on the training datasets, they still suffer from a weaker generalization capability from training datasets to others with different synthetic blurs, thus resulting in significantly inferior performance on testing datasets

In this paper, the stability for a class fractional-order inertial neural networks with time-delay are investigated. Moreover, some sufficient conditions for the Mittag-Leffler stability and the asymptotical ω-periodicity are obtained, by the appropriate transformation, using the property of the Riemann-Liouville fractional integral and derivative. In the end, results of the theoretical derivation

As the main research content of artificial intelligence, the artificial neural network has been widely concerned because of its excellent performance in the fields such as computer vision and natural language processing since it was proposed in the 1940s. The neuron model of the traditional neural network was proposed by McCulloch and Pitts in 1943 (MP neurons), But MP neurons is too simple to representing

Vehicle Re-Identification (V-ReID) is a critical task that associates the same vehicle across images from different camera viewpoints. Many works explore attribute clues to enhance V-ReID; however, there is usually a lack of effective interaction between the attribute-related modules and final V-ReID objective. In this work, we propose a new method to efficiently explore discriminative information

Under the Joint Photographic Experts Group (JPEG) framework, this paper proposes a simple yet efficient focus measure (FM) in discrete cosine transform (DCT) domain for fast multi-focus image fusion. At first, the DCT coefficients of multi-focus source images in JPEG format are read directly. Then, the initial decision map is constructed according to the proposed FM using only a few low-order DCT coefficients

The deep learning era endows immense opportunities for ubiquitous robotic applications by leveraging big data generated from widespread sensors and ever-growing computing capability. While the growing demands for natural human-robot interaction (HRI) as well as concerns for energy efficiency, real-time performance, and data security motive novel solutions. In this paper, we present a brain-inspired

Deep learning is an effective tool to assist doctors with many time-consuming and error-prone medical image analytical tasks. However, deep models are shown to be vulnerable to adversarial attacks, posing significant challenges to clinical applications. Existing works regarding the robustness of deep learning models are scarce, where most of them focus on the attack of medical image classification

With the explosive growth of videos captured everyday, how to efficiently extract useful information from videos has become a more and more important problem. As one of the most effective methods, video summarization aiming to extract the most important frames or shots has attracted more interests recently. Currently, lots of methods employ a recurrent structure. However, due to its step-by-step characteristic

The long short-term memory (LSTM) network underpins many achievements and breakthroughs especially in natural language processing fields. Essentially, it is endowed with certain memory capabilities to boost its performance. Currently, the volume and speed of big data generation are increasing exponentially, and such data require efficient models to acquire memory augmented knowledge. In this paper

At present, saliency detection methods have achieved gratifying progress benefiting from the development of deep learning. However, the existing methods always fail to make full use of the label information. To address this problem, we focus on the complementarity of salient body information and salient detail information within the labels and propose the Interactive Branch Network (IBNet) in this

In this paper, the leader-following consensus of nonlinear multi-agent systems with time delay and aperiodically intermittent communications is investigated. Compared with the intermittent communications for multi-agent systems in previous literature, we relax the periodicity or quasi-periodicity of the intermittent communications and render the intermittent communications to be completely aperiodic

Recent studies have confirmed that attention mechanisms with location constraint strategy are helpful to reduce the misrecognition caused by incorrect alignments in attention-based end-to-end automatic speech recognition (E2E ASR) systems. The significant advantage of these mechanisms is that they consider the monotonicity of the alignment by employing a location constraint vector. This vector is directly