Stereo superpixel segmentation aims to obtain the superpixel segmentation results of the left and right views more cooperatively and consistently, rather than simply performing independent segmentation directly. Thus, the correspondence between two views should be reasonably modeled and fully considered. In this paper, we propose a left-right interactive optimization framework for stereo superpixel

The minimum spanning tree clustering algorithm is known to be capable of detecting clusters with irregular boundaries. The paper presents a novel hierarchical clustering algorithm based on minimum spanning tree (MST), which tends to reduce the complexity of the merging process with guaranteed clustering performance. There are two core ideas in the proposed method: (1) The inter-cluster distance is

With the continued development of unmanned aerial vehicle (UAV) technologies, the UAV on-board automation is increasingly more capable of performing tasks formerly done by human operators. Thereby, the role of UAVs is changing from being mere tools to become members of integrated manned-unmanned systems. However, the high automation necessary to achieve this cooperation, introduces a new set of negative

Domain adaptation aims at leveraging rich knowledge in the source domain to build an accurate classifier in the different but related target domain. Most prior methods attempt to align features or reduce domain discrepancy by means of statistical properties yet ignore the differences among samples. In this paper, we put forward a novel solution based on collaborative representation for classifier adaptation

Intensive research interests have been paid for the vision and language communities. Especially, image captioning task aims to generate natural language descriptions from the image content. Oppositely, image synthesis task aims to generate realistic images from natural language descriptions. Moreover, both of them can achieve promising results by using Long Short-Term Memory (LSTM), which models the

This paper considers an optimal pricing problem for the black box producer-consumer Stackelberg game. A producer sets price over a set of goods to maximize profit (the difference in revenue and cost function). The consumer buys a quantity to maximize the difference between the value of the quantity consumed and the cost. The value function of the consumer and the cost function of the producer are ‘black

Current visual servoing methods used in robot manipulation require system modeling and parameters, only working in structured environments. This paper presents a nonparametric visual servoing for a robot manipulator operated in unstructured environments. A Gaussian-mapping likelihood process is used in Bayesian stochastic state estimation (SSE) for Robotic coordination control, in which the Monte Carlo

Head pose estimation is a crucial problem for many tasks, such as driver attention, fatigue detection, and human behaviour analysis. It is well known that neural networks are better at handling classification problems than regression problems. It is an extremely nonlinear process to let the network output the angle value directly for optimization learning, and the weight constraint of the loss function

Face alignment has been applied widely in the field of computer vision, which is still a very challenging task for the existence of large pose, partial occlusion, and illumination, etc. The method based on deep regression neural network has achieved the most advanced performance in the field of face alignment in recent years, and how to learn more representative facial appearance is the key to face

The issue of the global dissipativity of memristive neutral-type inertial neural networks with distributed and discrete time-varying delays is discussed without converting the original system to first-order equations. By taking some new Lyapunov-Krasovskii functionals and adopting inequality techniques, several effective criteria formulated by testable algebraic inequalities are derived to assure the

Many performance improvement techniques calibrate the outputs of convolutional layers to improve the performance of convolutional neural networks, e.g., Squeeze-and-Excitation Networks (SENets). These techniques train the network to extract calibration weights from the input itself. However, these methods increase the complexity of the model in order to perform calibration. We propose an approach to

Due to the complex dynamic behavior of a wastewater treatment process (WWTP), the existing soft-sensing models usually fail to efficiently and accurately predict its effluent water quality. Especially when a lot of practical data is provided and we do not know which data-pair is more valuable, WWTP modeling becomes a time-consuming process. The main reason is that the existing soft-sensing models update

Story ending generation is a challenging and under-explored task, which aims at generating a coherent, reasonable, and logical story ending given a context. Previous studies mainly focus on utilizing the contextual information and commonsense knowledge to generate story endings. However, there are still some issues must be addressed in the story endings generation processing, such as sentimental consistency

The task of session-based recommendation is predicting the next recommendation item when available information only includes the anonymous behavior sequence. Previous methods of session-based recommendation usually integrate the general interest, dynamic interest, and current interest to promote recommendation performance. However, most existing methods ignore the non-monotone feature interactions

Hyperspectral remote sensing is an important earth observation method with wide application. But the low spatial resolution of hyperspectral images makes it difficult to distinguish the ground objects. The hyperspectral image unmixing is a task to estimate the spectral signatures and corresponding fractional abundances. However, the unmixing speed and efficiency are still limited by traditional structures

Evolutionary algorithm (EA) incorporating with k-means local search operator represents an important approach for cluster analysis. In the existing EA approach, however, the k-means operators are usually directly employed on the individuals and generally applied with fixed intensity as well as frequency during evolution, which could significantly limit their performance. In this paper, we first introduce

Predicting users’ preference in a context of the uncertainty of user and the limited information is a challenging work in many online services, e.g., e-commerce and media streaming. Recent advances in session-based recommendation mostly focus on mining more available information within the current session. However, those methods ignored the sessions with similar context for the current session, which

Face sketch synthesis aims to generate a face sketch image from a corresponding photo image and has wide applications in law enforcement and digital entertainment. Despite the remarkable achievements that have been made in face sketch synthesis, most existing works pay main attention to the facial content transfer, at the expense of facial detail information. In this paper, we present a new generative

The suppression of interference for speech recognition is of great significance in noisy situation, especially in single channel receiving mode, the suppression of interference is much more difficult. In this paper, we propose a generative adversarial network (GAN) based method for single channel dereverberation and speech separation. Different from the existing methods, our method considers the influence

Zero-shot learning and self-supervised learning have been widely studied due to the advantage of performing representation learning in a data shortage situation efficiently. However, few studies consider zero-shot learning using semantic embeddings (e.g., CNN features or attributes) and self-supervision simultaneously. The reason is that most zero-shot learning works employ vector-level semantic embeddings

Compared with general joint-link robotic systems, bio-inspired musculoskeletal robotic systems offer the advantages of higher robustness, flexibility, and redundancy. Hence, they are a promising option for the development of next-generation robots. However, theoretical analysis regarding the superiorities of musculoskeletal systems is scarce. This study analyzes and proves the anti-interference of

Learning-based methods have attracted considerable interest in image dehazing. However, most existing methods are not well adapted to different hazy conditions, especially when dealing with the heavily hazy scene. There is often a significant amount of haze that remains in the images recovered by most methods. To address this issue, we propose an end-to-end Haze Concentration Adaptive Network (HCAN)

Brain plasticity or neuroplasticity refers to the ability of the nervous system to reorganise itself in response to stimuli. For instance, sensory and motor stimulation, memory formation, and learning depend on brain plasticity. Neuronal synchronisation can be enhanced or suppressed by the plasticity. Synchronisation is related to many functions in the brain, as well as to some brain disorders. One

Remote sensing image scene classification is challenging due to the complicated spatial arrangement and varied object sizes inside a large-scale aerial image. Among the bottlenecks for current deep learning methods to depict and discriminate the complexity of remote sensing scenes, strengthening the local semantic representation and multi-scale feature representation is necessary. In this paper, we

This paper is concerned with the problem of stochastic stability analysis for fractional-order Markovian jumping complex-valued neural networks (MJCVNNs) with time-varying delays. The novelty of this study is emphasized in two phases. In first phase, MJCVNNs is considered in the form of fractional-order systems. Secondly, complex-valued Wirtinger based integral inequality is newly constructed. The

The boundary quality is a key factor determining the success of accurate salient object detection (SOD). A number of edge-guided SOD methods have been proposed to improve the boundary quality, but shown unsatisfactory performance due to the lack of a comprehensive consideration of multi-level feature fusion and multi-type feature aggregation. To resolve this issue, we propose a novel Bidirectional

This paper presents the theoretical results on the multistability of state-dependent switching neural networks with discontinuous nonmonotonic piecewise linear activation functions. For n-neurons switching model, this paper shows that neural networks have 7n equilibrium points, 6n of which are located at the continuous points of activation functions and others are located at the discontinuous points

Making full use of the spatial information of the depth data is crucial for 3D hand pose estimation from a single depth image. In this paper, we propose a Spatial-aware Stacked Regression Network (SSRN) for fast, robust and accurate 3D hand pose estimation from a single depth image. By adopting a differentiable pose re-parameterization process, our method efficiently encodes the pose-dependent 3D spatial

Orientation field is the key foundation of palmprint feature extraction and recognition. However, due to the presence of numerous wide creases, the palmprint orientation field can hardly be accurately estimated by previous methods, especially in the thenar region, which still faces huge challenges. To solve this problem, we formulate palmprint orientation field recovery as an inpainting task and propose

Recently, due to its widespread applications in public safety, anomaly detection in crowd scenes has become a hot topic. Some deep-learning-based methods attain significant achievements in this field. Nevertheless, most of them suffer from over-fitting to some extent because of scarce data, which are usually abrupt and low-frequency in the real world. To remedy the above problem, this paper firstly

Despite the promising performance for clustering, weighted tensor nuclear norm based multi-view subspace clustering needs to artificially predefine a weighted vector when shrinking all the singular values of tensor. It is very difficult to select a suitable weighted vector due to the complex and unknown distribution of data in real applications. Another limitation is that, the learned affinity matrix

In this work, we propose a progressive principal component analysis (PPCA) method for compressing deep convolutional neural networks. The proposed method starts with a prespecified layer and progressively moves on to the final output layer. For each target layer, PPCA conducts kernel principal component analysis for the estimated kernel weights. This leads to a significant reduction in the number of

Action Unit (AU) detection plays an important role in facial behaviour analysis. In the literature, AU detection has extensive researches in macro-expressions. However, to the best of our knowledge, there is limited research about AU analysis for micro-expressions. In this paper, we focus on AU detection in micro-expressions. Due to the small quantity and low intensity of micro-expression databases

This paper proposes a solution to translating the visible images into infrared images, which is challenging in computer vision. Our solution belongs to unsupervised learning, which has recently become popular in image-to-image translation. However, existing methods do not produce satisfactory results because (1) most existing methods are mainly used in entertainment scenarios with single scenes and

In this paper, a robust non-singular fast terminal sliding mode control scheme with adaptive neural networks is presented for a class of nonlinear systems with unknown bounds of uncertainties. To reduce transmission and computation burden in resource-constrained networked systems, two kinds of event-triggering mechanisms are taken into consideration in the proposed adaptive sliding mode control scheme

An increasing number of change detection models are designed with different convolutional neural network (CNNs). However, the mechanism for designing network layers that can effectively extract robust features for different scenes remains unclear. Thus, novel networks with fluid pyramid integration network (FPIN) to detect changes are proposed in this study. Specifically, we first extract multi-scale

In this work, we propose a novel autoregressive event time-series model that can predict future occurrences of multivariate clinical events. Our model represents multivariate event time-series using different temporal mechanisms aimed to fit different temporal characteristics of the time-series. In particular, information about distant past is modeled through the hidden state space defined by an LSTM-based

This paper proposes a logical framework for representing and reasoning about imperfect information games. We first extend Game Description Language (GDL) with the standard epistemic operators and provide it with a semantics based on the epistemic state transition model. We then demonstrate how to use the language to represent the rules of an imperfect information game and formalize common game properties

In this work, we investigate the quadratic bilinear optimal control. We first review the case of finite‐time interval, and then focus on the case of infinite‐time horizon. The main difficulty in solving a quadratic optimal control for bilinear systems is the non‐convexity of the cost function, which due to the fact that the dependence of the state with respect to the control is highly nonlinear. Then

Reflecting on 2020 brings into focus clear challenges for the year ahead, including for AI research that contemplates its broader societal impact.

Flying insects employ elegant optical-flow-based strategies to solve complex tasks such as landing or obstacle avoidance. Roboticists have mimicked these strategies on flying robots with only limited success, because optical flow (1) cannot disentangle distance from velocity and (2) is less informative in the highly important flight direction. Here, we propose a solution to these fundamental shortcomings

We invited authors of selected Comments and Perspectives published in Nature Machine Intelligence in the latter half of 2019 and first half of 2020 to describe how their topic has developed, what their thoughts are about the challenges of 2020, and what they look forward to in 2021.

Retrospective artefact correction (RAC) improves image quality post acquisition and enhances image usability. Recent machine-learning-driven techniques for RAC are predominantly based on supervised learning, so practical utility can be limited as data with paired artefact-free and artefact-corrupted images are typically insufficient or even non-existent. Here we show that unwanted image artefacts can

Sliding mode control (SMC) has been a very popular control technology due to its simplicity and robustness against uncertainties and disturbances since its inception more than 60 years ago. Its very foundation of stability and stabilization is built on the principle of the Lyapunov theory which ascertains asymptotic stability. In the 1990s, a novel class of SMC, called the terminal sliding mode control

Aircraft electrification has been a major trend in aviation industry for past 20 years. Given the increasing electrical power requirement for future more electric aircraft and hybrid electric aircraft, research efforts has been ongoing in high power electrical conversion for air-borne systems. Safety critical nature of aviation systems places reliability of aerospace power converters as a critical

This paper collated and analysed information regarding the abilities, gameplay and game genre preferences perceived to be important by amateur gamers and whether these perceptions differed based on several criteria, including time spent gaming and the types of games people played. First-person Shooter (FPS), Multiplayer Online Battle Arena (MOBA) and Real-time Strategy (RTS) games were examined among

The motivation to stimulate children’s learning engagement could be found in the fact that learning is not always motivational in itself. This is particularly true when learning is obligatory and based upon material that has not been chosen by the children themselves. A Lean UX approach to the co-design of an educational serious videogame (MOBI) is proposed in this paper. The core idea is that children's

Over the past thirty years, research situated in many individual sub-domains of psychology has investigated the potential impact of video game play on behavior. Interestingly, although researchers in the various sub-fields are (presumably) versed in the results of the published research, there nonetheless remain significant individual differences in opinion across researchers regarding what exactly

Central Pattern Generators (CPGs) models have been long used to investigate both the neural mechanisms that underlie animal locomotion as well as a tool for robotic research. In this work we propose a spiking CPG neural network and its implementation on neuromorphic hardware as a means to control a simulated lamprey model. To construct our CPG model, we employ the naturally emerging dynamical systems

Differential evolution (DE) is an effective global evolutionary optimization algorithm using to solve global optimization problems mainly in a continuous domain. In this field, researchers pay more attention to improving the capability of DE to find better global solutions, however, the computational performance of DE is also a very interesting aspect especially when the problem scale is quite large

Deep-predictive-coding networks (DPCNs) are hierarchical, generative models that rely on feed-forward and feed-back connections to modulate latent feature representations of stimuli in a dynamic and context-sensitive manner. A crucial element of DPCNs is a forward-backward inference procedure to uncover sparse states of a dynamic model, which are used for invariant feature extraction. However, this

5G cellular networks are being deployed all over the world and this architecture supports ultra-dense network (UDN) deployment. Small cells have a very important role in providing 5G connectivity to the end users. Exponential increases in devices, data and network demands make it mandatory for the service providers to manage handovers better, to cater to the services that a user desire. In contrast

Many existing deep learning models are vulnerable to adversarial examples that are imperceptible to humans. To address this issue, various methods have been proposed to design network architectures that are robust to one particular type of adversarial attacks. It is practically impossible, however, to predict beforehand which type of attacks a machine learn model may suffer from. To address this challenge

Neuromorphic computing with spintronic devices has been of interest due to the limitations of CMOS-driven von Neumann computing. Domain wall-magnetic tunnel junction (DW-MTJ) devices have been shown to be able to intrinsically capture biological neuron behavior. Edgy-relaxed behavior, where a frequently firing neuron experiences a lower action potential threshold, may provide additional artificial

A novel notion of dense fuzzy lock set was introduced as an extension of fuzzy sets. Learning experiences have a vital role in this fuzzy lock set instigation. The novel fuzzy lock set reduces the fuzziness of the situation. Occasionally, the players are bound to make little changes in their game strategies to reach their goal for some matrix game problems. It may lead to some changes in payoffs. In

Negation in general represents the contradiction and denial of anything. In classical logic, negation is identified as the logical connective that takes truthfulness to falsehood. However, there can be situations in which we have to deal with the possibility of any truth value besides true or false. The probability theory has been effective in modelling such situations. Therefore exploring the concept

Representation learning (RL) methods learn objects' latent embeddings where information is preserved by distances. Since distances are invariant to certain linear transformations, one may obtain different embeddings while preserving the same information. In dynamic systems, a temporal difference in embeddings may be explained by the stability of the system or by the misalignment of embeddings due to

Multimodal generative models should be able to learn a meaningful latent representation that enables a coherent joint generation of all modalities (e.g., images and text). Many applications also require the ability to accurately sample modalities conditioned on observations of a subset of the modalities. Often not all modalities may be observed for all training data points, so semi-supervised learning