Search

This paper proposes a novel algorithm of discovering the structure of a kaleidoscopic imaging system that consists of multiple planar mirrors and a camera. The kaleidoscopic imaging system can be recognized as the virtual multi-camera system and has strong advantages in that the virtual cameras are strictly synchronized and have the same intrinsic parameters. In this paper, we focus on the extrinsic calibration of the virtual multi-camera system. The problems to be solved in this paper are two-fold. The first problem is to identify to which mirror chamber each of the 2D projections of mirrored 3D points belongs. The second problem is to estimate all mirror parameters, i.e., normals, and distances of the mirrors. The key contribution of this paper is to propose novel algorithms for these problems using a single 3D point of unknown geometry by utilizing a kaleidoscopic projection constraint, which is an epipolar constraint on mirror reflections. We demonstrate the performance of the proposed algorithm of chamber assignment and estimation of mirror parameters with qualitative and quantitative evaluations using synthesized and real data. [ABSTRACT FROM AUTHOR]

Due to the lack of distinctiveness to the background, robust monocular 6DOF pose tracking of less-distinct objects remains an important open problem. In this paper, we firstly analyze the object distinctiveness in the tracking process. Then, we propose a novel contour-part model based robust monocular pose tracking method for less-distinct objects. This paper uses the traditional contour feature for pose tracking in a novel strategy called contour part model. First, the contour part model is built by segmenting the projected contour rendered from the 3D model into contour segments of a certain length adaptively according to the Shi-Tomasi cornerness scores. Then, the correspondence is detected in the input image for each contour part by gradient orientation based template matching. Finally, pose tracking is achieved by solving the PnP problem. Experiment results on semi-synthetic and real images show that the proposed method performs better than the existing methods when pose tracking less-distinct objects and shows great robustness toward interference. Additionally, we combine the edge feature and the regional feature in a simple strategy. The overall performance of the fused method is boosted according to the experimental results on the RBOT dataset. The fact shows that the fusion of the edge and regional features has great potential for improving tracking performance. [ABSTRACT FROM AUTHOR]

With the abundance of data, machine learning applications engaged increased attention in the last decade. An attractive approach to robustify the statistical analysis is to preprocess the data through clustering. This paper develops a low-complexity Riemannian optimization framework for solving optimization problems on the set of positive semidefinite stochastic matrices. The low-complexity feature of the proposed algorithms stems from the factorization of the optimization variable $\mathbf {X}=\mathbf {Y}\mathbf {Y}^{\mathrm{T}}$ X = Y Y T and deriving conditions on the number of columns of $\mathbf {Y}$ Y under which the factorization yields a satisfactory solution. The paper further investigates the embedded and quotient geometries of the resulting Riemannian manifolds. In particular, the paper explicitly derives the tangent space, Riemannian gradients and Hessians, and a retraction operator allowing the design of efficient first and second-order optimization methods for the graph-based clustering applications of interest. The numerical results reveal that the resulting algorithms present a clear complexity advantage as compared with state-of-the-art euclidean and Riemannian approaches for graph clustering applications. [ABSTRACT FROM AUTHOR]

Battery energy storage system (BESS) plays an important role in solving problems in which the intermittency has to be considered while operating distribution network (DN) penetrated with renewable energy. Aiming at this problem, this paper proposes a global centralized dispatch model that applies BESS technology to DN with renewable energy source (RES). The method proposed in this paper aims to minimize the power purchase cost considering network active loss cost as well as voltage deviation penalty cost. Later, second-order cone programming (SOCP) method as well as big M method are applied to make the problem tractable. Last, the method illustrated in this paper is applied and validated on a modified IEEE 33-bus benchmark system to verify the effectiveness of the proposed scheduling model. [ABSTRACT FROM AUTHOR]

The stability problem of low-voltage multi-terminal DC (MTDC) systems has drawn much interest. This paper focuses on the oscillation instability phenomenon of low-voltage MTDC systems and analyzes the interaction behavior between each voltage-source converter and the DC network oscillation mode. The typical structure and control strategy of a low-voltage MTDC system under master-slave control is first described, and its equivalent circuit is established. Then, an interaction behavior analytical model is proposed, and the source-network and network-load interaction characteristics are studied. Furthermore, a system stability analysis method is built based on the modularized modeling, which can solve the problem of how to address the complexity of high-order low-voltage MTDC systems. The transfer function of the whole system is conveniently established, revealing the system instability mechanism. The proposed method can provide effective stability assessment for low-voltage MTDC systems. Finally, the results are verified using electromagnetic transient simulation and experimentally validated using a low-voltage three-terminal DC system test platform with AC 0.4 kV/DC 800 V. This research can be flexibly extended to high-order systems for controller design and performance optimization. [ABSTRACT FROM AUTHOR]

The structure stability of the diameter-expanded conductor with fewer inner wires is the principal limitation in its large-scale use at present. As the traditional design method cannot be adopted to solve this problem, the instability properties of the diameter-expanded conductors were studied in this paper. To perform this analysis, different typical diameter-expanded conductors with fewer inner wires were chosen for the sheave tests under different working conditions at first. Then the simulation model as well as the instability criterion was established to analyze the influence factors of the structure stability. Finally, the synchronous stringing tests were carried out to assess the correctness of the model proposed. The results showed that the weakened support of the inner layer(s) and the local buckling of the external wires are the main causes of the wire jumping phenomenon. Therefore, a reasonable increase in the outmost wire's gap and decrease in the inner wire's gap are feasible to improve the load-carrying ability of the diameter-expanded conductor. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of reconstructing 3D poses of multiple people from a few calibrated camera views. The main challenge of this problem is to find the cross-view correspondences among noisy and incomplete 2D pose predictions. Most previous methods address this challenge by directly reasoning in 3D using a pictorial structure model, which is inefficient due to the huge state space. We propose a fast and robust approach to solve this problem. Our key idea is to use a multi-way matching algorithm to cluster the detected 2D poses in all views. Each resulting cluster encodes 2D poses of the same person across different views and consistent correspondences across the keypoints, from which the 3D pose of each person can be effectively inferred. The proposed convex optimization based multi-way matching algorithm is efficient and robust against missing and false detections, without knowing the number of people in the scene. Moreover, we propose to combine geometric and appearance cues for cross-view matching. Finally, an efficient tracking method is proposed to track the detected 3D poses across the multi-view video. The proposed approach achieves the state-of-the-art performance on the Campus and Shelf datasets, while being efficient for real-time applications. [ABSTRACT FROM AUTHOR]

Estimating the pose of a calibrated camera relative to a 3D point set from one image is an important task in computer vision. Perspective-n-Point algorithms are often used if perfect 2D-3D correspondences are known. However, it is difficult to determine 2D-3D correspondences perfectly, and then the simultaneous pose and correspondence determination problem is needed to be solved. Early methods aimed to solve this problem by local optimization. Recently, several new methods are proposed to globally solve this problem by using branch-and-bound (BnB) method, but they tend to be slow because the time complexity of the BnB-based methods is exponential to the dimensionality of the parameter space, and they directly search the 6D parameter space. In this paper, we propose to decompose the joint searching into two separate searching processes by introducing a rotation invariant feature (RIF). Specifically, we construct RIFs from the original 3D and 2D point sets and search for the globally optimal translation to match these two RIFs first. Then, the original 3D point set is translated and matched with the 2D point set to find a globally optimal rotation. Experiments on challenging data show that the proposed method outperforms state-of-the-art methods in terms of both speed and accuracy. [ABSTRACT FROM AUTHOR]

Given a natural language expression and an image/video, the goal of referring segmentation is to produce the pixel-level masks of the entities described by the subject of the expression. Previous approaches tackle this problem by implicit feature interaction and fusion between visual and linguistic modalities in a one-stage manner. However, human tends to solve the referring problem in a progressive manner based on informative words in the expression, i.e., first roughly locating candidate entities and then distinguishing the target one. In this paper, we propose a cross-modal progressive comprehension (CMPC) scheme to effectively mimic human behaviors and implement it as a CMPC-I (Image) module and a CMPC-V (Video) module to improve referring image and video segmentation models. For image data, our CMPC-I module first employs entity and attribute words to perceive all the related entities that might be considered by the expression. Then, the relational words are adopted to highlight the target entity as well as suppress other irrelevant ones by spatial graph reasoning. For video data, our CMPC-V module further exploits action words based on CMPC-I to highlight the correct entity matched with the action cues by temporal graph reasoning. In addition to the CMPC, we also introduce a simple yet effective Text-Guided Feature Exchange (TGFE) module to integrate the reasoned multimodal features corresponding to different levels in the visual backbone under the guidance of textual information. In this way, multi-level features can communicate with each other and be mutually refined based on the textual context. Combining CMPC-I or CMPC-V with TGFE can form our image or video version referring segmentation frameworks and our frameworks achieve new state-of-the-art performances on four referring image segmentation benchmarks and three referring video segmentation benchmarks respectively. Our code is available at https://github.com/spyflying/CMPC-Refseg. [ABSTRACT FROM AUTHOR]

This paper explores the non-convex composition optimization consisting of inner and outer finite-sum functions with a large number of component functions. This problem arises in important applications such as nonlinear embedding and reinforcement learning. Although existing approaches such as stochastic gradient descent (SGD) and stochastic variance reduced gradient (SVRG) descent can be applied to solve this problem, their query complexities tend to be high, especially when the number of inner component functions is large. Therefore, to significantly improve the query complexity of current approaches, we have devised the stochastic composition via variance reduction (SCVR). What's more, we analyze the query complexity under different numbers of inner function and outer function. Based on different kinds of estimation of inner component function, we also present the SCVRII algorithm, though the order of query complexities are the same with SCVR. Additionally, we propose an extension to handle the mini-batch cases, which improve the query complexity under the optimal mini-batch size. The experimental results validate our proposed algorithms and theoretical analyses. [ABSTRACT FROM AUTHOR]

The existing research on voltage-source converter HVDC (VSC-HVDC) system stability mostly focuses on small-signal stability analysis methods. However, when large-signal disturbances occur, the intrinsic nonlinearity of the VSC-HVDC system becomes inevitable so that the small-signal studies are no longer valid. In this paper, a large-signal stability analysis method of the VSC-HVDC system is proposed based on the estimation of domain of attraction (DOA). This method can not only analyze the asymptotic stability of the operating point, but also answer the question of how large deviations from the operating point can be tolerated by the system. By using Takagi-Sugeno (T-S) fuzzy model and Lyapunov stability theorem, the DOA of the VSC-HVDC System at the operating point is estimated, and the large-signal stability of VSC-HVDC System is analyzed. On this foundation, the influence of system parameters on the large-signal stability is studied. The results can be used to guide the adjustment of system parameters to solve the problem of system instability. The time-domain simulations conducted in Matlab/Simulink are used to test the stability of the system under large-signal disturbance in the range of DOA. The simulation results verify the feasibility and effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

This paper presents a novel hierarchical cooperative control strategy to solve the problems of unbalanced State of Charge (SoC), unreasonable load current sharing, and unstable bus voltage for battery storage system (BSS) in islanded DC microgrid. In the communication layer, a neighbor-to-neighbor communication network architecture is constructed in which each battery storage unit (BSU) only communicates information with neighboring nodes, and a multi-agent consensus algorithm is used to iteratively estimate the relevant average global variables. In the main control layer, the droop coefficient is dynamically adjusted by constructing a fast SoC convergence function to ensure that the load current is reasonably distributed based on the rated capacity of each BSU. In the secondary control layer, a virtual voltage drop equalization controller and an average bus voltage compensation controller are designed to eliminate the impact of line impedance mismatch and compensate the average bus voltage. Furthermore, an optimized factor is designed to accelerate the later stage of SoC convergence. Finally, a DC microgrid experimental platform based on StarSim HIL is built, and the results demonstrate that the proposed strategy can achieve the control objectives of fast SoC balance, proportional load current sharing, and bus voltage stability. [ABSTRACT FROM AUTHOR]

Voltage sag insurance (VSI) is an effective measure to reduce the voltage sag loss and risk for enterprises with insufficient mitigation confidence or economic ability. However, due to the lack of understanding of voltage sag risk (VSR), it is difficult for power utilities to identify the enterprises with VSI demands, and it is also unable to realize differentiated premium according to different enterprises' situations. To solve the above problems, this paper proposes an improved voltage sag premium model based on VSR. Firstly, the VSR factors are analyzed, such as the hazard, the vulnerability, the exposure. The process immune time is introduced to describe the vulnerability. Based on the traditional consideration of only the ability of users to resist voltage sag, the ability of users to recover from voltage sag is further considered. Then, the risk evaluation model of voltage sag is established. The evaluation results can help power utilities to judge whether enterprises have the demand of VSI. Finally, the improved premium model of VSI based on VSR is constructed to ensure the differentiation and rationalization of the premium. The correctness and rationality of this method are proved by ten manufacturing enterprises in China by analyzing the VSR and comparing the premium before and after the improvement. [ABSTRACT FROM AUTHOR]

This paper studies the problem of learning the conditional distribution of a high-dimensional output given an input, where the output and input may belong to two different domains, e.g., the output is a photo image and the input is a sketch image. We solve this problem by cooperative training of a fast thinking initializer and slow thinking solver. The initializer generates the output directly by a non-linear transformation of the input as well as a noise vector that accounts for latent variability in the output. The slow thinking solver learns an objective function in the form of a conditional energy function, so that the output can be generated by optimizing the objective function, or more rigorously by sampling from the conditional energy-based model. We propose to learn the two models jointly, where the fast thinking initializer serves to initialize the sampling of the slow thinking solver, and the solver refines the initial output by an iterative algorithm. The solver learns from the difference between the refined output and the observed output, while the initializer learns from how the solver refines its initial output. We demonstrate the effectiveness of the proposed method on various conditional learning tasks, e.g., class-to-image generation, image-to-image translation, and image recovery. The advantage of our method over GAN-based methods is that our method is equipped with a slow thinking process that refines the solution guided by a learned objective function. [ABSTRACT FROM AUTHOR]

With the development of multimedia technology, Augmented Reality (AR) has become a promising next-generation mobile platform. The primary value of AR is to promote the fusion of digital contents and real-world environments, however, studies on how this fusion will influence the Quality of Experience (QoE) of these two components are lacking. To achieve better QoE of AR, whose two layers are influenced by each other, it is important to evaluate its perceptual quality first. In this paper, we consider AR technology as the superimposition of virtual scenes and real scenes, and introduce visual confusion as its basic theory. A more general problem is first proposed, which is evaluating the perceptual quality of superimposed images, i.e., confusing image quality assessment. A ConFusing Image Quality Assessment (CFIQA) database is established, which includes 600 reference images and 300 distorted images generated by mixing reference images in pairs. Then a subjective quality perception experiment is conducted towards attaining a better understanding of how humans perceive the confusing images. Based on the CFIQA database, several benchmark models and a specifically designed CFIQA model are proposed for solving this problem. Experimental results show that the proposed CFIQA model achieves state-of-the-art performance compared to other benchmark models. Moreover, an extended ARIQA study is further conducted based on the CFIQA study. We establish an ARIQA database to better simulate the real AR application scenarios, which contains 20 AR reference images, 20 background (BG) reference images, and 560 distorted images generated from AR and BG references, as well as the correspondingly collected subjective quality ratings. Three types of full-reference (FR) IQA benchmark variants are designed to study whether we should consider the visual confusion when designing corresponding IQA algorithms. An ARIQA metric is finally proposed for better evaluating the perceptual quality of AR images. Experimental results demonstrate the good generalization ability of the CFIQA model and the state-of-the-art performance of the ARIQA model. The databases, benchmark models, and proposed metrics are available at: https://github.com/DuanHuiyu/ARIQA. [ABSTRACT FROM AUTHOR]

Full projector compensation aims to modify a projector input image to compensate for both geometric and photometric disturbance of the projection surface. Traditional methods usually solve the two parts separately and may suffer from suboptimal solutions. In this paper, we propose the first end-to-end differentiable solution, named CompenNeSt++, to solve the two problems jointly. First, we propose a novel geometric correction subnet, named WarpingNet, which is designed with a cascaded coarse-to-fine structure to learn the sampling grid directly from sampling images. Second, we propose a novel photometric compensation subnet, named CompenNeSt, which is designed with a siamese architecture to capture the photometric interactions between the projection surface and the projected images, and to use such information to compensate the geometrically corrected images. By concatenating WarpingNet with CompenNeSt, CompenNeSt++ accomplishes full projector compensation and is end-to-end trainable. Third, to improve practicability, we propose a novel synthetic data-based pre-training strategy to significantly reduce the number of training images and training time. Moreover, we construct the first setup-independent full compensation benchmark to facilitate future studies. In thorough experiments, our method shows clear advantages over prior art with promising compensation quality and meanwhile being practically convenient. [ABSTRACT FROM AUTHOR]

Disguised tailing and visual monitoring of suspicious mobile targets is a promising application of security unmanned aerial vehicles (UAVs). But trajectory planning is non-trivial, especially for fixed-wing UAVs with more constrained maneuverability and dynamic models. This paper proposes a new framework to optimize collectively the propulsion power and the three-dimensional (3D) trajectory of a solar-powered, fixed-wing UAV on a disguised tailing and video surveillance mission. The multi-objective optimization strikes a balance between distance keeping, elevation variance, and power efficiency. A key aspect is that we develop a new propulsion power model of the fixed-wing UAV by analyzing the forces undergone while the UAV is ascending or descending. Another important aspect is a series of non-trivial reformulations, which convexify the multi-objective problem progressively with increasingly tightening linear approximation and solve the problem with a polynomial time-complexity. Our algorithm can control the trajectory of the UAV on-the-fly. Simulations confirm that the algorithm outperforms existing schemes in terms of visual disguise and power efficiency. The fixed-wing UAV also demonstrates its advantage of energy efficiency and sustainability to elongate the surveillance mission, over its rotary-wing counterpart. [ABSTRACT FROM AUTHOR]

With Denmark dedicated to maintaining its leading position in the integration of massive shares of wind energy, the construction of new offshore energy islands has been recently approved by the Danish government. These new islands will be zero-inertia systems, meaning that no synchronous generation will be installed in the island and that power imbalances will be shared only among converters. To this end, this paper proposes a methodology to calculate and update the frequency droops gains of the offshore converters in compliance with the N-1 security criterion in case of converter outage. The frequency droop gains are calculated solving an optimization problem which takes into consideration the power limitations of the converters as well as the stability of the system. As a consequence, the proposed controller ensures safe operation of off-shore systems in the event of any power imbalance and allows for greater loadability at pre-fault state, as confirmed by the simulation results. [ABSTRACT FROM AUTHOR]

Reconfigurable intelligent surface (RIS) technology is promising to enhance wireless communications services by providing smart radio environment. In this paper, we investigate the RIS aided cellular networks with device-to-device (D2D) users, and maximize the sum of the transmission rate of the D2D communications and the cellular networks from a new perspective. In addition to solving the typical resource allocation problems for D2D communications, this paper further optimize the wireless environment by adjusting the position and phase shift of the RIS. To solve this non-convex problem, we propose a novel decentralized double deep Q-network (D3QN) framework for the resource allocation at users and a centralized DDQN for RIS optimization at the base station (BS), which are verified to achieve the near-optimal performance with lower complexity and enhanced robustness. Simulation results illustrate that the proposed framework can achieve higher transmission rates compared to benchmarks, meanwhile meeting the quality of service (QoS) requirements at the BS and D2D users. [ABSTRACT FROM AUTHOR]

Addressing non-convexity plays a fundamental role in solving the optimal electricity-gas flow models. In this paper, an improved spatial branch-and-bound algorithm is proposed to solve the non-convex problem, which is formulated as a mixed-integer bilinear programming, for its exact solution. The core of the algorithm is to divide the non-convex model into convex and small sub-models by branching on specific continuous variables, so that the non-convex problem can be equivalent to a rooted tree for exploration. The exactness of the algorithm is guaranteed by the same criterion as the classical branch-and-bound algorithm. To alleviate the computational burden, a novel two-stage spatial branching strategy is developed to improve the effectiveness and efficiency of the branching operations. The performance of the proposed algorithm is verified on two integrated electricity-gas systems with different sizes. Numerical results demonstrate that our method achieves a balance among feasibility, optimality, and efficiency. The comparison with another 6 convexification-based methods, 3 state-of-the-art non-convex optimization solvers, and 2 spatial branch-and-bound algorithms with classical branching rules further shows the superiority of our algorithm. [ABSTRACT FROM AUTHOR]

Instance segmentation needs to locate all instances in an image correctly and segment each instance precisely. Currently, the most dominant methods for instance segmentation take object detection as a pre-task. However, they rely on the accuracy of object detection incredibly. If the pre-task cannot predict an accurate bounding box, the performance of instance segmentation will degenerate. In this paper, we present a novel method for instance segmentation to solve this problem, which is called Segmenting Beyond the Bounding Box (S3B-Net). Our S3B-Net designs a sub-network to help instance segmentation methods based on object detection to segment the part of an instance beyond the bounding box. Specifically, the sub-network first predicts a two-dimensional pixel embedding for each pixel. Then, the Gaussian function is employed to calculate a pixel’s probability belongs to a corresponding instance according to the two-dimensional pixel embedding. Finally, the output of the sub-network combines with the output of instance segmentation based on object detection to generate a more precise instance mask. Our sub-network can easily extend on the existing instance segmentation method based on object detection to segment instance beyond the bounding box. We do our experiments on dominant instance segmentation datasets, such as the COCO dataset and Cityscapes dataset. The results show that our method can achieve 6.8 points gain compared with the baseline Mask R-CNN with ResNet-50-FPN in Cityscapes datasets, and 1.7 points gain with ResNet-101-FPN-DCN in COCO datasets. Our S3B-Net outperforms the previous state-of-the-art instance segmentation method, which proves our method is competitive. The source code of our method will be made available. [ABSTRACT FROM AUTHOR]

In this paper, we propose to extend the standard Convolutional Dictionary Learning problem to a tensor representation where the activations are constrained to be “low-rank” through a Canonical Polyadic decomposition. We show that this additional constraint increases the robustness of the CDL with respect to noise and improve the interpretability of the final results. In addition, we discuss in detail the advantages of this representation and introduce two algorithms, based on ADMM or FISTA, that efficiently solve this problem. We show that by exploiting the low rank property of activations, they achieve lower complexity than the main CDL algorithms. Finally, we evaluate our approach on a wide range of experiments, highlighting the modularity and the advantages of this tensorial low-rank formulation. [ABSTRACT FROM AUTHOR]

Distributed primal-dual methods have been widely used for solving large-scale constrained optimization problems. The majority of existing results focus on the problems with decoupled constraints. Some recent works have studied the problems subject to separable globally coupled constraints. This paper considers the distributed optimization problems with globally coupled constraints over networks without requiring the separability of the globally coupled constraints. This is made possible by the local estimates of the constraint violations. For solving such a problem, we propose a primal-dual algorithm in the augmented Lagrangian framework, combining the average consensus technique. We first establish a non-ergodic convergence rate of $\mathcal {O}(1/k)$ in terms of the objective residual for solving a distributed constrained convex optimization problem, where $k$ is the iteration counter. Specifically, the global objective function is the aggregate of the local convex and possibly non-smooth costs, and the coupled constraint is the sum of the local linear equality constraints. The numerical results illustrate the performance of the proposed method. [ABSTRACT FROM AUTHOR]

Thanks to the strong ability against the inter-cell interference, cell-free network is considered as a promising technique to improve network capacity. However, further capacity improvement requires to deploy more base stations (BSs) with high cost and power consumption. To address this issue, inspired by the recently developed reconfigurable intelligent surface (RIS) technique, we propose the concept of RIS-aided cell-free network to improve the capacity with low cost and power consumption. The key idea is to replace some of the required BSs by low-cost and energy-efficient RISs. Then, in a wideband RIS-aided cell-free network, we formulate the problem of joint precoding design at BSs and RISs to maximize the network capacity. Due to the non-convexity and high complexity of the formulated problem, we develop an alternating optimization framework to solve this challenging problem. In particular, we decouple this problem via fractional programming, and solve the subproblems alternatively. Note that most of the scenarios considered in existing works are special cases of the general scenario studied in this paper, and the proposed joint precoding framework can serve as a general solution to maximize the capacity in most existing RIS-aided scenarios. Finally, simulation results demonstrate that, compared with the conventional cell-free network, the network capacity under the proposed scheme can be improved significantly. [ABSTRACT FROM AUTHOR]

The integration of the variable renewable energies makes the operation conditions of the power system ever-changeable. Consequently, the power system operational reliability evaluation is increasingly important. This paper introduces the concept of decision-dependent uncertainty (DDU) in the operational reliability evaluation. Unlike the exogenous uncertainties, DDU reveals that the decisions of the system operation could significantly affect the resolution of the uncertainties which influence the reliability metrics. In this paper, the proposed DDU modeling method links the device reliability indices, i.e., the forced outage rate, and the operational-decision variables. The impacts of DDU on operational reliability are analyzed based on a reliability-constrained stochastic unit commitment (UC) model. An adaptive reliability improvement UC (ARIUC) algorithm is proposed to efficiently solve the problem. Case studies underline the necessity of considering DDU in power system operational reliability evaluations. [ABSTRACT FROM AUTHOR]

In this paper, the decentralized energy management of a community of prosumers is studied. The coordination of the prosumers participating in the community is cast as a mixed-integer linear program (MILP) with local and global coupling constraints. A dual decomposition method with a tightening of the coupling constraints is applied to solve the problem in a decentralized way. The resulting tightened problem provides feasibility guarantees for the obtained solutions. A receding horizon approach that exploits the structure of the problem is proposed to divide the problem in subproblems and solve them sequentially. The proposed approach ensures that the tightened problem is feasible under realistic conditions, whereas the existing methods may result in infeasible problems. Moreover, it may reduce the necessary constraint tightening compared to existing methods. Two setups are evaluated for the organizational structure of the community, one with a community coordinator and one without. Moreover, three different structures of the communication graph are analyzed for the setup without a coordinator. The simulation results demonstrate that the proposed method results in feasible problems that can be solved due to the reduced constraint tightening when other methods are not feasible. In the case of feasible problems, the optimality gap is comparable to that achieved with existing methods and even smaller for communities with a small number of participating prosumers. [ABSTRACT FROM AUTHOR]

Stochastic unit commitment is an efficient method for grid operation in the presence of significant uncertainties. An example is an operation during a predicted hurricane with uncertain line out-ages. However, the solution quality comes at the cost of substantial computational burden, which makes its adoption challenging. This paper evaluates some possible ways that machine learning can be used to reduce this computational burden. First, a set of feasibility studies is conducted. Results suggest that using machine learning as an assistant to the stochastic unit commitment solver is more advantageous than using it as a standalone solver. In particular, the machine learning model is trained to facilitate solving the problem by determining the unnecessary constraints that can be removed from the original problem without affecting the final accuracy. The variables that can be used as input features/predictors or outputs for the machine learning model are determined through feasibility studies. Then, an algorithm to train and utilize a machine learning model is proposed. The method is tested on a 500-bus synthetic South Carolina system. Various test cases show an average reduction in solution time by more than 90% by using the trained machine learning model to assist the stochastic unit commitment solver. [ABSTRACT FROM AUTHOR]

With the increase of mobile devices, Mobile Crowdsensing (MCS) has become an efficient way to ubiquitously sense and collect environment data. Comparing to traditional sensor networks, MCS has a vital advantage that workers play an active role in collecting and sensing data. However, due to the openness of MCS, workers and sensors are of different qualities. Low quality sensors and workers may yield noisy data or even inaccurate data. Which gives the importance of inferring the quality of workers and sensors and seeking a valid task assignment with enough total qualities for MCS. To solve the problem, we adopt truth inference methods to iteratively infer the truth and qualities. Based on the quality inference, this paper proposes a task assignment problem called quality-bounded task assignment with redundancy constraint (QTAR). Different from traditional task assignment problem, redundancy constraint is added to satisfy the preliminaries of truth inference, which requires that each task should be assigned a certain or more amount of workers. We prove that QTAR is NP-complete and propose a $ (2+\epsilon)$ (2 + ε) - approximation algorithm for QTAR, called QTA. Finally, experiments are conducted on both synthesis data and real dataset. The results of the experiments prove the efficiency and effectiveness of our algorithms. [ABSTRACT FROM AUTHOR]

This paper considers and solves the problem of estimating camera pose given a pair of point-tangent correspondences between a 3D scene and a projected image. The problem arises when considering curve geometry as the basis of forming correspondences, computation of structure and calibration, which in its simplest form is a point augmented with the curve tangent. We show that while the resectioning problem is solved with a minimum of three points given the intrinsic parameters, when points are augmented with tangent information only two points are required, leading to substantial robustness and computational savings, e.g., as a minimal engine within ransac. In addition, algorithms are developed to find a practical solution shown to effectively recover camera pose using synthetic and real datasets. This technology is intended as a building block of curve-based structure from motion systems, allowing new views to be incrementally registered to a core set of views for which relative pose has been computed. [ABSTRACT FROM AUTHOR]

For solving the problem of the inevitable decline in the accuracy of cross-subject emotion recognition via Electroencephalograph (EEG) signal transfer learning due to the negative transfer of data in the source domain, this paper offers a new method to dynamically select the data suitable for transfer learning and eliminate the data that may lead to negative transfer. The method which is called cross-subject source domain selection (CSDS) consists of the next three parts. 1) First, a Frank-copula model is established according to Copula function theory to study the correlation between the source domain and the target domain, which is described by the Kendall correlation coefficient. 2) The calculation method for the Maximum Mean Discrepancy is improved to determine the distance between classes in a single source. After normalization, the Kendall correlation coefficient is superimposed, and the threshold is set to identify the source-domain data most suitable for transfer learning. 3) In the process of transfer learning, on the basis of Manifold Embedded Distribution Alignment, the Local Tangent Space Alignment method is used to provide a low-dimensional linear estimation of the local geometry of nonlinear manifolds, which maintains the local characteristics of the sample data after dimensionality reduction. Experimental results show that compared with the traditional methods, the CSDS increases the accuracy of emotion classification by approximately 2.8% and reduces the runtime by approximately 65%. [ABSTRACT FROM AUTHOR]

Multi-set membership queries are fundamental operations in data science. In this paper, we propose a new data structure for multi-set membership queries, named coloring embedder, which is fast, accurate, and memory efficient. The idea of coloring embedder is to first map elements to a high-dimensional space, which nearly eliminates hashing collisions, and then use a dimensional reduction representation, similar to coloring a graph, to save memory. Theoretical proofs and experimental results show that the coloring embedder is effective in solving the problem of multi-set membership queries. We also find that web cache sharing is one of the typical application scenarios of the multi-set membership queries and current methods based on Bloom filters always send redundant queries. We apply coloring embedder to web cache sharing by arranging our data structure on the on-chip and off-chip memory and designing query, insertion and deletion operations for this scenario. The experimental results show that compared with the present method, our method can reduce the queries sent by proxies while reaching equal hit rate with the same size of on-chip memory. The source code of coloring embedder has been released on Github. [ABSTRACT FROM AUTHOR]

The problem of computing the Hamming weight distribution of linear codes is considered in this paper. A novel method to enumerate all codewords up to a certain Hamming weight for binary linear block codes in general and in particular for the punctured, shortened, precoded polar codes is introduced. The proposed approach performs a recursive decomposition of the codes using construction X4 that is typically used to combine codes of different lengths. This allows to enumerate the low-weight codewords of the overall code as combinations of the low-weight codewords of the component codes. Numerical results show that the proposed approach can efficiently compute the exact partial weight distribution of the 5G New Radio punctured/shortened polar codes with CRC11 and pure polar codes. In the former and latter cases, the low-weight codeword number is up to 106 and 108, respectively. Besides, randomly punctured and shortened polar codes and randomly precoded polar codes are also considered. To the best of the authors’ knowledge, this is the first method able to solve these problems. [ABSTRACT FROM AUTHOR]

Accurate solar photovoltaic (PV) generation forecast is critical to the reliable and economic operation of a modern power system. In practice, due to various faulty issues in the sensor, communication, or database system, the historical and online measurement data may not be always complete, and the missing data could dramatically degrade the forecasting model's accuracy. To solve this problem, this paper proposes an integrated missing-data tolerant model for probabilistic PV power generation forecasting. Taking historical PV generations as input, this model is based on a recursive long short-term memory network (Rec-LSTM), which can provide multi-step ahead forecasting of the probability distribution of PV generation. The unobserved input data will be imputed recursively based on the model output at the previous time step. During the training process, the imputations and forecasting values are iteratively updated by the negative log-likelihood loss function. As a salient advantage, this method can deal with data missing scenarios at both offline and online stages. Numerical experiments are conducted on two one-year datasets from Australia and Singapore, respectively. Probabilistic forecasting for both large-scale and small-scale building-level PV power generation is tested at the time resolution of 15 mins. Testing results show the proposed method can achieve superior probabilistic prediction accuracy as well as strong robustness under various data missing scenarios, compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

As an emulous alternative to deep neural networks, Deep Forest emerges with features like low complexity, fewer hyper-parameters, and good robustness, which are predominantly desired in distributed computing applications and ecosystems. Recently, an efficient distributed Deep Forest system, named ForestLayer, was proposed, designing a fine-grained sub-Forest-based task-parallel algorithm to improve the parallel computing efficiency of Deep Forest. However, the sub-Forest splitting of ForestLayer is static and one-off without adaptability to the computing environment, nevertheless, the size of splitting granularity has a significant impact on the system performance. To further improve the computing efficiency and scalability of the distributed Deep Forest, in this paper, we propose a novel distributed Deep Forest algorithm, named BLB-gcForest (Bag of Little Bootstraps-gcForest), which augments the gcForest (multi-Grained Cascade Forest) approach for constructing Deep Forest. BLB-gcForest carries out parallel computation for each tree in sub-Forests at a finer parallel granularity and integrates with the Bag of Little Bootstraps (BLB) mechanism to reduce massive transmitted feature instances for Cascade Forest Layers, utterly improving both computation efficiency and communication efficiency. Moreover, to solve the problem of the forest splitting granularity, we further design an adaptive sub-Forest splitting algorithm to ensure the maximum resource utilization for parallel computation of each sub-Forest. Experimental results on four well-known large-scale datasets, namely YEAST, LETTER, MNIST, CIFAR10, show that the training efficiency of BLB-gcForest achieves up to 20.3x and 1.64x speedups compared with the state-of-the-art gcForest and ForestLayer, respectively while guaranteeing higher accuracy and better robustness [ABSTRACT FROM AUTHOR]

The existing state-of-the-art (SOTA) video salient object detection (VSOD) models have widely followed short-term methodology, which dynamically determines the balance between spatial and temporal saliency fusion by solely considering the current consecutive limited frames. However, the short-term methodology has one critical limitation, which conflicts with the real mechanism of our visual system — a typical long-term methodology. As a result, failure cases keep showing up in the results of the current SOTA models, and the short-term methodology becomes the major technical bottleneck. To solve this problem, this paper proposes a novel VSOD approach, which performs VSOD in a complete long-term way. Our approach converts the sequential VSOD, a sequential task, to a data mining problem, i.e., decomposing the input video sequence to object proposals in advance and then mining salient object proposals as much as possible in an easy-to-hard way. Since all object proposals are simultaneously available, the proposed approach is a complete long-term approach, which can alleviate some difficulties rooted in conventional short-term approaches. In addition, we devised an online updating scheme that can grasp the most representative and trustworthy pattern profile of the salient objects, outputting framewise saliency maps with rich details and smoothing both spatially and temporally. The proposed approach outperforms almost all SOTA models on five widely used benchmark datasets. [ABSTRACT FROM AUTHOR]

The stable continuation of trajectories among different targets has always been the key to the tracking performance of multi-object tracking (MOT) tasks. If features of the target are aggregated and classified simply, the discriminant features of the target will be ignored. This will affect the robustness of the trajectory generated by the model. Meanwhile, many popular models are keen to execute detection and feature extraction tasks in parallel. But these two tasks will conflict with each other when optimized respectively. Therefore, we propose our tracker MOTFR to solve the above problems. In this paper, we propose a Locally Shared Information Decoupling Module (LSIDM) to reduce task optimization conflicts while ensuring the necessary information sharing. Meanwhile, a feature recoding module for deep extraction of identity discriminative features is proposed, which is called the Feature Purification Module (FPM). By combining LSIDM and FPM modules, the model utilizes the discriminative appearance features to guide the optimization of detection and further improves the performance of our model. To solve the problem of targets disappearing due to various abnormal occlusion, a Short-term Trajectory Online Complement Strategy (STOCS) is proposed to realize the trajectories continuation of these targets in the tracking stage. Through sufficient experiments, we demonstrate the superior performance of our MOTFR, which guarantees high-quality detection while achieving the stability of the target trajectory. [ABSTRACT FROM AUTHOR]

$\ell _{1}$ ℓ 1 -norm quantile regression is a common choice if there exists outlier or heavy-tailed error in high-dimensional data sets. However, it is computationally expensive to solve this problem when the feature size of data is ultra high. As far as we know, existing screening rules can not speed up the computation of the $\ell _{1}$ ℓ 1 -norm quantile regression, which dues to the non-differentiability of the quantile function/pinball loss. In this paper, we introduce the dual circumscribed sphere technique and propose a novel $\ell _{1}$ ℓ 1 -norm quantile regression screening rule. Our rule is expressed as the closed-form function of given data and eliminates inactive features with a low computational cost. Numerical experiments on some simulation and real data sets show that this screening rule can be used to eliminate almost all inactive features. Moreover, this rule can help to reduce up to 23 times of computational time, compared with the computation without our screening rule. [ABSTRACT FROM AUTHOR]

In complex real-world situations, problems such as illumination changes, facial occlusion, and variant poses make facial expression recognition (FER) a challenging task. To solve the robustness problem, this paper proposes an adaptive multilayer perceptual attention network (AMP-Net) that is inspired by the facial attributes and the facial perception mechanism of the human visual system. AMP-Net extracts global, local, and salient facial emotional features with different fine-grained features to learn the underlying diversity and key information of facial emotions. Different from existing methods, AMP-Net can adaptively guide the network to focus on multiple finer and distinguishable local patches with robustness to occlusion and variant poses, improving the effectiveness of learning potential facial diversity information. In addition, the proposed global perception module can learn different receptive field features in the global perception domain, and AMP-Net also supplements salient facial region features with high emotion correlation based on prior knowledge to capture key texture details and avoid important information loss. Many experiments show that AMP-Net achieves good generalizability and state-of-the-art results on several real-world datasets, including RAF-DB, AffectNet-7, AffectNet-8, SFEW 2.0, FER-2013, and FED-RO, with accuracies of 89.25%, 64.54%, 61.74%, 61.17%, 74.48%, and 71.75%, respectively. All codes and training logs are publicly available at https://github.com/liuhw01/AMP-Net. [ABSTRACT FROM AUTHOR]

In this paper, we study a quantized feedback scheme to maximize the goodput of a finite blocklength communication scenario over a quasi-static fading channel. It is assumed that the receiver has perfect channel state information (CSI) and sends back the CSI to the transmitter over a resolution-limited error-free feedback channel. With this partial CSI, the transmitter is supposed to select the optimum transmission rate, such that it maximizes the overall goodput of the communication system. This problem has been studied for the asymptotic blocklength regime, however, no solution has so far been presented for finite blocklength. Here, we study this problem in two cases: with and without constraint on reliability. We first formulate the optimization problems and analytically solve them. Iterative algorithms that successfully exploit the system parameters for both cases are presented. It is shown that although the achievable maximum goodput decreases with shorter blocklengths and higher reliability requirements, significant improvement can be achieved even with coarsely quantized feedback schemes. [ABSTRACT FROM AUTHOR]

Non-overlapping codes are a set of codewords in $\bigcup _{n \ge 2} \mathbb {Z}_{q}^{n}$ , where $\mathbb {Z}_{q} = \{0,1, {\dots },q-1\}$ , such that the prefix of each codeword is not a suffix of any codeword in the set, including itself; and for variable-length codes, a codeword does not contain any other codeword as a subword. In this paper, we investigate a generic method to generalize binary codes to $q$ -ary ones for $q > 2$ , and analyze this generalization on the two constructions given by Levenshtein (also by Gilbert; Chee, Kiah, Purkayastha, and Wang) and Bilotta, respectively. The generalization on the former construction gives large non-expandable fixed-length non-overlapping codes whose size can be explicitly determined; the generalization on the latter construction is the first attempt to generate $q$ -ary variable-length non-overlapping codes. More importantly, this generic method allows us to utilize the generating function approach to analyze the cardinality of the underlying $q$ -ary non-overlapping codes. The generating function approach not only enables us to derive new results, e.g., recurrence relations on their cardinalities, new combinatorial interpretations for the constructions, and the superior limit of their cardinalities for some special cases, but also greatly simplifies the arguments for these results. Furthermore, we give an exact formula for the number of fixed-length words that do not contain the codewords in a variable-length non-overlapping code as subwords. This thereby solves an open problem by Bilotta and induces a recursive upper bound on the maximum size of variable-length non-overlapping codes. [ABSTRACT FROM AUTHOR]

Traditional single-ended fault location method is influenced by the fault resistance, and the remote in feed, which reflects as the two equations built by fault phase have four unknowns. And in the grid-connected converter system, the weak feedback characteristic further reduces the performance of the method. To solve it, a single-ended fault location method based on control and protection coordination is proposed in this paper. First, using the high controlled-ability of the converter, the control strategy for fault ride-through (FRT) operation is divided into two stages by switching control modes. Then, according to the electrical quantities under two stages, four uncorrelated equations can be established, and the equations still have four unknown parameters. The fault distance can be calculated by solving them. The simulation results show that the proposed method has high accuracy and is immune to fault resistance and fault location, it solves the problem of insufficient equations in principle. [ABSTRACT FROM AUTHOR]

We study network pruning which aims to remove redundant channels/kernels and hence speed up the inference of deep networks. Existing pruning methods either train from scratch with sparsity constraints or minimize the reconstruction error between the feature maps of the pre-trained models and the compressed ones. Both strategies suffer from some limitations: the former kind is computationally expensive and difficult to converge, while the latter kind optimizes the reconstruction error but ignores the discriminative power of channels. In this paper, we propose a simple-yet-effective method called discrimination-aware channel pruning (DCP) to choose the channels that actually contribute to the discriminative power. To this end, we first introduce additional discrimination-aware losses into the network to increase the discriminative power of the intermediate layers. Next, we select the most discriminative channels for each layer by considering the discrimination-aware loss and the reconstruction error, simultaneously. We then formulate channel pruning as a sparsity-inducing optimization problem with a convex objective and propose a greedy algorithm to solve the resultant problem. Note that a channel (3D tensor) often consists of a set of kernels (each with a 2D matrix). Besides the redundancy in channels, some kernels in a channel may also be redundant and fail to contribute to the discriminative power of the network, resulting in kernel level redundancy. To solve this issue, we propose a discrimination-aware kernel pruning (DKP) method to further compress deep networks by removing redundant kernels. To avoid manually determining the pruning rate for each layer, we propose two adaptive stopping conditions to automatically determine the number of selected channels/kernels. The proposed adaptive stopping conditions tend to yield more efficient models with better performance in practice. Extensive experiments on both image classification and face recognition demonstrate the effectiveness of our methods. For example, on ILSVRC-12, the resultant ResNet-50 model with 30 percent reduction of channels even outperforms the baseline model by 0.36 percent in terms of Top-1 accuracy. We also deploy the pruned models on a smartphone (equipped with a Qualcomm Snapdragon 845 processor). The pruned MobileNetV1 and MobileNetV2 achieve 1.93× and 1.42× inference acceleration on the mobile device, respectively, with negligible performance degradation. The source code and the pre-trained models are available at https://github.com/SCUT-AILab/DCP. [ABSTRACT FROM AUTHOR]

Computation over multiple access channels (CoMAC) has been proposed to solve the problem of spectrum scarcity in wireless networks, which combines communication and computation efficiently using the superposition property of wireless channels. In this paper, we consider a multi-cluster CoMAC network, whose performance is affected by the inter-cluster interference and the non-uniform fading. To minimize the sum mean squared error of signals aggregated at different fusion centers (FCs), we propose a transceiver design for multi-cluster CoMAC. Specifically, we adopt a uniform-forcing transmitter design to formulate the receiver design as a quadratic sum-of-ratios problem with nonconvex quadratic constraints. Then, we propose a branch-and-bound algorithm to find its optimal solution with a given error tolerance. To solve the problem in a decentralized way, we develop a distributed algorithm based on the primal decomposition theory. Each subproblem is solved by using the successive convex approximation method. Further combining Lagrange duality, we derive the optimal solution structure of each subproblem, based on which we can find the solution with lower complexity. Simulation results demonstrate the effectiveness of the proposed distributed transceiver design. [ABSTRACT FROM AUTHOR]

Doubly salient wound field machines exhibit the advantages of robust structure and controllable flux, and hence have been utilized as generators in applications of automobiles and renewable energy. However, the inherent unbalanced phase back-electromotive force (EMF) waveform caused by the asymmetric flux path brings difficulties for precise control and smooth operation. To solve the problem caused by unbalanced back-EMF waveform in conventional doubly salient machines, this paper presents a novel doubly salient wound field machine with balanced and symmetrical back-EMF waveform as starter generator in automobile application. The robust structure and the controllable flux are inherited, while the magnetless feature makes it promising for cost-sensitive applications. The proposed machine can be operated as an assistant motor for torque boosting at start-up stage, as well as a power recycling generator for battery charging at steady state. It is revealed that the proposed wound field machine exhibits similar cost, comparable torque density, improved torque ripple, and higher efficiency than the switched reluctance machine. Finally, the proposed prototype is fabricated, and dynamic experiment is conducted to validate the feasibility for automobile starter generator application. [ABSTRACT FROM AUTHOR]

Recent years have witnessed a big leap in automatic visual saliency detection attributed to advances in deep learning, especially Convolutional Neural Networks (CNNs). However, inferring the saliency of each image part separately, as was adopted by most CNNs methods, inevitably leads to an incomplete segmentation of the salient object. In this paper, we describe how to use the property of part-object relations endowed by the Capsule Network (CapsNet) to solve the problems that fundamentally hinge on relational inference for visual saliency detection. Concretely, we put in place a two-stream strategy, termed Two-Stream Part-Object RelaTional Network (TSPORTNet), to implement CapsNet, aiming to reduce both the network complexity and the possible redundancy during capsule routing. Additionally, taking into account the correlations of capsule types from the preceding training images, a correlation-aware capsule routing algorithm is developed for more accurate capsule assignments at the training stage, which also speeds up the training dramatically. By exploring part-object relationships, TSPORTNet produces a capsule wholeness map, which in turn aids multi-level features in generating the final saliency map. Experimental results on five widely-used benchmarks show that our framework consistently achieves state-of-the-art performance. The code can be found on https://github.com/liuyi1989/TSPORTNet. [ABSTRACT FROM AUTHOR]

The iterative closest point (ICP) algorithm and its variants are a fundamental technique for rigid registration between two point sets, with wide applications in different areas from robotics to 3D reconstruction. The main drawbacks for ICP are its slow convergence, as well as its sensitivity to outliers, missing data, and partial overlaps. Recent work such as Sparse ICP achieves robustness via sparsity optimization at the cost of computational speed. In this paper, we propose a new method for robust registration with fast convergence. First, we show that the classical point-to-point ICP can be treated as a majorization-minimization (MM) algorithm, and propose an Anderson acceleration approach to speed up its convergence. In addition, we introduce a robust error metric based on the Welsch’s function, which is minimized efficiently using the MM algorithm with Anderson acceleration. On challenging datasets with noises and partial overlaps, we achieve similar or better accuracy than Sparse ICP while being at least an order of magnitude faster. Finally, we extend the robust formulation to point-to-plane ICP, and solve the resulting problem using a similar Anderson-accelerated MM strategy. Our robust ICP methods improve the registration accuracy on benchmark datasets while being competitive in computational time. [ABSTRACT FROM AUTHOR]

This paper proposes a gaze correction and animation method for high-resolution, unconstrained portrait images, which can be trained without the gaze angle and the head pose annotations. Common gaze-correction methods usually require annotating training data with precise gaze, and head pose information. Solving this problem using an unsupervised method remains an open problem, especially for high-resolution face images in the wild, which are not easy to annotate with gaze and head pose labels. To address this issue, we first create two new portrait datasets: CelebGaze ($256 \times 256$) and high-resolution CelebHQGaze ($512 \times 512$). Second, we formulate the gaze correction task as an image inpainting problem, addressed using a Gaze Correction Module (GCM) and a Gaze Animation Module (GAM). Moreover, we propose an unsupervised training strategy, i.e., Synthesis-As-Training, to learn the correlation between the eye region features and the gaze angle. As a result, we can use the learned latent space for gaze animation with semantic interpolation in this space. Moreover, to alleviate both the memory and the computational costs in the training and the inference stage, we propose a Coarse-to-Fine Module (CFM) integrated with GCM and GAM. Extensive experiments validate the effectiveness of our method for both the gaze correction and the gaze animation tasks in both low and high-resolution face datasets in the wild and demonstrate the superiority of our method with respect to the state of the art. [ABSTRACT FROM AUTHOR]

Zero-shot recognition has been a hot topic in recent years. Since no direct supervision is available, researchers use semantic information as the bridge instead. However, most zero-shot recognition methods jointly model images on the class level without considering the distinctive character of each image. To solve this problem, in this paper, we propose a novel exemplar-based, semantic guided zero-shot recognition method (EBSG). Both visual and semantic information of each image is used. We train visual sub-model to separate each image from the other images of different classes. We also train semantic sub-model to separate this image from the other images described with different semantics. We concatenate the outputs of visual and semantic sub-models to represent images. Image classification model is then learned by measuring visual similarity and semantic consistency of both source and target images. We conduct zero-shot recognition experiments on four widely used datasets. Experimental results show the effectiveness of the proposed EBSG method. [ABSTRACT FROM AUTHOR]

Existing video captioning methods usually ignore the important fine-grained semantic attributes, the video diversity, as well as the association and motion state between objects within and between frames. Thus, they cannot adapt to small sample data sets. To solve the above problems, this paper proposes a novel video captioning model and an adversarial reinforcement learning strategy. Firstly, an object-scene relational graph model is designed based on the object detector and scene segmenter to express the association features. The graph is encoded by the graph neural network to enrich the expression of visual features. Meanwhile, a trajectory-based feature representation model is designed to replace the previous data-driven method to extract motion and attribute information, so as to analyze the object motion in the time domain and establish the connection between the visual content and language under small data sets. Finally, an adversarial reinforcement learning strategy and a multi- branch discriminator are designed to learn the relationship between the visual content and corresponding words so that rich language knowledge is integrated into the model. Experimental results on three standard datasets and one small sample dataset indicate that our proposed method achieves state-of-the-art performance. Also, the ablation experiments and visualization results verify the effectiveness of proposed each strategy. [ABSTRACT FROM AUTHOR]