University of Electronic Science and Technology of China

In this paper, we extend the modulus-based matrix splitting method for solving the vertical nonlinear complementarity problem. Some necessary convergence conditions of the proposed methods are investigated. Numerical examples are given to compare ...

The increasing need for large-scale deep neural networks (DNN) has made parallel training an area of intensive focus. One effective method, microbatch-based pipeline parallelism (notably GPipe), accelerates parallel training in various architectures. ...

We present a novel deep camera path optimization framework for minimum latency online video stabilization. Typically, a stabilization pipeline consists of three steps: motion estimation, path smoothing, and novel view synthesis. Most previous methods ...

Federated Learning (FL) is to collaboratively train a global model among distributed clients by iteratively aggregating their local updates without sharing their raw data, whereby the global modal can approximately converge to the centralized training way ...

Autonomous Underwater Vehicle (AUV)-assisted Underwater Acoustic Networks (UANs) are promising for complex ocean applications. In essence, an AUV-assisted UAN is still dominated by fixed nodes, and Time Division Multiple Access (TDMA)-based Medium Access ...

Secret key generation exploiting inherent channel randomness stands as an important paradigm for physical-layer security in wireless networks. However, existing work relying on quantization has some difficulties in eliminating inconsistent key bits due to ...

Summarization quality evaluation is a non-trivial task in text summarization. Contemporary methods can be mainly categorized into two scenarios: (1) <italic>reference-based:</italic> evaluating with human-labeled reference summary; (2) <italic>reference-...

Social recommendations leverage social networks to augment the performance of recommender systems. However, the critical task of denoising social information has not been thoroughly investigated in prior research. In this study, we introduce a ...

In this paper, a multi-object recognition scenario is considered to extend the random finite set into random permutation set. Probabilistic information on random permutation set can be viewed as an distribution determined by three random variables. We use ...

This article investigates the Bayesian detection problem for the distributed targets in the compound Gaussian (CG) sea clutter. The CG sea clutter is formulated as a product of lognormal texture and speckle component with an inverse Wishart ...

• Four Bayesian detectors have been designed in the compound Gaussian distribution clutter with lognormal texture.
• The proposed detectors attain Constant False Alarm Rate (CFAR) properties.
• The proposed detectors attain better ...

Dual-functional Radar-Communication (DFRC) systems have been recognized as one of the most promising technologies in the field of wireless communications. Nevertheless, the low probability of intercept (LPI) performance in the DFRC systems cannot ...

• A dual-functional radar-communication system based on frequency diverse array (FDA) radar is investigated.
• A comprehensive optimization model is presented to improve the sensing performance.
• An iterative relaxed algorithm is ...

Linearly-constrained adaptive filtering algorithms have emerged as promising candidates for system estimation. The existing methods such as the constrained least mean square algorithm rely on mean square error based learning, which delivers ...

• We derived a low-complexity version of RCMVC for constrained adaptive filtering.
• DCD-RCMVC is obtained by using the weighting method and the DCD iteration method.
• For DCD-RCMVC, we conducted the equivalence and convergence ...

This paper deals with the radar target detecting problem in nonzero-mean compound Gaussian sea clutter with random texture. The texture is considered to be an inverse Gamma, Gamma, or inverse Gaussian variable. Three novel adaptive detectors ...

• Three adaptive GLRT-based nonzero-mean detectors have been proposed to address the problem of target detection in nonzero-mean compound Gaussian sea clutter.
• The novel mean vector estimating method and covariance matrix estimator have ...

Tensor ring (TR) decomposition has made remarkable achievements in numerous high-order data processing tasks. However, the current alternating least squares (ALS)- and singular value decomposition (SVD)-based algorithms for TR decomposition, i.e.,...

• Propose TR-HLanczos for fast tensor ring decomposition using a unified framework.
• TR-HLanczos defines three decomposition structures for tensor ring processing steps.
• Establish a relationship between the TR-Lanczos and TR-HLanczos ...

Recently, conformal arrays have attracted considerable interest because such arrays can provide reduced radar cross-section and increased angle coverage. In this article, we devise a robust adaptive beamforming (RAB) approach using cylindrical ...

• A robust beamforming method for cylindrical conformal arrays is proposed.
• A low-rank covariance matrix via nuclear norm minimization is constructed.
• The robustness of adaptive beamforming is significantly improved.

This paper considers the problem of multitarget tracking (MT) under situations where sensors have limited resolution, which leads to the presence of merged measurements (MMs). In general, an algorithm for MT under MMs can be derived by extending ...

Display Omitted

• Multitarget tracking under measurements merging is practically common but it is challenging.
• Data association under measurements merging allows a measurement to be simultaneously produced by multiple targets.
• The message passing ...

Target occlusion or pollution has always been a common and difficult problem in 3D reconstruction, seriously affecting the reconstruction effect, especially in single image scenario. To address the issues of incomplete reconstruction caused by ...

Display Omitted

• This paper proposes a novel framework for 3D face reconstruction with missing pixel completion, which enables the generation of complete 3D face models from largely masked images. Unlike previous reconstruction methods, it possesses the ...

Recently, convolutional neural networks (CNNs) and multiple instance learning (MIL) methods have been successfully applied to MRI images. However, CNNs directly utilize the whole image as the model input and the downsampling strategy (like max or ...

• We introduce a dual-branch network with cross-attention for liver tumor-related classification.
• We design a cross-attention module between two branches for interpreting lesion-relevant regions.
• We propose a novel loss function to ...

• We introduce a self-confidence evolution model.
• We propose a novel opinion dynamics model incorporating self-confidence evolution.
• We propose a game model to find optimal resource allocation strategies of players.
• We provide ...

The formation of public opinion is typically influenced by different stakeholders, such as governments and firms. Recently, various real-world problems related to the management of public opinion have emerged, necessitating stakeholders to ...

Unsupervised multi-view graph representation learning (UMGRL) aims to capture the complex relationships in the multi-view graph without human annotations, so it has been widely applied in real-world applications. However, existing UMGRL methods ...

• Effectively fuse the information in the multi-view graph with dual weight-net.
• Considering the importance of node, graph and edge level simultaneously.
• Fused representations show better generalization ability on downstream tasks.