检索结果-内蒙古大学图书馆

International Conference on Computer Supported Cooperative Work in Design

作者： Hengwei Zhang Yuejia Wu Jian-Tao Zhou Inner Mongolia University College of Computer Science Hohhot China Ministry of Education National & Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Engineering Research Center of Ecological Big Data Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Hohhot China Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Hohhot China Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Named Entity Recognition (NER) is one of the contents of Knowledge Extraction (KE) that transforms data into knowledge representation. However, Chinese NER faces the problem of lacking clear word boundaries that limit the effectiveness of the KE. Although the flat lattice Transformer (FLAT) framework, which converts lattice structure into a flat structure including a set of spans, can effectively improve this problem and obtain advanced results, there still exist the problems of insensitivity to entity importance weights and insufficient feature learning. This paper proposes a weighted flat lattice Transformer architecture for Chinese NER, namely WFLAT. The WFLAT first adds a weight matrix into self-attention calculation, which can obtain finer-grained partitioning of entities to improve experimental performance, and then adopts a multi-layer Transformer encoder with each layer using a multi-head self-attention mechanism. Extensive experimental results on benchmarks demonstrate that our proposed KE model can obtain state-of-the-art performance for the Chinese NER task.

关键词： Representation learning Computational modeling Memory management Lattices Named entity recognition Transforms Knowledge representation

来源：评论

学校读者我要写书评

暂无评论

Progressive Human Motion Generation Based on Text and Few Motion Frames

arXiv

引用

arXiv 2025年

作者： Zeng, Ling-An Wu, Gaojie Wu, Ancong Hu, Jian-Fang Zheng, Wei-Shi School of Artificial Intelligence Sun Yat-sen University Guangdong Zhuhai519082 China School of Computer Science and Engineering Sun Yat-sen University Guangdong Guangzhou510275 China School of Computer Science and Engineering Sun Yat-sen University China The Guangdong Key Laboratory of Information Security Technology China The Key Laboratory of Machine Intelligence and Advanced Computing Ministry of Education China Peng Cheng Laboratory China

Although existing text-to-motion (T2M) methods can produce realistic human motion from text description, it is still difficult to align the generated motion with the desired postures since using text alone is insufficient for precisely describing diverse postures. To achieve more controllable generation, an intuitive way is to allow the user to input a few motion frames describing precise desired postures. Thus, we explore a new Text-Frame-to-Motion (TF2M) generation task that aims to generate motions from text and very few given frames. Intuitively, the closer a frame is to a given frame, the lower the uncertainty of this frame is when conditioned on this given frame. Hence, we propose a novel Progressive Motion Generation (PMG) method to progressively generate a motion from the frames with low uncertainty to those with high uncertainty in multiple stages. During each stage, new frames are generated by a Text-Frame Guided Generator conditioned on frame-aware semantics of the text, given frames, and frames generated in previous stages. Additionally, to alleviate the train-test gap caused by multi-stage accumulation of incorrectly generated frames during testing, we propose a Pseudo-frame Replacement Strategy for training. Experimental results show that our PMG outperforms existing T2M generation methods by a large margin with even one given frame, validating the effectiveness of our PMG. Code is available here. Copyright © 2025, The Authors. All rights reserved.

关键词： Human engineering

来源：评论

学校读者我要写书评

暂无评论

Schrödingerization based Quantum Circuits for Maxwell’s Equation with time-dependent source terms

arXiv

引用

arXiv 2024年

作者： Ma, Chuwen Jin, Shi Liu, Nana Wang, Kezhen Zhang, Lei School of Mathematical Sciences Shanghai Jiao Tong University Shanghai200240 China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai200240 China Ministry of Education Key Laboratory in Scientific and Engineering Computing Shanghai Jiao Tong University Shanghai200240 China University of Michigan Shanghai Jiao Tong University Joint Institute Shanghai200240 China

The Schrödingerisation method combined with the autonomozation technique in [10] converts general non-autonomous linear differential equations with non-unitary dynamics into systems of autonomous Schrödinger-type equations, via the so-called warped phase transformation that maps the equation into two higher dimension. Despite the success of Schrödingerisation techniques, they typically require the black box of the sparse Hamiltonian simulation, suitable for continuous-variable based analog quantum simulation. For qubit-based general quantum computing one needs to design the quantum circuits for practical implementation. This paper explicitly constructs a quantum circuit for Maxwell’s equations with perfect electric conductor (PEC) boundary conditions and time-dependent source terms, based on Schrödingerization and autonomozation, with corresponding computational complexity analysis. Through initial value smoothing and high-order approximation to the delta function, the increase in qubits from the extra dimensions only requires minor rise in computational complexity, almost log log 1/Ε where Ε is the desired precision. Our analysis demonstrates that quantum algorithms constructed using Schrödingerisation exhibit polynomial acceleration in computational complexity compared to the classical Finite Difference Time Domain (FDTD) format. Copyright © 2024, The Authors. All rights reserved.

关键词： Delta functions

来源：评论

学校读者我要写书评

暂无评论

Batch-in-Batch: A new adversarial training framework for initial perturbation and sample selection

arXiv

引用

arXiv 2024年

作者： Wu, Yinting Peng, Pai Cai, Bo Li, Le School of Mathematics and Statistics Key Lab NAA-MOE Central China Normal University Wuhan China School of Mathematics and Computer Science Jianghan University Wuhan China Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University China

Adversarial training methods commonly generate independent initial perturbation for adversarial samples from a simple uniform distribution, and obtain the training batch for the classifier without selection. In this work, we propose a simple yet effective training framework called Batch-in-Batch (BB) to enhance models robustness. It involves specifically a joint construction of initial values that could simultaneously generates m sets of perturbations from the original batch set to provide more diversity for adversarial samples;and also includes various sample selection strategies that enable the trained models to have smoother losses and avoid overconfident outputs. Through extensive experiments on three benchmark datasets (CIFAR-10, SVHN, CIFAR-100) with two networks (PreActResNet18 and WideResNet28-10) that are used in both the single-step (Noise-Fast Gradient Sign Method, N-FGSM) and multi-step (Projected Gradient Descent, PGD-10) adversarial training, we show that models trained within the BB framework consistently have higher adversarial accuracy across various adversarial settings, notably achieving over a 13% improvement on the SVHN dataset with an attack radius of 8/255 compared to the N-FGSM baseline model. Furthermore, experimental analysis of the efficiency of both the proposed initial perturbation method and sample selection strategies validates our insights. Finally, we show that our framework is cost-effective in terms of computational resources, even with a relatively large value of m. © 2024, CC BY.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Loss Network for Localization of Image Manipulation 19th

A Hybrid Loss Network for Localization of Image Manipulation

引用

19th International Workshop on Digital Forensics and Watermarking, IWDW 2020

作者： Yin, Qilin Wang, Jinwei Luo, Xiangyang Nanjing University of Information Science and Technology and Engineering Research Center of Digital Forensics Ministry of Education Nanjing210044 China State Key Laboratory of Mathematical Engineering and Advanced Computing Henan450001 China Shanxi Key Laboratory of Network and System Security Xidian University Xi’an710071 China

ISBN: (纸本)9783030694487

With the development of information security, localization of image manipulations havs become a hot topic. In this paper, a hybrid loss network is proposed for the manipulated image forensics. First, the patch prediction module extracts corresponding features representing the discrepancy of the tampered region boundaries. Then, these features are constrained by the Pixel Normalization, thereby improving the classification performance for the tampered patches. Finally, multi-scale patch prediction masks and semantic information are fused to segment out the tampered regions. The experiments demonstrate the proposed model can achieve high performance. © 2021, Springer Nature Switzerland AG.

关键词： Pixels

来源：评论

学校读者我要写书评

暂无评论

FOURIER NEURAL SOLVER FOR LARGE SPARSE LINEAR ALGEBRAIC SYSTEMS

arXiv

引用

arXiv 2022年

作者： Cui, Chen Jiang, Kai Liu, Yun Shu, Shi Hunan Key Laboratory for Computation and Simulation in Science and Engineering Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Large sparse linear algebraic systems can be found in a variety of scientific and engineering fields, and many scientists strive to solve them in an efficient and robust manner. In this paper, we propose an interpretable neural solver, the Fourier Neural Solver (FNS), to address them. FNS is based on deep learning and Fast Fourier transform. Because the error between the iterative solution and the ground truth involves a wide range of frequency modes, FNS combines a stationary iterative method and frequency space correction to eliminate different components of the error. Local Fourier analysis reveals that the FNS can pick up on the error components in frequency space that are challenging to eliminate with stationary methods. Numerical experiments on the anisotropy diffusion equation, convection-diffusion equation, and Helmholtz equation show that FNS is more efficient and more robust than the state-of-the-art neural *** Codes 65F10 65N22 68T07 35Q68 Copyright © 2022, The Authors. All rights reserved.

关键词： Fourier analysis

来源：评论

学校读者我要写书评

暂无评论

Vehicle Destination Prediction Based on Trajectory Data

Vehicle Destination Prediction Based on Trajectory Data

引用

Neural Networks, Information and Communication engineering (NNICE), International Conference on

作者： Wenming Guo Ruiqi Jia Che Zong Ruichao Li Key Laboratory of Trustworthy Distributed Computing and Service Ministry of Education School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing China School of Information Engineering Xinjiang Institute of Engineering Urumqi China School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China

With the increasing requirements of real-time traffic management in urban transportation, vehicle destination prediction data, as an important part of smart city brain data, is becoming more and more important in urban traffic management and operation. This paper builds a vehicle destination prediction scheme based on trajectory data. By collecting public vehicle trajectory datasets, the Sequence to Sequence (Seq2Seq) sequence generation model and the Text-Convolutional Neural Network (Text-CNN) sequence classification model are built respectively to implement the vehicle destination prediction. In order to evaluate the performance of the models, Accuracy and Mean Distance are used as metrics to compare the model performance under different training data conditions. Advantage analysis was done in combination with different application scenarios for practical application reference. According to the prediction performance of different models built in this work in different application scenarios, the advantages are analyzed for reference in practice.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Push-Pull Method for Decentralized Optimization via State Decomposition

arXiv

引用

arXiv 2023年

作者： Cheng, Huqiang Liao, Xiaofeng Li, Huaqing Zhao, You Key Laboratory of Dependable Services Computing in Cyber Physical Society Ministry of Education College of Computer Science Chongqing University Chongqing400044 China Chongqing Key Laboratory of Nonlinear Circuits and Intelligent Information Processing College of Electronic and Information Engineering Southwest University Chongqing400715 China

Distributed optimization is manifesting great potential in multiple fields, e.g., machine learning, control, and resource allocation. Existing decentralized optimization algorithms require sharing explicit state information among the agents, which raises the risk of private information leakage. To ensure privacy security, combining information security mechanisms, such as differential privacy and homomorphic encryption, with traditional decentralized optimization algorithms is a commonly used means. However, this would either sacrifice optimization accuracy or incur heavy computational burden. To overcome these shortcomings, we develop a novel privacy-preserving decentralized optimization algorithm, called PPSD, that combines gradient tracking with a state decomposition mechanism. Specifically, each agent decomposes its state associated with the gradient into two substates. One substate is used for interaction with neighboring agents, and the other substate containing private information acts only on the first substate and thus is entirely agnostic to other agents. For the strongly convex and smooth objective functions, PPSD attains a R-linear convergence rate. Moreover, the algorithm can preserve the agents’ private information from being leaked to honest-but-curious neighbors. Simulations further confirm the results. © 2023, CC BY.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Multitask kernel-learning parameter prediction method for solving time-dependent linear systems

arXiv

引用

arXiv 2022年

作者： Jiang, Kai Zhang, Juan Zhou, Qi Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

Matrix splitting iteration methods play a vital role in solving large sparse linear systems. Their performance heavily depends on the splitting parameters, however, the approach of selecting optimal splitting parameters has not been well developed. In this paper, we present a multitask kernel-learning parameter prediction method to automatically obtain relatively optimal splitting parameters, which contains simultaneous multiple parameters prediction and a data-driven kernel learning. For solving time-dependent linear systems, including linear differential systems and linear matrix systems, we give a new matrix splitting Kronecker product method, as well as its convergence analysis and preconditioning strategy. Numerical results illustrate our methods can save an enormous amount of time in selecting the relatively optimal splitting parameters compared with the exists methods. Moreover, our iteration method as a preconditioner can effectively accelerate GMRES. As the dimension of systems increases, all the advantages of our approaches becomes significantly. Especially, for solving the differential Sylvester matrix equation, the speedup ratio can reach tens to hundreds of times when the scale of the system is larger than one hundred thousand. Copyright © 2022, The Authors. All rights reserved.

关键词： Linear systems

来源：评论

学校读者我要写书评

暂无评论

A general alternating-direction implicit Newton method for solving complex continuous-time algebraic Riccati matrix equation

arXiv

引用

arXiv 2022年

作者： Li, Shifeng Jiang, Kai Zhang, Juan Key Laboratory of Intelligent Computing and Information Processing of Ministry of Education Hunan Key Laboratory for Computation and Simulation in Science and Engineering School of Mathematics and Computational Science Xiangtan University Hunan Xiangtan411105 China

In this paper, applying the Newton method, we transform the complex continuous-time algebraic Riccati matrix equation into a Lyapunov equation. Then, we introduce an efficient general alternating-direction implicit (GADI) method to solve the Lyapunov equation. The inexact Newton-GADI method is presented to save computational amount effectively. Moreover, we analyze the convergence of the Newton-GADI method. The convergence rate of the Newton-GADI and Newton-ADI methods is compared by analyzing their spectral radii. Furthermore, we give a way to select the quasi-optimal parameter. Corresponding numerical tests are shown to illustrate the effectiveness of the proposed algorithms. © 2022, CC BY-SA.

关键词： Newton-Raphson method

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：