检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Lin, Weichen Chen, Jiaxiang Huang, Ruomin Ding, Hu School of Data Science University of Science and Technology of China Anhui China Duke University United States School of Computer Science and Technology University of Science and Technology of China Anhui China

Continual learning (CL) is a fundamental topic in machine learning, where the goal is to train a model with continuously incoming data and tasks. Due to the memory limit, we cannot store all the historical data, and therefore confront the "catastrophic forgetting" problem, i.e., the performance on the previous tasks can substantially decrease because of the missing information in the latter period. Though a number of elegant methods have been proposed, the catastrophic forgetting phenomenon still cannot be well avoided in practice. In this paper, we study the problem from the gradient perspective, where our aim is to develop an effective algorithm to calibrate the gradient in each updating step of the model;namely, our goal is to guide the model to be updated in the right direction under the situation that a large amount of historical data are unavailable. Our idea is partly inspired by the seminal stochastic variance reduction methods (e.g., SVRG and SAGA) for reducing the variance of gradient estimation in stochastic gradient descent algorithms. Another benefit is that our approach can be used as a general tool, which is able to be incorporated with several existing popular CL methods to achieve better performance. We also conduct a set of experiments on several benchmark datasets to evaluate the performance in practice. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Internet of Brain, Thought, Thinking, and Creation

引用

Chinese Journal of Electronics 2022年第6期31卷 1025-1042页

作者： ZHANG Zhimin YIN Rui NING Huansheng School of Computer and Communication Engineering University of Science and Technology Beijing Beijing Engineering Research Center for Cyberspace Data Analysis and Applications

Thinking space came into being with the emergence of human civilization. With the emergence and development of cyberspace, the interaction between those two spaces began to take place. In the collision of thinking and technology, new changes have taken place in both thinking space and cyberspace. To this end, this paper divides the current integration and development of thinking space and cyberspace into three stages, namely Internet of brain(IoB), Internet of thought(IoTh), and Internet of thinking(IoTk). At each stage, the contents and technologies to achieve convergence and connection of spaces are discussed. Besides, the Internet of creation(IoC) is proposed to represent the future development of thinking space and cyberspace. Finally, a series of open issues are raised, and they will become thorny factors in the development of the Io C stage.

关键词： thinking space IoTk Internet of thinking IoTh Internet of thought cyberspace development Internet of Things Internet of brain cyber-physical systems IoB human civilization emergence

来源：评论

学校读者我要写书评

暂无评论

Identifying the best common factor model via exploratory eactor analysis

引用

Applied Mathematics(A Journal of Chinese Universities) 2024年第1期39卷 24-33页

作者： HE Bao-hua TANG Rui TAGN Qi-yi School of Big Data Fuzhou University of International Studies and TradeFuzhou 350202China School of Mathematics Sun Yat-Sen UniversityGuangzhou 510275China Department of Computer Science University of BathUK Institute of Insect Science Zhejiang UniversityHangzhou 310058China.

Currently,there is no solid criterion for judging the quality of the estimators in factor *** paper presents a new evaluation method for exploratory factor analysis that pinpoints an appropriate number of factors along with the best method for factor *** proposed technique consists of two steps:testing the normality of the residuals from the fitted model via the Shapiro-Wilk test and using an empirical quantified index to judge the quality of the factor *** are presented to demonstrate how the method is implemented and to verify its effectiveness.

关键词： factor analysis Shapiro-Wilk normality residuals

来源：评论

学校读者我要写书评

暂无评论

Impulsive Control of Nonlinear Multiagent Systems: A Hybrid Fuzzy Adaptive and Event-Triggered Strategy

引用

IEEE Transactions on Fuzzy Systems 2025年第6期33卷 1889-1898页

作者： Han, Fang Jin, Hai Huazhong University of Science and Technology National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Laboratory Cluster and Grid Computing Laboratory School of Computer Science and Technology Wuhan430074 China

In this article, we present a hybrid control approach that integrates an adaptive fuzzy mechanism with an event-triggered impulse strategy to address consensus control challenges in nonlinear multiagent systems (MASs) with uncertain information, both in leader and leaderless scenarios. First, a fuzzy logic-based adaptive control mechanism is proposed to handle system nonlinearity and uncertainty. This mechanism dynamically adjusts fuzzy control rules in real time, enabling the system to adapt to changing conditions and enhancing its robustness against nonlinear disturbances. Second, to alleviate communication overhead and reduce control frequency, an event-triggered impulse strategy is implemented. This strategy activates impulse control only under specific conditions, effectively minimizing control actions while maintaining system consensus. Using Lyapunov stability theory, sufficient conditions for achieving system consensus are established, demonstrating the global consensus and robustness of the MASs under certain criteria. Finally, numerical simulations and experimental evaluations validate the proposed method's effectiveness and its practical advantages. © 1993-2012 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Visual abstraction of dynamic network via improved multi-class blue noise sampling

引用

Frontiers of computer science 2023年第1期17卷 171-185页

作者： Yanni PENG Xiaoping FAN Rong CHEN Ziyao YU Shi LIU Yunpeng CHEN Ying ZHAO Fangfang ZHOU School of Computer Science and Engineering Central South UniversityChangsha 410083China Institute of Big Data Hunan University of Finance and EconomicsChangsha 410205China Rail Data Research and Application Key Laboratory of Hunan Province Changsha 410083China

Massive sequence view (MSV) is a classic timeline-based dynamic network visualization approach. However, it is vulnerable to visual clutter caused by overlapping edges, thereby leading to unexpected misunderstanding of time-varying trends of network communications. This study presents a new edge sampling algorithm called edge-based multi-class blue noise (E-MCBN) to reduce visual clutter in MSV. Our main idea is inspired by the multi-class blue noise (MCBN) sampling algorithm, commonly used in multi-class scatterplot decluttering. First, we take a node pair as an edge class, which can be regarded as an analogy to classes in multi-class scatterplots. Second, we propose two indicators, namely, class overlap and inter-class conflict degrees, to measure the overlapping degree and mutual exclusion, respectively, between edge classes. These indicators help construct the foundation of migrating the MCBN sampling from multi-class scatterplots to dynamic network samplings. Finally, we propose three strategies to accelerate MCBN sampling and a partitioning strategy to preserve local high-density edges in the MSV. The result shows that our approach can effectively reduce visual clutters and improve the readability of MSV. Moreover, our approach can also overcome the disadvantages of the MCBN sampling (i.e., long-running and failure to preserve local high-density communication areas in MSV). This study is the first that introduces MCBN sampling into a dynamic network sampling.

关键词： dynamic network visualization massive sequence view multi-class blue noise sampling visual abstraction

来源：评论

学校读者我要写书评

暂无评论

Automated face recognition using deep learning technique and center symmetric multivariant local binary pattern

引用

Neural Computing and Applications 2025年第1期37卷 263-281页

作者： Sekhar, J.C. Josephson, P. Joel Chinnasamy, A. Maheswari, M. Sankar, S. Kalangi, Ruth Ramya Department of Computer Science and Engineering NRI Institute of Technology Andhra Pradesh Guntur India Department of Electronics and Communication Engineering Malla Reddy Engineering College Telangana Hyderabad India Department of Data Science and Business Systems School of Computing SRMIST Kattankulathur Chennai India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Computer Science and Engineering Saveetha School of Engineering SIMATS Chennai India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vijayawada India

Researchers have recently created several deep learning strategies for various tasks, and facial recognition has made remarkable progress in employing these techniques. Face recognition is a noncontact, nonobligatory, acceptable, and harmonious biometric recognition method with a promising national and social security future. The purpose of this paper is to improve the existing face recognition algorithm, investigate extensive data-driven face recognition methods, and propose a unique automated face recognition methodology based on generative adversarial networks (GANs) and the center symmetric multivariable local binary pattern (CS-MLBP). To begin, this paper employs the center symmetric multivariant local binary pattern (CS-MLBP) algorithm to extract the texture features of the face, addressing the issue that C2DPCA (column-based two-dimensional principle component analysis) does an excellent job of removing the global characteristics of the face but struggles to process the local features of the face under large samples. The extracted texture features are combined with the international features retrieved using C2DPCA to generate a multifeatured face. The proposed method, GAN-CS-MLBP, syndicates the power of GAN with the robustness of CS-MLBP, resulting in an accurate and efficient face recognition system. Deep learning algorithms, mainly neural networks, automatically extract discriminative properties from facial images. The learned features capture low-level information and high-level meanings, permitting the model to distinguish among dissimilar persons more successfully. To assess the proposed technique’s GAN-CS-MLBP performance, extensive experiments are performed on benchmark face recognition datasets such as LFW, YTF, and CASIA-WebFace. Giving to the findings, our method exceeds state-of-the-art facial recognition systems in terms of recognition accuracy and resilience. The proposed automatic face recognition system GAN-CS-MLBP provides a solid basis for a

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-media cleaning system based on tip-electrode optimisation and its application in energy efficient purification 4

Multi-media cleaning system based on tip-electrode optimisat...

引用

4th International Conference on New Energy and Power Engineering, ICNEPE 2024

作者： Liang, Tianyou Huang, Tingkun Liang, Baoer Zhu, Guanyu Liang, Yanchun Zhu, Tianyuan Zhuhai College of Science and Technology School of Computer Science Zhuhai China Zhuhai College of Science and Technology School of Life Science Zhuhai China Zhuhai College of Science and Technology School of Big Data Science Zhuhai China

ISBN: (纸本)9798331516086

In this paper, a multi-media cleaning system based on the optimisation of the tip electrode structure is developed, which significantly improves the electrochemical reaction efficiency and realises the efficient purification of air, water and industrial waste gas by adopting the carbon nanotube material and the design of awn-shaped tip electrode. The experimental results show that the system has low energy consumption, long service life and excellent purification performance, and is suitable for a variety of environmental treatment scenarios with broad application prospects. © 2024 IEEE.

关键词： Air cleaners

来源：评论

学校读者我要写书评

暂无评论

Robust Multi-Object Tracking Using Vision Sensor with Fine-Grained Cues in Occluded and Dynamic Scenes

引用

IEEE Sensors Journal 2025年第11期25卷 20547-20560页

作者： Hu, Yaoqi Sun, Jinqiu Jin, Hao Niu, Axi Yan, Qingsen Zhu, Yu Zhang, Yanning School of Computer Science China School of Astronautics China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology Northwestern Polytechnical University Dongxiang Road Shaanxi Xi'an710129 China

Multi-object tracking (MOT) using vision sensors remains a challenging problem, particularly in dynamic backgrounds and severe occlusions. Existing methods, relying on holistic appearance or spatial cues, fail to capture detailed information within object regions and the background, resulting in inaccurate and inconsistent tracking. To address these issues, we propose a novel Detail-Driven Multi-Object Tracking (DD-MOT) method that revisits and leverages fine-grained cues to discover the dynamics of both object regions and the background, facilitating the recovery and association of trajectories. Specifically, the proposed method consists of three key modules: (i) Points Trajectories Generator, (ii) Camera Motion and Occlusion Compensation, and (iii) Fine- and Coarsegrained Association. The Points Trajectories Generator is responsible for generating fine-grained cues by sampling an initial set of points, generating point trajectories, and refining the initial set of points. The Camera Motion and Occlusion Compensation module utilizes the background and object point trajectories to correct background motion and recover occluded object bounding boxes. Finally, the Fine- and Coarse-grained Association module leverages point trajectory cues to assist in establishing a more effective association strategy, combining both fine-grained and coarse-grained spatial cues from the object bounding boxes. We evaluate our DD-MOT method on several benchmark datasets, including MOT17, MOT20, demonstrating that it consistently outperforms state-of-the-art (SOTA) methods in key metrics such as HOTA (64.2, 62.6), MOTA (80.8, 78.1), and IDF1 (78.8, 77.1). © 2025 IEEE.

关键词： Motion compensation

来源：评论

学校读者我要写书评

暂无评论

Multi-Modal Self-Perception Enhanced Large Language Model for 3D Region-of-Interest Captioning With Limited data

引用

IEEE Transactions on Multimedia 2025年 27卷 2935-2948页

作者： Shi, Lu Kan, Shichao Jin, Yi Zhang, Linna Cen, Yigang Bejing Jiaotong University State Key Laboratory of Advanced Rail Autonomous Operation School of Computer Science and Technology Visual Intellgence + X International Cooperation Joint Laboratory of MOE Beijing100044 China Central South University School of Computer Science and Engineering Changsha410083 China Beijing Jiaotong University Key Laboratory of Big Data and Artificial Intelligence in Transportation Ministry of Education and the School of Computer Science and Technology Beijing100044 China Guizhou University School of Mechanical Engineering Guiyang550025 China

3D Region-of-Interest (RoI) Captioning involves translating a model's understanding of specific objects within a complex 3D scene into descriptive captions. Recent advancements in Large Language Models (LLMs) have shown great potential in this area. Existing methods capture the visual information from RoIs as input tokens for LLMs. However, this approach may not provide enough detailed information for LLMs to generate accurate region-specific captions. In this paper, we introduce Self-RoI, a Large Language Model with multi-modal self-perception capabilities for 3D RoI captioning. To ensure LLMs receive more precise and sufficient information, Self-RoI incorporates Implicit Textual Info. Perception to construct a multi-modal vision-language information. This module utilizes a simple mapping network to generate textual information about basic properties of RoI from vision-following response of LLMs. This textual information is then integrated with the RoI's visual representation to form a comprehensive multi-modal instruction for LLMs. Given the limited availability of 3D RoI-captioning data, we propose a two-stage training strategy to optimize Self-RoI efficiently. In the first stage, we align 3D RoI vision and caption representations. In the second stage, we focus on 3D RoI vision-caption interaction, using a disparate contrastive embedding module to improve the reliability of the implicit textual information and employing language modeling loss to ensure accurate caption generation. Our experiments demonstrate that Self-RoI significantly outperforms previous 3D RoI captioning models. Moreover, the Implicit Textual Info. Perception can be integrated into other multi-modal LLMs for performance enhancement. We will make our code available for further research. © 1999-2012 IEEE.

关键词： Digital elevation model

来源：评论

学校读者我要写书评

暂无评论

Angle-uniform parallel coordinates

引用

Computational Visual Media 2023年第3期9卷 495-512页

作者： Kaiyi Zhang Liang Zhou Lu Chen Shitong He Daniel Weiskopf Yunhai Wang School of Computer Science and Technology Shandong UniversityQingdao 266237China National Institute of Health Data Science Peking UniversityBeijing 100191China Visualization Research Center(VISUS) University of Stuttgart70569 StuttgartGermany

We present angle-uniform parallel coordinates,a data-independent technique that deforms the image plane of parallel coordinates so that the angles of linear relationships between two variables are linearly mapped along the horizontal axis of the parallel coordinates *** being a common method for visualizing multidimensional data,parallel coordinates are ineffective for revealing positive correlations since the associated parallel coordinates points of such structures may be located at infinity in the image plane and the asymmetric encoding of negative and positive correlations may lead to unreliable *** address this issue,we introduce a transformation that bounds all points horizontally using an angleuniform mapping and shrinks them vertically in a structure-preserving fashion;polygonal lines become smooth curves and a symmetric representation of data correlations is *** further propose a combined subsampling and density visualization approach to reduce visual clutter caused by *** method enables accurate visual pattern interpretation of data correlations,and its data-independent nature makes it applicable to all multidimensional *** usefulness of our method is demonstrated using examples of synthetic and real-world datasets.

关键词： parallel coordinates multidimensional data deformation correlations

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：