检索结果-内蒙古大学图书馆

48th IEEE International Conference on Acoustics, Speech and Signal Processing, ICASSP 2023

作者： Yang, Kun Lu, Jun Heilongjiang University College of Computer Science and Technology Harbin150080 China Jiaxiang Industrial Technology Research Institute of Hlju Jining China Key Laboratory of Database and Parallel Computing of Heilongjiang Province Harbin China

ISBN: (纸本)9781728163277

The proposed method in this paper proposes an end-to-end unsupervised semantic segmentation architecture DMSA based on four loss functions. The framework uses Atrous Spatial Pyramid Pooling (ASPP) module to enhance feature extraction. At the same time, a dynamic dilation strategy is designed to better capture multi-scale context information. Secondly, a Pixel-Adaptive Refinement (PAR) module is introduced, which can adaptively refine the initial pseudo labels after feature fusion to obtain high quality pseudo labels. Experiments show that the proposed DSMA framework is superior to the existing methods on the saliency dataset. On the COCO 80 dataset, the MIoU is improved by 2.0, and the accuracy is improved by 5.39. On the Pascal VOC 2012 Augmented dataset, the MIoU is improved by 4.9, and the accuracy is improved by 3.4. In addition, the convergence speed of the model is also greatly improved after the introduction of the PAR module. © 2023 IEEE.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Cryptocurrency Transaction Network Embedding From Static and Dynamic Perspectives: An Overview

引用

IEEE/CAA Journal of Automatica Sinica 2023年第5期10卷 1105-1121页

作者： Yue Zhou Xin Luo MengChu Zhou the School of Computer Science and Technology Chongqing University of Posts and TelecommunicationsChongqing 400065 the Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Institute of Green and Intelligent TechnologyChinese Academy of SciencesChongqing 400714 the Chongqing School University of Chinese Academy of SciencesChongqing 400714China the College of Computer and Information Science Southwest UniversityChongqing 400715China the School of Information and Electronic Engineering Zhejiang Gongshang UniversityHangzhou 310018China the Helen and John C.Hartmann Department of Electrical and Computer Engineering New Jersey Institute of TechnologyNewark NJ 07102 USA

Cryptocurrency, as a typical application scene of blockchain, has attracted broad interests from both industrial and academic communities. With its rapid development, the cryptocurrency transaction network embedding(CTNE) has become a hot topic. It embeds transaction nodes into low-dimensional feature space while effectively maintaining a network structure,thereby discovering desired patterns demonstrating involved users' normal and abnormal behaviors. Based on a wide investigation into the state-of-the-art CTNE, this survey has made the following efforts: 1) categorizing recent progress of CTNE methods, 2) summarizing the publicly available cryptocurrency transaction network datasets, 3) evaluating several widely-adopted methods to show their performance in several typical evaluation protocols, and 4) discussing the future trends of CTNE. By doing so, it strives to provide a systematic and comprehensive overview of existing CTNE methods from static to dynamic perspectives,thereby promoting further research into this emerging and important field.

关键词： Big data analysis cryptocurrency transaction network embedding(CTNE) dynamic network network embedding network representation static network

来源：评论

学校读者我要写书评

暂无评论

Generalized Goldwasser and Micali’s Type Cryptosystem

引用

Journal of computer Science & technology 2022年第2期37卷 459-467页

作者： Ying Guo Zhen-Fu Cao Xiao-Lei Dong Department of Computer Science and Engineering Shanghai Jiao Tong UniversityShanghai 200240China Shanghai Key Laboratory of Trustworthy Computing East China Normal UniversityShanghai 200062China Institute of Intelligent Science and Technology Tongji UniversityShanghai 200092China

In 1982,Goldwasser and Micali proposed the first probabilistic public key cryptosystem with indistinguishability under chosen plaintext attack security based on the quadratic residuosity *** expansion of Goldwasser's scheme is quite large,thereby the scheme is inefficient.A lot of schemes have been proposed to reduce the ciphertext *** schemes use the same encryption algorithm as Goldwasser's scheme with different parameters and keys,which we call them Goldwasser and Micali's type(GM-type)***-type schemes can be divided into two categories according to different parameters and decryption *** this paper,we propose the first generalized GM-type scheme combining these two *** GM-type schemes are special cases of our generalized GM-type *** ciphertext expansion of our scheme is smaller than that of any other GM-type schemes.

关键词： Goldwasser and Micali's type(GM-type)scheme k-th power residuosity discrete logarithm problem

来源：评论

学校读者我要写书评

暂无评论

When Does Sora Show:The Beginning of TAO to Imaginative Intelligence and Scenarios Engineering

引用

IEEE/CAA Journal of Automatica Sinica 2024年第4期11卷 809-815页

作者： Fei-Yue Wang Qinghai Miao Lingxi Li Qinghua Ni Xuan Li Juanjuan Li Lili Fan Yonglin Tian Qing-Long Han School of Artificial Intelligence University of Chinese Academy of SciencesBeijing 100049China State Key Laboratory for Management and Control of Complex Systems Chinese Academy of SciencesBeijing 100190China Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIndianapolisIN 46202USA Faculty of Innovation Engineering Macao University of Science and TechnologyMacao 999078China Virtual Reality Fundamental Research Laboratory Department of Mathematics and TheoriesPeng Cheng LaboratoryShenzhen 518000China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of AutomationChinese Academy of SciencesBeijing 100190China School of Information and Electronics Beijing Institute of TechnologyBeijing 100081China School of Science Computing and Engineering TechnologiesSwinburne University of TechnologyMelbourneVIC 3122Australia

DURING our discussion at workshops for writing“What Does ChatGPT Say:The DAO from Algorithmic Intelligence to Linguistic Intelligence”[1],we had expected the next milestone for Artificial Intelligence(AI)would be in the direction of Imaginative Intelligence(II),i.e.,something similar to automatic wordsto-videos generation or intelligent digital movies/theater technology that could be used for conducting new“Artificiofactual Experiments”[2]to replace conventional“Counterfactual Experiments”in scientific research and technical development for both natural and social studies[2]-[6].Now we have OpenAI’s Sora,so soon,but this is not the final,actually far away,and it is just the beginning.

关键词： something Intelligence replace

来源：评论

学校读者我要写书评

暂无评论

A New Noise-Tolerant Dual-Neural-Network Scheme for Robust Kinematic Control of Robotic Arms With Unknown Models

引用

IEEE/CAA Journal of Automatica Sinica 2022年第10期9卷 1778-1791页

作者： Ning Tan Peng Yu Zhiyan Zhong Fenglei Ni IEEE the School of Computer Science and Engineering&Key Laboratory of Machine Intelligence and Advanced Computing Ministry of EducationSun Yat-sen UniversityGuangzhou 510006China the School of Automation Guangdong Polytechnic Normal UniversityGuangzhou 510665China the State Key Laboratory of Robotics and Systems Harbin Institute of Technology(HIT)Harbin 150080China

Taking advantage of their inherent dexterity,robotic arms are competent in completing many tasks *** a result of the modeling complexity and kinematic uncertainty of robotic arms,model-free control paradigm has been proposed and investigated ***,robust model-free control of robotic arms in the presence of noise interference remains a problem worth *** this paper,we first propose a new kind of zeroing neural network(ZNN),i.e.,integration-enhanced noise-tolerant ZNN(IENT-ZNN)with integration-enhanced noisetolerant ***,a unified dual IENT-ZNN scheme based on the proposed IENT-ZNN is presented for the kinematic control problem of both rigid-link and continuum robotic arms,which improves the performance of robotic arms with the disturbance of noise,without knowing the structural parameters of the robotic *** finite-time convergence and robustness of the proposed control scheme are proven by theoretical ***,simulation studies and experimental demonstrations verify that the proposed control scheme is feasible in the kinematic control of different robotic arms and can achieve better results in terms of accuracy and robustness.

关键词： Dual zeroing neural networks(ZNN) finite-time convergence model-free robot control robustness analysis

来源：评论

学校读者我要写书评

暂无评论

A Versatile Low-Light Enhancement Module for Improved Workpiece Detection 13

A Versatile Low-Light Enhancement Module for Improved Workpi...

引用

13th International Conference of Information and Communication technology, ICTech 2024

作者： Yin, ZhenYu Lin, DaHeng Wang, XiaoHui Xin, Qi Zhang, XueMei Shenyang Institute of Computing Technology Chinese Academy of Sciences Shenyang110168 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing100049 China Liaoning Key Laboratory of Domestic Industrial Control Platform Technology on Basic Hardware & Software China School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110168 China

ISBN: (纸本)9798350376258

This study presents a versatile Low-Light Enhancement Module (LLEM) to enhance object detection models, particularly for workpieces in challenging lighting conditions. The LLEM seamlessly integrates into existing models, addressing low-light challenges through a denoising branch, a global branch, and a Structural Perception loss for image quality improvement. The denoising branch utilizes Residual Denoising Modules to effectively reduce noise and preserve low-level features. Meanwhile, the global branch focuses on color recovery and gamma correction. Experimental results show YOLOv3+LLEM significantly improves detection performance, achieving a mAP increase from 88.0% to 91.9%. This enhancement, especially with the introduction of Structural Perception loss, maintains computational efficiency, validating its practicality for industrial workpiece detection in low-light conditions. ©2024 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Continuous Verification of Catastrophic Recalling in Machine Unlearning via Adversarial Testing 9

Continuous Verification of Catastrophic Recalling in Machine...

引用

9th IEEE International Conference on Data Science in Cyberspace, DSC 2024

作者： Qu, Y. Neil Ji, Zonghao Cui, Lei Zhang, Chong Liu, Lei Tian, Zhiyi Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Jinan250031 China Shandong Fundamental Research Center for Computer Science Shandong Provincial Key Laboratory of Computer Networks Jinan250031 China Deakin University School of IT VIC3125 Australia Xidian University Guangzhou Institute of Technology Guangzhou510555 China University of Technology School of Computer Science SydneyNSW2007 Australia

ISBN: (纸本)9798350391367

Throughout the process of machine unlearning, in order to fulfill the requirements of machine unlearning and to comply with the rules of the right to be forgotten, it is natural to verify whether the unlearning model actually removes data points. Therefore, machine unlearning verification plays a crucial role. However, existing validation methods only perform one validation, and it is still challenging to determine whether subsequent updates of the model still maintain the unlearning effect. To address this challenge, we propose a novel continuous verification of catastrophic recalling in machine unlearning framework that aims to continuously evaluate whether a machine learning model effectively forgets specified data after an update. In this work, we first introduce adversarial testing as a crucial part of the overall framework. Verification then continues as the unlearned model is updated (adding or continuing to forget data points). We also analyzed the possibility that learning new data after unlearning may diminish the effect. Overall, our continuous unlearning verification framework provides a proactive approach to protecting individual privacy in the machine learning domain, thus facilitating the generation of more robust unlearning algorithms. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CurMIM: Curriculum Masked Image Modeling

CurMIM: Curriculum Masked Image Modeling

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Liu, Hao Wang, Kun Han, Yudong Wang, Haocong Hu, Yupeng Wang, Chunxiao Nie, Liqiang School of Software Shandong University Jinan China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology Shandong Academy of Sciences Jinan China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

ISBN: (纸本)9798350368741

Masked Image Modeling (MIM), following "mask-and-reconstruct" scheme, is a promising self-supervised method to learn scalable visual representation. Studies indicate that selecting an effective mask strategy is vital for MIM. However, existing approaches often rely on static pre-defined priors, which limit their ability to adapt mask strategies dynamically for network optimization. In this paper, we focus on the learning process of the network and introduce human-like curriculum into MIM for dynamic representation refinement, and propose an end-to-end framework Curriculum Masked Image Modeling (CurMIM). CurMIM consists of two components: Mask Priority Measurer, which acts as a curriculum learner to determine mask priority values using the network's intrinsic state information, and Dual Adaptive Selector, which serves as a curriculum scheduler to create effective masks based on these values. With negligible extra parameters, our curriculum-based method consistently establishes noticeable improvements across varying model sizes and benchmarks, showing effectiveness and generalization. © 2025 IEEE.

关键词： Curriculum Learning Image Representation Masked Image Modeling Visual Pre-training

来源：评论

学校读者我要写书评

暂无评论

Experimental demonstration of quantum transport enhancement using time-reversal symmetry breaking on a silicon photonic chip

引用

Science China(Physics,Mechanics & Astronomy) 2022年第10期65卷 2-9页

作者： Yang Wang Xinyao Yu Shichuan Xue Yizhi Wang Junwei Zhan Chao Wu Pingyu Zhu Qilin Zheng Miaomiao Yu Yingwen Liu Xiaogang Qiang Junjie Wu Xuejun Yang Ping Xu Institute for Quantum Information&State Key Laboratory of High Performance Computing College of Computer Science and TechnologyNational University of Defense TechnologyChangsha 410073China National Innovation Institute of Defense Technology Academy of Military SciencesBeijing 100071China National Laboratory of Solid State Microstructures and School of Physics Nanjing UniversityNanjing 210093China

The continuous-time quantum walk is a basic model for studying quantum transport and developing quantum-enhanced algorithms. Recent studies show that by introducing a phase into the standard continuous-time quantum walk model, the time-reversal symmetry can be broken without changing the Hermitian property of the Hamiltonian. The time-reversal symmetry breaking quantum walk shows advantages in quantum transport, such as perfect state transfer, directional control, transport speedup, and quantum transport efficiency enhancement. In this work, we implement the time-reversal symmetry breaking quantum walks on a reconfigurable silicon photonic chip and demonstrate the enhancement introduced by breaking time-reversal symmetry. Perfect state transfer on a three-site ring, a quantum switch implemented on a six-site graph, and transport speedup using a linear chain of triangles are demonstrated with high fidelity. Time-reversal asymmetry has also been used in a simplified light-harvesting model,implying the potential of time-reversal symmetry breaking in photosynthesis investigations.

关键词： quantum walk time-reversal asymmetry quantum transport

来源：评论

学校读者我要写书评

暂无评论

Entity Alignment Study Based on Hybrid Similarity Calculation 9

Entity Alignment Study Based on Hybrid Similarity Calculatio...

引用

9th International Conference on computer and Communications, ICCC 2023

作者： Zhang, Xinyue Ren, Chulan Yu, Bo Shenyang University of Chemical Technology College of Computer Science and Technology Shenyang China Liaoning Provincial Key Laboratory of Industrial Intelligent Technology for Chemical Processes Shenyang China Chinese Academy of Sciences Shenyang Institute of Computing Technology Shenyang China

ISBN: (纸本)9798350317251

The task of entity alignment is to determine whether two or more entities are pointing to the same object in the real world. In information retrieval tasks, entity alignment can help us to identify and connect related entities in different data sources, providing more accurate and comprehensive search results. The LCS algorithm is a simple and commonly used entity alignment method, which measures the similarity by finding the longest common subsequence of two strings but it ignores the order of words and semantic information. This may result in entities that are semantically similar but have different character order being considered dissimilar. By combining LCS and Word2Vec, it is possible to consider both formal similarity and semantic similarity of entities but this approach is more sensitive to the presence of misspellings in the data and lacks multi-level understanding of the entities, which may lead to inaccurate alignment results. To address the above problems, this paper proposes two improvement methods Lcs+Word2Vec- Word Rotator's Distance and Lcs+bert-whitening. In order to validate the improvement methods proposed in this paper, the unclassified tax invoices provided by the tax system are used as the experimental data for experiments, and h@5 (Hits@5), mr( Mean Rank) and mrr (Mean Reciprocal Ranking) are used as experimental evaluation indexes. Finally, the comparison experiment shows that Lcs+bert-whitening is better on the alignment task. © 2023 IEEE.

关键词： Semantics

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：