检索结果-内蒙古大学图书馆

2nd International Conference on computer, Big Data and Artificial Intelligence, ICCBDAI 2021

作者： Zheng, Menghua Xu, Jiayu Shen, Yinjie Tian, Chunwei Li, Jian Fei, Lunke Zong, Ming Liu, Xiaoyang School of Software Northwestern Polytechnic University Xi'an China Yangtze River Delta Research Institute of NPU Taicang China Shenzhen Research Institute Guangdong Databeyond Technology Co. Ltd Guangdong Shenzhen China Software Technology Co. Ltd. China School of Computers Guangdong University of Technology Guangzhou510006 China School of Electronics Engineering and Computer Science Peking University Beijing China School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

Deep learning techniques as well as CNNs can learn power context information, they have been widely applied in image recognition. However, deep CNNs may reply on large width and large depth, which may increase computational costs. Attention mechanism fused into CNNs can address this problem. In this paper, we summary an attention mechanism acts a CNN for image classification. Firstly, the survey shows the development of CNNs for image classification. Then, we illustrate basis of CNNs and attention mechanisms for image classification. Next, we give the main architecture of CNNs with attentions, public and our collected datasets, experimental results in image classification. Finally, we point out potential research points, challenges attention-based for image classification and summary the whole paper. © 2022 Institute of Physics Publishing. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Can Individuals be Repeatedly Selected for Mutation in Matrix-Based DE? A Comparative Study

Can Individuals be Repeatedly Selected for Mutation in Matri...

引用

Machine Intelligence Theory and Applications (MiTA), International Conference on

作者： Ling-Ling Wei Bing Sun Jian-Yu Li Qiang Yang Jing Xu Zong-Gan Chen Fei-Yi Tang School of Computer Science South China Normal University Guangzhou China College of Artificial Intelligence Nankai University Tianjin China School of Artificial Intelligence Nanjing University of Information Science and Technology Jiangsu China School of Information Engineering Guangzhou Panyu Polytechnic Pazhou Lab Guangdong China

ISBN: (数字)9798350385670

ISBN: (纸本)9798350385687

Evolutionary Computation (EC) is a class of algorithms derived from the simulation of natural phenomena, which faces the challenges of long running times and high computing loads resulting from large-scale problems. For this reason, the matrix-based EC (MEC) has been presented as an extension of classic EC algorithms to address large-scale optimization. The MEC can be implemented directly on high-performance computing resources, thus accelerating the computation of evolutionary operators. However, MEC is still in its infancy and lacks deeper analysis. Hence, this paper analyzes and investigates matrix-based differential evolution (MDE) and advances the development of related research through theoretical analysis and experimental validation, which has two contributions. First, through the comprehensive comparison of MDE and DE in different problems, we compare the solution quality and computational speed of MDE and DE, and show that the solution quality of MDE is not significantly different from that of DE, but the computational speed of MDE is much faster than that of DE. Second, we also further analyze the mutation mechanism of MDE, focusing on the effect of the repeatability of individuals in the mutation process on the performance of the algorithms, which provides a basis for future research on MDE of MEC.

关键词： High performance computing Focusing Evolutionary computation Stability analysis Reproducibility of results Problem-solving Optimization Machine intelligence Faces Convergence

来源：评论

学校读者我要写书评

暂无评论

Explicitly Guided Difficulty-Controllable Visual Question Generation 39

Explicitly Guided Difficulty-Controllable Visual Question Ge...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Xie, Jiayuan Cheng, Mengqiu Zhang, Xinting Cai, Yi Hu, Guimin Xie, Mengying Li, Qing Department of Computing The Hong Kong Polytechnic University Hong Kong School of Software Engineering South China University of Technology Guangzhou China Department of Computer Science University of Copenhagen Denmark Department of Mathematics The University of Hong Kong Hong Kong College of Computer Science Chongqing University China Guangdong Neusoft University Foshan China

ISBN: (纸本)157735897X

Visual question generation (VQG) aims to generate questions from images automatically. While existing studies primarily focus on the quality of generated questions, such as fluency and relevance, the difficulty of the questions is also a crucial factor in assessing their quality. Question difficulty directly impacts the effectiveness of VQG systems in applications like education and human-computer interaction, where appropriately challenging questions can stimulate learning interest and improve interaction experiences. However, accurately defining and controlling question difficulty is a challenging task due to its multidimensional and subjective nature. In this paper, we propose a new definition of the difficulty of questions, i.e., being positively correlated with the number of reasoning steps required to answer a question. For our definition, we construct a corresponding dataset and propose a benchmark as a foundation for future research. Our benchmark is designed to progressively increase the reasoning steps involved in generating questions. Specifically, we first extract the relationships among objects in the image to form a reasoning chain, then gradually increase the difficulty by rewriting the generated question to include more reasoning sub-chains. Experimental results on our constructed dataset show that our benchmark significantly outperforms existing baselines in controlling the reasoning chains of generated questions, producing questions with varying difficulty levels. © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Efficient Privacy-Preserving Multi-Functional Data Aggregation Scheme for Multi-Tier IoT System

Efficient Privacy-Preserving Multi-Functional Data Aggregati...

引用

IEEE Symposium on computers and Communications (ISCC)

作者： Yunting Tao Fanyu Kong Yuliang Shi Jia Yu Hanlin Zhang Huiyi Liu School of Software Shandong University College of Information Engineering Binzhou Polytechnic College of Computer Science and Technology Qingdao University Shandong Sansec Information Technology Co. Ltd

The proliferation of Internet of Things (IoT) devices has led to the generation of massive amounts of data that require efficient aggregation for analysis and decision-making. However, multi-tier IoT systems, which involve multiple layers of devices and gateways, face more complex security challenges in data aggregation compared to ordinary IoT systems. In this paper, we propose an efficient privacy-preserving multi-functional data aggregation scheme for multi-tier IoT architecture. The scheme supports privacy-preserving calculation of mean, variance, and anomaly proportion. The scheme uses the Paillier cryptosystem and the BLS algorithm for encryption and signature, and uses blinding techniques to keep the size of the IoT system secret. In order to make the Paillier algorithm more suitable for the IoT scenario, we also improve its efficiency of encryption and decryption. The performance evaluation shows that the scheme improves encryption efficiency by 43.7% and decryption efficiency by 45% compared to the existing scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Top-Down Target Object Detection Through Context

Top-Down Target Object Detection Through Context

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Ibrahim M. H. Rahman Christopher Hollitt Mengjie Zhang Osama Rehman Aisha Ajmal Simon Jigwan Park Information Technology The Open Polytechnic of New Zealand Wellington New Zealand School of Engg. and Computer Science Victoria University of Wellington Wellington New Zealand Department of Software Engineering Bahria University Karachi Pakistan

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

Visual attention is crucial for identifying the most salient regions in an image. However, when the objective involves higher-level visual tasks, such as target object detection, it becomes necessary to incorporate high-level information to guide the search for the target. This process, known as top-down saliency detection, leverages guidance sources like contextual information and target features to identify regions of interest that are more likely to contain the target object. In this paper, we propose a model that generates top-down saliency maps by adjusting the feature map weights of a universal visual attention model based on contextual information. While contextual information has traditionally been used to understand the gist of an image, it has not been integrated into the creation of saliency maps for target object detection. We demonstrate that incorporating contextual information into a visual attention model enhances target object detection performance. The proposed model, tested on six datasets, shows significant improvements in detecting target objects compared to models that do not utilize contextual information.

关键词： Weight measurement Visualization Accuracy Object detection Feature extraction Search problems Tuning Optimization Context modeling Saliency detection

来源：评论

学校读者我要写书评

暂无评论

A Performance Investigation of Genetic Algorithm with Different Evolutionary Operators

A Performance Investigation of Genetic Algorithm with Differ...

引用

Machine Intelligence Theory and Applications (MiTA), International Conference on

作者： Jian-Yu Li Zhao-Kun Shao Zi-Jia Wang Yuhui Zhang Ruoyu Zhu Zong-Gan Chen Tao Li College of Artificial Intelligence Nankai University Tianjin China College of Electrical and Electronic Engineering Hanyang University Ansan Korea College of Software Engineering Guangzhou University Guanzhou China College of Computer Science and Technology Dongguan University of Technology Dongguan China School of Computer Science South China Normal University Guangzhou China College of Computer and Information Engineering Henan Normal University Xinxiang China

ISBN: (数字)9798350385670

ISBN: (纸本)9798350385687

Genetic Algorithm (GA) as a bio-inspired optimization technique, has shown significant potential for applications in many fields. This paper aims to provide a comprehensive overview of the main types of evolutionary operators in GA—selection, crossover, and mutation, which have a direct and significant influence on optimization performance. First, this study systematically summarizes the various evolutionary operators currently used in the field of GA. Subsequently, these different operators are embedded into the standard GA framework to assess their influence on algorithm performance. Last, this paper also explores the effect of setting crossover and mutation rates on GA performance, determining the optimal values of these parameters through a series of experiments. This research not only offers a comprehensive overview of the evolutionary operators in GA but also demonstrates the specific performance of different operator combinations through empirical evidence, providing valuable reference for further research and application of GA.

关键词： Refining Focusing Space exploration Optimization Standards Machine intelligence Genetic operators Convergence

来源：评论

学校读者我要写书评

暂无评论

Correlation Fusion with Instance-level Auto-weighted for Multi-view Graph Clustering

Correlation Fusion with Instance-level Auto-weighted for Mul...

引用

IEEE International Conference on High Performance Computing and Communications (HPCC)

作者： Xuan Chen Zhikui Chen Liang Yao Shubin Ma Peng Li Shuo Yu School of Software Dalian University of Technology Da'lian China School of Electrical Engineering Anhui Polytechnic University Wu'hu China School of Computer Science and Technology Dalian University of Technology Da'lian China

Multi-view graph clustering (MGC) has emerged as a hot research topic due to its effectiveness. Previous works mainly focus on the fusion of similarity graphs to exploit the complementary and consistent. However, these approaches suffer from three shortcomings: 1) The distance similarity estimate by the linear Euclidean metric may be incorrect in revealing the association relationship of heterogeneous multi-view samples. 2) Most of them often weight the whole view to balance the effect of different views, which ignores the importance of local samples. 3) They fail to preserve the inherent manifold structure between views via directly applying similarity matrix fusion to obtain a consistent graph. To fill these gaps, this paper proposed a novel framework called correlation fusion with instance-level auto-weighted for MGC (CFIMGC). In particular, the Spearman distance is leveraged to effectively characterize the versatile correlation matrix. The sample-level auto-weighted fusion mechanism is presented for flexible assigning weight values to different sample-wise relations in intra-view and inter-view, through which the complementary of numerous correlation matrices is appropri-ately explored to produce a consistent correlation matrix. What's more, a probability graph is adaptively learned based on the fusion correlation matrix for constructing a clustering-friendly similarity graph. Meanwhile, an alternating iteration algorithm is devised to address the non-convex joint optimization problem. Comprehensive experiment results on seven widely used but challenging multi-view datasets demonstrate that the proposed method yields superiority in clustering performance against six state-of-the-art counterparts.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network

arXiv

引用

arXiv 2023年

作者： Wei, Mingze Huang, Yaomin Xu, Zhiyuan Liu, Ning Che, Zhengping Zhang, Xinyu Shen, Chaomin Feng, Feifei Shan, Chun Tang, Jian School of Software Engineering East China Normal University China School of Computer Science East China Normal University China Midea Group China School of Electronics and Information Guangdong Polytechnic Normal University China

In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. We present an effective end-to-end network, CMG-Net, for grasping unknown objects in a cluttered environment by efficiently predicting multi-finger grasp poses and hand configurations from a single-shot point cloud. Moreover, we create a synthetic grasp dataset that consists of five thousand cluttered scenes, 80 object categories, and 20 million annotations. We perform a comprehensive empirical study and demonstrate the effectiveness of our grasping representation and CMG-Net. Our work significantly outperforms the state-of-the-art for three-finger robotic hands. We also demonstrate that the model trained using synthetic data performs very well for real robots. Copyright © 2023, The Authors. All rights reserved.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

CMG-Net: An End-to-End Contact-based Multi-Finger Dexterous Grasping Network

CMG-Net: An End-to-End Contact-based Multi-Finger Dexterous ...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Mingze Wei Yaomin Huang Zhiyuan Xu Ning Liu Zhengping Che Xinyu Zhang Chaomin Shen Feifei Feng Chun Shan Jian Tang School of Software Engineering East China Normal University China School of Computer Science East China Normal University China Midea Group China School of Electronics and Information Guangdong Polytechnic Normal University China

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mining Repetitive Negative Sequential Patterns with Gap Constraints

引用

ACM Transactions on Knowledge Discovery from Data 2025年第4期19卷

作者： Li, Yan Wang, Zhulin Liu, Jing Guo, Lei Fournier-Viger, Philippe Wu, Youxi Wu, Xindong School of Economics and Management Hebei University of Technology Tianjin China School of Artificial Intelligence Hebei University of Technology Tianjin China State Key Laboratory of Reliability and Intelligence of Electrical Equipment Hebei University of Technology Tianjin China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Hebei Key Laboratory of Big Data Computing Tianjin China Hefei University of Technology Hefei China

Sequential pattern mining (SPM) with gap constraints (or repetitive SPM or tandem repeat discovery in bioinformatics) can find frequent repetitive subsequences satisfying gap constraints, which are called positive sequential patterns with gap constraints (PSPGs). However, classical SPM with gap constraints cannot find the frequent missing items in the PSPGs. To tackle this issue, this article explores negative sequential patterns with gap constraints (NSPGs). We propose an efficient NSPG-Miner algorithm that can mine both frequent PSPGs and NSPGs simultaneously. To effectively reduce candidate patterns, we propose a pattern join strategy with negative patterns which can generate both positive and negative candidate patterns at the same time. To calculate the support (frequency of occurrence) of a pattern in each sequence, we explore a NegPair algorithm that employs a key-value pair array structure to deal with the gap constraints and the negative items simultaneously and can avoid redundant rescanning of the original sequence, thus improving the efficiency of the algorithm. To report the performance of NSPG-Miner, 11 competitive algorithms and 11 datasets are employed. The experimental results not only validate the effectiveness of the strategies adopted by NSPG-Miner but also verify that NSPG-Miner can discover more valuable information than the state-of-the-art algorithms. Copyright © 2025 held by the owner/author(s). Publication rights licensed to ACM.

关键词： sequential pattern mining gap constraint negative sequential pattern key-value pair

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：