检索结果-内蒙古大学图书馆

26th European Conference on artificial intelligence, ECAI 2023

作者： Ma, Leilei Sun, Dengdi Wang, Lei Zhao, Haifeng Luo, Bin School of Computer Science and Technology Anhui University China School of Artificial Intelligence Anhui University China School of Computer Science and Engineering Nanjing University of Science and Technology China Anhui Provincial Key Laboratory of Multimodal Cognitive Computing Anhui University China Institute of Artificial Intelligence Hefei Comprehensive National Science Center China

ISBN: (纸本)9781643684369

Extracting image semantics effectively and assigning corresponding labels to multiple objects or attributes for natural images is challenging due to the complex scene contents and confusing label dependencies. Recent works have focused on modeling label relationships with graph and understanding object regions using class activation maps (CAM). However, these methods ignore the complex intra- and inter-category relationships among specific semantic features, and CAM is prone to generate noisy information. To this end, we propose a novel semantic-aware dual contrastive learning framework that incorporates sample-to-sample contrastive learning (SSCL) as well as prototype-to-sample contrastive learning (PSCL). Specifically, we leverage semantic-aware representation learning to extract category-related local discriminative features and construct category prototypes. Then based on SSCL, label-level visual representations of the same category are aggregated together, and features belonging to distinct categories are separated. Meanwhile, we construct a novel PSCL module to narrow the distance between positive samples and category prototypes and push negative samples away from the corresponding category prototypes. Finally, the discriminative label-level features related to the image content are accurately captured by the joint training of the above three parts. Experiments on five challenging large-scale public datasets demonstrate that our proposed method is effective and outperforms the state-of-the-art methods. Code and supplementary materials are released on https://***/yu-gi-oh-leilei/SADCL. © 2023 The Authors.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

A Research on the Relationship between Cognitive Level and Emotion by Integrating EBCNN Model and Epistemic Network Analysis 4

A Research on the Relationship between Cognitive Level and E...

引用

4th International Conference on Educational Technology, ICET 2024

作者： Ren, Wen Ye, Junmin Yu, Shuang Yin, Xinghan Si, Kaiyan Luo, Sheng Zhao, Gang Central China Normal University School of Computer Science WuHan China Central China Normal University Faculty of Artificial Intelligence Education WuHan China Central China Normal University Hubei Key Laboratory of Digital Education Faculty of Artificial Intelligence Education WuHan China

ISBN: (纸本)9798350376944

In online collaborative learning environments, cognitive level is a key indicator for assessing the learning process, and real-time assessment of students' cognitive level is crucial for facilitating effective learning, while assessing students' cognitive level is also the basis for investigating the relationship between cognitive level and emotion. To this end, a deep learning model based on ELMo-BiLSTM-CNN (EBCNN) is proposed, aiming to realize the automatic assessment of students' cognitive level in online collaborative learning. On this basis, Epistemic Network Analysis (ENA) is used to investigate the relationship between students' cognitive level and their emotion. The results of the study show that, first, the EBCNN model can support the automatic assessment of learners' cognitive level. Second, we find that students in online collaborative learning show richer emotion at lower cognitive level. Furthermore, positive emotion is more conducive to students' cognitive level than negative emotion. © 2024 IEEE.

关键词： Collaborative learning

来源：评论

学校读者我要写书评

暂无评论

Fixed-parameter tractability of capacitated k-facility location

引用

Frontiers of computer science 2023年第6期17卷 171-173页

作者： Xiangyan KONG Zhen ZHANG School of Computer Science and Engineering Central South UniversityChangsha 410000China School of Frontier Crossover Studies Hunan University of Technology and BusinessChangsha 410205China Changsha Social Laboratory of Artificial Intelligence Changsha 410205China

1 Introduction In this paper we study the capacitated k-facility location(Capk-FL)*** instance I of the problem is specified by a set C of clients and a set F of facilities located in a metric space with distance function d,and a positive integer k,where ICI+[F|=n,each facility f eF is associated with a capacityμ(f)>0 and a facility-opening cost o(f)>0,and connecting a client c ∈ C to f incurs a client-connection cost that equals the distance from c to f.

关键词： client problem Fixed

来源：评论

学校读者我要写书评

暂无评论

Latent Diffusion-Enhanced Virtual Try-On via Optimized Pseudo-Label Generation 39

Latent Diffusion-Enhanced Virtual Try-On via Optimized Pseud...

引用

39th Annual AAAI Conference on artificial intelligence, AAAI 2025

作者： Du, Chenghu Wang, Junyin Yu, Feng Xiong, Shengwu School of Computer Science and Artificial Intelligence Wuhan University of Technology China Shanghai Artificial Intelligence Laboratory China Interdisciplinary Artificial Intelligence Research Institute Wuhan College China School of Computer Science and Artificial Intelligence Wuhan Textile University China

ISBN: (纸本)157735897X

Efficiently applying fully supervised learning to virtual try-on tasks is challenging due to the lack of paired ground truth in available training samples. Recent works have achieved virtual try-ons by employing self-supervised learning-based inpainting paradigms. However, this approach is heavily dependent on the constraints of inpainting masks. An incorrect mask can mislead the generated results, while overly large mask areas can lose essential original information, thereby hindering the synthesis of high-quality results. To address these problems, we propose a latent diffusion model-based virtual try-on network that achieves fully supervised learning using the concept of cycle consistency and knowledge distillation. Specifically, we divide our approach into pretext and downstream tasks. In the pretext task, we generate a pseudo-label (pseudo-person image) to form paired training samples, which enables the downstream task to achieve fully supervised learning. To prevent the unreliable pseudo-person image from introducing irresponsible prior knowledge, we propose a noise-covering strategy, which aims at fully optimizing the pseudo-label to eliminate the impact of the incorrect inpainting mask as much as possible. Additionally, we propose a skin refinement loss to further enhance the generation of details in the skin region. Extended experiments demonstrate that our proposed method is superior to state-of-the-art methods. © 2025, Association for the Advancement of artificial intelligence (***). All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Evolutionary analysis of adherence to the ISO 27001:2013 standard in Portugal: Regional and sectoral study 12

Evolutionary analysis of adherence to the ISO 27001:2013 sta...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Alves, Ines Teixeira, Paulo Lopes, Nuno School of Technology Polythecnic University of Cavado and Ave Barcelos Portugal Polythecnic University of Cavado and Ave. Barcelos Portugal Liacc - Artificial Intelligence and Computer Science Lab. Porto Portugal 2Ai - School of Technology Ipca Barcelos Portugal Lasi - Associate Laboratory of Intelligent Systems Guimarães Portugal

ISBN: (纸本)9798350330366

The growing threat of cybercrime and the explosion of data volume raise critical concerns about information security. Organizations must implement systems that manage, ensure the quality, integrity, and security of information. These systems should adhere to the globally recognized ISO 27001:2013 standard. Certification against this standard has become increasingly important in the business world, prompting an examination of Portugal's progress in this area. This study investigates the evolution of the number of ISO 27001:2013 certified companies in Portugal, including a regional and sectoral analysis of information security management system adoption. © 2024 IEEE.

关键词： Information management

来源：评论

学校读者我要写书评

暂无评论

Robust Motion-Guided Frame Sampler with Interpretive Evaluation for Video Action Recognition

引用

IEEE Transactions on Mobile Computing 2025年第7期24卷 6197-6208页

作者： Bai, Jing Zhang, Yuxiang Wang, Yiran Xiao, Zhu Xiong, Yong Jiao, Licheng Xidian University School of Artificial Intelligence Key Laboratory of Intelligent Perception and Image Understanding Ministry of Education Xi'an710071 China Hunan University College of Computer Science and Electronic Engineering Changsha410082 China Hunan Lianzhi Technology Co. Ltd Changsha410200 China

Due to the presence of redundancy and interference, frame sampling is a promising but challenging solution to mitigate the expensive computation of video action recognition. Although the motion prior has shown great potential for frame selection, existing motion-based strategies suffer from limitations in terms of robustness and interpretive evaluation. In this paper, we devise a robust frame sampling strategy called positive motion guided sampler (PMGSampler). It consists of two procedures, local motion capture and global motion statistics. At the local level, we propose two concepts about inter-frame motion amplitude and motion continuity, which helps to perceive the movement of subjects and identify abnormal events that may generate negative pseudo-motion information. Then, through a global analysis of the obtained local motions, the sampler becomes more sensitive to informative frames and robust to outliers. The proposed sampler can be applied to most existing models for improving recognition accuracy. We conduct extensive experiments on four widely-used benchmarks to demonstrate the superiority of our PMGSampler over other methods of the same type. In addition, to analyse how sampled frames influence action recognition, we present a visual interpretation method for video models, termed as spatio-temporal class activation map (STCAM). By introducing spatial and temporal branches, our STCAM is able to visualise the salience of spatio-temporal features. With the help of STCAM, we can further intuitively evaluate the performance of different sampling strategies. Code is available at https://***/zyx-cv/PMGSampler. © 2002-2012 IEEE.

关键词： Motion capture

来源：评论

学校读者我要写书评

暂无评论

A Multi-Objective Particle Swarm Optimization Algorithm Based on Decomposition and Multi-Selection Strategy

引用

computers, Materials & Continua 2025年第1期82卷 997-1026页

作者： Li Ma Cai Dai Xingsi Xue Cheng Peng School of Computer Science Shaanxi Normal UniversityXi’an710119China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of TechnologyFuzhou350118China Information Construction and Management Center and Institute of Artificial Intelligence and Educational New Productivity Ningxia Normal UniversityGuyuan756099China

The multi-objective particle swarm optimization algorithm(MOPSO)is widely used to solve multi-objective optimization *** the article,amulti-objective particle swarm optimization algorithmbased on decomposition and multi-selection strategy is proposed to improve the search ***,two update strategies based on decomposition are used to update the evolving population and external archive,***,a multiselection strategy is *** first strategy is for the subspace without a non-dominated *** the neighbor particles,the particle with the smallest penalty-based boundary intersection value is selected as the global optimal solution and the particle far away fromthe search particle and the global optimal solution is selected as the personal optimal solution to enhance global *** second strategy is for the subspace with a non-dominated *** the neighbor particles,two particles are randomly selected,one as the global optimal solution and the other as the personal optimal solution,to enhance local *** third strategy is for Pareto optimal front(PF)discontinuity,which is identified by the cumulative number of iterations of the subspace without non-dominated *** the subsequent iteration,a new probability distribution is used to select from the remaining subspaces to ***,an adaptive inertia weight update strategy based on the dominated degree is designed to further improve the search ***,the proposed algorithmis compared with fivemulti-objective particle swarm optimization algorithms and five multi-objective evolutionary algorithms on 22 test *** results show that the proposed algorithm has better performance.

关键词： Multi-objective optimization multi-objective particle swarm optimization decomposition multi-selection strategy

来源：评论

学校读者我要写书评

暂无评论

Understanding Resolution of Multi-Language Bugs: An Empirical Study on Apache Projects 17

Understanding Resolution of Multi-Language Bugs: An Empirica...

引用

17th ACM/IEEE International Symposium on Empirical Software Engineering and Measurement, ESEM 2023

作者： Li, Zengyang Wang, Wenshuo Wang, Sicheng Liang, Peng Mo, Ran School of Computer Science Central China Normal University Hubei Provincial Key Laboratory of Artificial Intelligence and Smart Learning Wuhan China School of Computer Science Wuhan University Wuhan China

ISBN: (纸本)9781665452236

Background: In modern software systems, more and more systems are written in multiple programming languages (PLs). There is no comprehensive investigation on the phenomenon of multi-programming-language (MPL) bugs, which resolution involves source files written in multiple PLs. Aim: This work investigated the characteristics of bug resolution in MPL software systems and explored the reasons why bug resolution involves multiple PLs. Method: We conducted an empirical study on 54 MPL projects selected from 655 Apache OSS projects, of which 66,932 bugs were analyzed. Results: (1) the percentage of MPL bugs (MPLBs) in the selected projects ranges from 0.17% to 42.26%, and the percentage of MPLBs for all projects as a whole is 10.01%;(2) 95.0% and 4.5% of all the MPLBs involve source files written in 2 and 3 PLs, respectively;(3) the change complexity resolution characteristics of MPLBs tend to be higher than those of single-programming-language bugs (SPLBs);(4) the open time for MPLBs is 19.52% to 529.57% significantly longer than SPLBs regarding 9 PL combinations;(5) the reopen rate of bugs involving the PL combination of JavaScript and Python reaches 20.66%;(6) we found 6 causes why the bug resolution involves multiple PLs and identified 5 cross-language calling mechanisms. Conclusion: MPLBs are related to increased development difficulty. © 2023 IEEE.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

Parallel Committees: High-Performance, Scalable, Secure and Fault-Tolerant Data Replication Using a Novel Sharding Technique 5

Parallel Committees: High-Performance, Scalable, Secure and ...

引用

5th International Conference on Blockchain Computing and Applications, BCCA 2023

作者： Solat, Siamak Naït-Abdesselam, Farid Université de Paris Cité France ENGIE Laboratory for Computer Science & Artificial Intelligence France University of Missouri Kansas City United States

ISBN: (纸本)9798350339239

Distributed replication systems that use consensus mechanisms to process clients' requests have major limitations and problems in scalability, throughput, and performance. Such problems are mainly due to the time and message complexity of the consensus algorithms used in such systems. Sharding has already been implemented in several blockchain-based replication systems and although it has shown remarkable potential to improve performance and scalability, yet current sharding techniques have several significant scalability and security issues. In this paper, we propose a novel sharding technique for distributed replication systems that use a consensus to process clients' requests. We modified the approach of how nodes are allocated between shards through the public key generation process. Our approach effectively reduces undesirable cross-shard transactions that are more complex and costly to process than intra-shard transactions. Also, there is no concept of Beacon chain-as a shared-ledger between shards-which imposes additional scalability limitations and security issues on the network. With our approach, a network using a classical distributed consensus algorithm can grow outstandingly in number of nodes and still remain permissionless, © 2023 IEEE.

关键词： Scalability

来源：评论

学校读者我要写书评

暂无评论

Training Graph Neural Networks on Growing Stochastic Graphs 48

Training Graph Neural Networks on Growing Stochastic Graphs

引用

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

作者： Cerviño, Juan Ruiz, Luana Ribeiro, Alejandro University of Pennsylvania Department of Electrical and Systems Engineering Philadelphia United States Mit Computer Science & Artificial Intelligence Laboratory Cambridge United States

ISBN: (纸本)9781728163277

Graph Neural Networks (GNNs) rely on graph convolutions to exploit meaningful patterns in networked data. Based on matrix multiplications, convolutions incur in high computational costs leading to scalability limitations in practice. To overcome these limitations, proposed methods rely on training GNNs in smaller number of nodes, and then transferring the GNN to larger graphs. Even though these methods are able to bound the difference between the output of the GNN with different number of nodes, they do not provide guarantees against the optimal GNN on the very large graph. In this paper, we propose to learn GNNs on very large graphs by leveraging the limit object of a sequence of growing graphs, the graphon. We propose to grow the size of the graph as we train, and we show that our proposed methodology - learning by transference - converges to a neighborhood of a first order stationary point on the graphon data. A numerical experiment validates our proposed approach. © 2023 IEEE.

关键词： Graph Neural Networks Graphons

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：