检索结果-内蒙古大学图书馆

IEEE Transactions on Knowledge and data Engineering 2024年第07期37卷 3933-3946页

作者： Liu, Xinyuan Zhu, Jihua Yue, Kun Zheng, Qinghai Li, Zhongyu Tian, Zhiqiang Zhu, Mingchen Xi'an Jiaotong University School of Software Engineering Xi'an China Yunnan University School of Information Science and Engineering Kunming China Fuzhou University College of Computer and Data Science Fuzhou China

Label enhancement (LE) is still a challenging task to mitigate the dilemma of the lack of label distribution. Existing LE work typically focuses on primarily formulating a projection between feature space and label distribution space from discriminative model perspective, which preserves the relevance consistency that the sign of recovered label distribution should be consistent with the logical label. Different from previous algorithms, we formulate this problem from a causal perspective and present a novel LE method via the structured causal model (LESCM). Specifically, the proposed LESCM deliberates establishing the causal graph with assuming that label distribution is a cause of feature and logical label, which naturally satisfies the definition of label distribution learning (LDL). With capturing the underlying causal relationships, we can significantly boost the interpretability and identifiability of label enhancement. Meanwhile, except for the relevance consistency, LESCM are encouraged to sustain the order consistency that assigns higher description degree of the recovered label distribution to the positive labels, as compared with the negative labels. Empirically, sufficient experiments on several label distribution learning data sets validate the effectiveness of LESCM. © 1989-2012 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Learning a Mixture of Conditional Gating Blocks for Visual Question Answering

引用

Journal of computer science & Technology 2024年第4期39卷 912-928页

作者： Qiang Sun Yan-Wei Fu Xiang-Yang Xue School of Statistics and Information Shanghai University of International Business and EconomicsShanghai 201620China Academy for Engineering and Technology Fudan UniversityShanghai 200433China School of Data Science Fudan UniversityShanghai 200433China School of Computer Science Fudan UniversityShanghai 200433China

As a Turing test in multimedia,visual question answering(VQA)aims to answer the textual question with a given ***,the“dynamic”property of neural networks has been explored as one of the most promising ways of improving the adaptability,interpretability,and capacity of the neural network ***,despite the prevalence of dynamic convolutional neural networks,it is relatively less touched and very nontrivial to exploit dynamics in the transformers of the VQA tasks through all the stages in an end-to-end ***,due to the large computation cost of transformers,researchers are inclined to only apply transformers on the extracted high-level visual features for downstream vision and language *** this end,we introduce a question-guided dynamic layer to the transformer as it can effectively increase the model capacity and require fewer transformer layers for the VQA *** particular,we name the dynamics in the Transformer as Conditional Multi-Head Self-Attention block(cMHSA).Furthermore,our questionguided cMHSA is compatible with conditional ResNeXt block(cResNeXt).Thus a novel model mixture of conditional gating blocks(McG)is proposed for VQA,which keeps the best of the Transformer,convolutional neural network(CNN),and dynamic *** pure conditional gating CNN model and the conditional gating Transformer model can be viewed as special examples of *** quantitatively and qualitatively evaluate McG on the CLEVR and VQA-Abstract *** experiments show that McG has achieved the state-of-the-art performance on these benchmark datasets.

关键词： visual question answering Transformer dynamic network

来源：评论

学校读者我要写书评

暂无评论

Immersive video interaction system: a survey

引用

Visual Intelligence 2025年第1期3卷 1-14页

作者： Fang, Xiaohan Chen, Peilin Wang, Meng Wang, Shiqi Department of Computer Science City University of Hong Kong Hong Kong School of Data Science Lingnan University Hong Kong

As communication technologies undergo rapid evolution, human interaction technologies have become increasingly efficient and accessible. Videoconferencing, for example, facilitates real-time, face-to-face communication worldwide, providing unprecedented convenience. Nevertheless, traditional two-dimensional (2D) videoconferencing systems frequently fall short of delivering a fully immersive experience, as they lack the ability to convey physical presence, depth perception, and natural interaction—key elements that are of particular significance in replicating the subtleties inherent in in-person communication. This disconnection leaves users yearning for the rich, multi-sensory experiences that real-life interactions can offer. In response, significant research efforts have been dedicated to the development of immersive video interaction systems (IVISs). This paper introduces the concept of IVISs and reviews a spectrum of systems advanced by researchers and industry innovators, each of whom contributes unique insights into the evolution of this field. A comparative analysis of the characteristics of current IVISs is provided, offering insights across multiple dimensions. This survey concludes with a discussion of potential future research directions and the challenges that remain in enhancing the IVIS technology. Through a comprehensive analysis, this work aims to foster further exploration and innovation in immersive communication technologies. © The Author(s) 2025.

关键词： 3D vision Immersive video interaction systems Survey Video communication

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Educational Fund Management and Operational Cost Efficiency: Analyzing U.S. Public schools data

Evaluation of Educational Fund Management and Operational Co...

引用

2024 International Conference on Artificial Intelligence and Mechatronics System, AIMS 2024

作者： Eleeas, Kevina Nugraha Muljana, Richie Ayuningtyas, Lintang Diah Gunawan, Alexander Agung Santoso Setiawan, Karli Eka School of Computer Science Bina Nusantara University Jakarta Data Science Program 11480 Indonesia School of Computer Science Bina Nusantara University Jakarta Computer Science Department 11480 Indonesia

ISBN: (纸本)9798350350524

This study investigates the challenges and opportunities of managing educational funds and controlling operational costs in two educational systems. It examines how factors such as school infrastructure, technology integration, teacher professional development, and parental involvement influence educational funding and quality. This study also explores the importance of equitable and efficient fund allocation, especially for remote schools that face resource constraints and development gaps. To analyze the financial trends of educational fund management, this study applies three machine learning models: decision trees, random forests, and support vector machines. The results show that the random forest model has the highest overall accuracy (90%) and the decision tree model has perfect accuracy in classifying institutions based on local income. This study identifies the most relevant features and demonstrates the effectiveness of the models in categorizing institutions and evaluating the fund management performance in the education sector. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

A blockchain-empowered authentication scheme for worm detection in wireless sensor network

引用

Digital Communications and Networks 2024年第2期10卷 265-272页

作者： Yuling Chen Xiong Yang Tao Li Yi Ren Yangyang Long State Key Laboratory of Public Big Data College of Computer Science and TechnologyGuizhou UniversityGuiyang550025China School of Computing Science University of East AngliaNorwichNR57TJUK

Wireless Sensor Network(WSN)is a distributed sensor network composed a large number of nodes with low cost,low performance and *** special structure of WSN brings both convenience and *** example,a malicious participant can launch attacks by capturing a physical ***,node authentication that can resist malicious attacks is very important to network ***,blockchain technology has shown the potential to enhance the security of the Internet of Things(IoT).In this paper,we propose a Blockchain-empowered Authentication Scheme(BAS)for *** our scheme,all nodes are managed by utilizing the identity information stored on the ***,the simulation experiment about worm detection is executed on BAS,and the security is evaluated from detection and infection *** experiment results indicate that the proposed scheme can effectively inhibit the spread and infection of worms in the network.

关键词： Wireless Sensor Network(WSN) Node authentication Blockchain Tangle Worm detection

来源：评论

学校读者我要写书评

暂无评论

CONTESTS: a Framework for Consistency Testing of Span Probabilities in Language Models

CONTESTS: a Framework for Consistency Testing of Span Probab...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Wagner, Eitan Slavutsky, Yuli Abend, Omri School of Computer Science and Engineering Department of Statistics and Data Science Hebrew University of Jerusalem Israel

ISBN: (纸本)9798891761643

Although language model scores are often treated as probabilities, their reliability as probability estimators has mainly been studied through calibration, overlooking other aspects. In particular, it is unclear whether language models produce the same value for different ways of assigning joint probabilities to word spans. Our work introduces a novel framework, ConTestS (Consistency Testing over Spans), involving statistical tests to assess score consistency across interchangeable completion and conditioning orders. We conduct experiments on post-release real and synthetic data to eliminate training effects. Our findings reveal that both Masked Language Models (MLMs) and autoregressive models exhibit inconsistent predictions, with autoregressive models showing larger discrepancies. Larger MLMs tend to produce more consistent predictions, while autoregressive models show the opposite trend. Moreover, for both model types, prediction entropies offer insights into the true word span likelihood and therefore can aid in selecting optimal decoding strategies. The inconsistencies revealed by our analysis, as well their connection to prediction entropies and differences between model types, can serve as useful guides for future research on addressing these limitations. © 2024 Association for Computational Linguistics.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Efficient Evaluation Methods for Neural Architecture Search: A Survey

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第12期5卷 5990-6011页

作者： Song, Xiaotian Xie, Xiangning Lv, Zeqiong Yen, Gary G. Ding, Weiping Lv, Jiancheng Sun, Yanan Sichuan University College of Computer Science Chengdu610065 China Oklahoma State University School of Electrical and Computer Engineering StillwaterOK74078 United States Nantong University School of Artificial Intelligence and Computer Science Nantong226019 China City University of Macau Faculty of Data Science 999078 China

Neural architecture search (NAS) has received increasing attention because of its exceptional merits in automating the design of deep neural network (DNN) architectures. However, the performance evaluation process, as a key part of NAS, often requires training a large number of DNNs. This inevitably makes NAS computationally expensive. In past years, many efficient evaluation methods (EEMs) have been proposed to address this critical issue. In this article, we comprehensively survey these EEMs published up to date, and provide a detailed analysis to motivate the further development of this research direction. Specifically, we divide the existing EEMs into four categories based on the number of DNNs trained for constructing these EEMs. The categorization can reflect the degree of efficiency in principle, which can in turn help quickly grasp the methodological features. In surveying each category, we further discuss the design principles and analyze the strengths and weaknesses to clarify the landscape of existing EEMs, thus making easily understanding the research trends of EEMs. Furthermore, we also discuss the current challenges and issues to identify future research directions in this emerging topic. In summary, this survey provides a convenient overview of EEM for interested users, and they can easily select the proper EEM method for the tasks at hand. In addition, the researchers in the NAS field could continue exploring the future directions suggested in the article. © 2020 IEEE.

关键词： Network architecture

来源：评论

学校读者我要写书评

暂无评论

Identifying Affected Libraries and Their Ecosystems for Open Source Software Vulnerabilities 24

Identifying Affected Libraries and Their Ecosystems for Open...

引用

44th ACM/IEEE International Conference on Software Engineering, ICSE 2024

作者： Wu, Susheng Song, Wenyan Huang, Kaifeng Chen, Bihuan Peng, Xin School of Computer Science Shanghai Key Laboratory of Data Science Fudan University Shanghai China

ISBN: (纸本)9798400702174

Software composition analysis (SCA) tools have been widely adopted to identify vulnerable libraries used in software applications. Such SCA tools depend on a vulnerability database to know affected libraries of each vulnerability. However, it is labor-intensive and error prone for a security team to manually maintain the vulnerability database. While several approaches adopt extreme multi-label learning to predict affected libraries for vulnerabilities, they are practically ineffective due to the limited library labels and the unawareness of ecosystems. To address these problems, we first conduct an empirical study to assess the quality of two fields, i.e., affected libraries and their ecosystems, for four vulnerability databases. Our study reveals notable inconsistency and inaccuracy in these two fields. Then, we propose HOLMES to identify affected libraries and their ecosystems for vulnerabilities via a learning-to-rank technique. The key idea of HOLMES is to gather various evidences about affected libraries and their ecosystems from multiple sources, and learn to rank a pool of libraries based on their relevance to evidences. Our extensive experiments have shown the effectiveness, efficiency and usefulness of HOLMES © 2024 ACM.

关键词： Open source software

来源：评论

学校读者我要写书评

暂无评论

High-precision Online Log Parsing with Large Language Models 24

High-precision Online Log Parsing with Large Language Models

引用

46th International Conference on Software Engineering: Companion, ICSE-Companion 2024

作者： Chen, Xiaolei Shi, Jie Chen, Jia Wang, Peng Wang, Wei Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400705021

System logs are vital for diagnosing system failures, with log parsing converting unstructured logs into structured data. Existing methods fall into two categories: non-deep-learning approaches cluster logs based on stats but often miss semantic information, resulting in poor performance. Deep-learning approaches excel at identifying variables and constants but often lack generalizability beyond training data. And they always suffer from low efficiency. This paper proposes a novel LLM-based log parsing approach, named Hooglle, to address these challenges. Leveraging a large language model, Hooglle extracts templates for precise and generalized parsing. To overcome the efficiency issue, we propose a prefix-tree-based full-matching strategy which significantly improves parsing efficiency. Extensive evaluation across real-world datasets showcases Hooglle's superior performance on 16 public benchmark datasets. © 2024 IEEE computer Society. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Linking Adaptive Structure Induction and Neuron Filtering: A Spectral Perspective for Aspect-based Sentiment Analysis 30

Linking Adaptive Structure Induction and Neuron Filtering: A...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Niu, Hao Wang, Maoyi Xiong, Yun Yang, Biao Jia, Xing Guo, Zhonglei Shanghai Key Laboratory of Data Science School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9782493814104

Recently, it has been discovered that incorporating structure information (e.g., dependency trees) can improve the performance of aspect-based sentiment analysis (ABSA). The structure information is often obtained from off-the-shelf parsers, which are sub-optimal and unwieldy. Therefore, adaptively inducing task-specific structures is helpful in resolving this issue. In this work, we concentrate on adaptive graph structure induction for ABSA and explore the impact of neuron-level manipulation from a spectral perspective on structure induction. Specifically, we consider word representations from PLMs (pre-trained language models) as node features and employ a graph learning module to adaptively generate adjacency matrices, followed by graph neural networks (GNNs) to capture both node features and structural information. Meanwhile, we propose the Neuron Filtering (NeuLT), a method to conduct neuron-level manipulations on word representations in the frequency domain. We conduct extensive experiments on three public datasets to observe the impact of NeuLT on structure induction and ABSA. The results and further analysis demonstrate that performing neuron-level manipulation through NeuLT can shorten Aspects-sentiment Distance of induced structures and be beneficial to improve the performance of ABSA. The effects of our method can achieve or come close to SOTA (state-of-the-art) performance. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Neurons

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：