检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kennington, Casey Lison, Pierre Schlangen, David DEPARTMENT OF COMPUTER SCIENCE BOISE STATE UNIVERSITY United States NORWEGIAN COMPUTING CENTER Norway COMPUTATIONAL LINGUISTICS UNIVERSITY OF POTSDAM Germany

Efforts towards endowing robots with the ability to speak have benefited from recent advancements in natural language processing, in particular large language models. However, current language models are not fully incremental, as their processing is inherently monotonic and thus lack the ability to revise their interpretations or output in light of newer observations. This monotonicity has important implications for the development of dialogue systems for human–robot interaction. In this paper, we review the literature on interactive systems that operate incrementally (i.e., at the word level or below it). We motivate the need for incremental systems, survey incremental modeling of important aspects of dialogue like speech recognition and language generation. Primary focus is on the part of the system that makes decisions, known as the dialogue manager. We find that there is very little research on incremental dialogue management, offer some requirements for practical incremental dialogue management, and the implications of incremental dialogue for embodied, robotic platforms in the age of large language models. © 2025, CC BY.

关键词： Social robots

来源：评论

学校读者我要写书评

暂无评论

Optimizing Distributed Denial of Service (DDoS) Attack Detection Techniques on Software Defined Network (SDN) Using Feature Selection 4

Optimizing Distributed Denial of Service (DDoS) Attack Detec...

引用

4th International Conference on Innovations in computer science, ICONICS 2024

作者： Haq, Inamul Khan, Salman A. Mohammad, Nazeeruddin Zaman, Ali College of Computing and Info. Sciences Karachi Institute of Economics and Technology Karachi Pakistan Cyber Security Center Prince Mohammad Bin Fahd University Al-Khobar Saudi Arabia Shaheed Zulfiqar Ali Bhutto University Computer Science Department Karachi Pakistan

ISBN: (纸本)9798331504342

Distributed denial of service (DDoS) attacks refer to a category of cyber attacks in which an attacker attempts to overwhelm a resource, such as a server, destination, or bandwidth through various means. This is usually done by either flooding the traffic or sending a heavy crunching job to exhaust the CPU or heavy amounts of data to pileup the storage. By the rise of virtualization and cloud technologies, networks have also evolved from hardware to a piece of software which virtualizes the operation of a network equipment. This virtualization is termed as a Software Defined Network (SDN). Due to the sheer impact of cyberattacks on the performance of networks, the study of DDoS attacks on SDN is vital in the present era. Contemporary approaches such as machine learning and deep learning have proven to be effective in attack detection of DDoS in SDNs. In this paper, a preliminary analysis is carried out to study the impact of feature selection to increase the throughput and response time of Machine learning techniques in detection of DDoS attacks on SDN. The results indicate that feature selection, when applied to machine learning algorithms, is an effective approach for DDoS attack detection in SDNs. © 2024 IEEE.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Modeling Language for Scenario Development of Autonomous Driving Systems

Modeling Language for Scenario Development of Autonomous Dri...

引用

FME Workshop on Formal Methods in Software Engineering (FormaliSE)

作者： Toshiaki Aoki Takashi Tomita Tatsuji Kawai Daisuke Kawakami Nobuo Chida Graduate School of Advanced Science and Technology JAIST Research Center for Advanced Computing Infrastructure JAIST Department of Computer Science Kochi University Mitsubishi Electric Corporation

ISBN: (数字)9798331537944

ISBN: (纸本)9798331501761

Autonomous driving systems are typically verified based on scenarios. To represent the positions and movements of cars in these scenarios, diagrams that utilize icons are typically employed. However, the interpretation of such diagrams is typically ambiguous, which can lead to misunderstandings among users, making them unsuitable for the development of highreliability systems. To address this issue, this study introduces a notation called the car position diagram (CPD). The CPD allows for the concise representation of numerous scenarios and is particularly suitable for scenario analysis and design. In addition, we propose a method for converting CPD-based models into propositional logic formulas and enumerating all scenarios using a SAT solver. A tool for scenario enumeration is implemented, and experiments are conducted on both typical car behaviors and international standards. The results demonstrate that the CPD enables the concise description of numerous scenarios, thereby confirming the effectiveness of our scenario analysis method.

关键词： visualization Reviews Network topology Roads Safety Automobiles Logic Autonomous vehicles Standards Software engineering

来源：评论

学校读者我要写书评

暂无评论

On the Effects of Self-supervision and Contrastive Alignment in Deep Multi-view Clustering

On the Effects of Self-supervision and Contrastive Alignment...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Daniel J. Trosten Sigurd Løkse Robert Jenssen Michael C. Kampffmeyer Department of Physics and Technology UiT The Arctic University of Norway UiT Machine Learning group Visual Intelligence Centre Norwegian Computing Center Department of Computer Science University of Copenhagen Pioneer Centre for AI

Self-supervised learning is a central component in recent approaches to deep multi-view clustering (MVC). However, we find large variations in the development of self-supervision-based methods for deep MVC, potentially slowing the progress of the field. To address this, we present Deep-MVC, a unified framework for deep MVC that includes many recent methods as instances. We leverage our framework to make key observations about the effect of self-supervision, and in particular, drawbacks of aligning representations with contrastive learning. Further, we prove that contrastive alignment can negatively influence cluster separability, and that this effect becomes worse when the number of views increases. Motivated by our findings, we develop several new DeepMVC instances with new forms of self-supervision. We conduct extensive experiments and find that (i) in line with our theoretical findings, contrastive alignments decreases performance on datasets with many views; (ii) all methods benefit from some form of self-supervision; and (iii) our new instances outperform previous methods on several datasets. Based on our results, we suggest several promising directions for future research. To enhance the openness of the field, we provide an open-source implementation of DeepMVC, including recent models and our new instances. Our implementation includes a consistent evaluation protocol, facilitating fair and accurate evaluation of methods and components 1 1 Code: https://***/DanielTrosten/DeepMVC.

关键词：

来源：评论

学校读者我要写书评

暂无评论

TPS++: Attention-Enhanced Thin-Plate Spline for Scene Text Recognition

arXiv

引用

arXiv 2023年

作者： Zheng, Tianlun Chen, Zhineng Bai, Jinfeng Xie, Hongtao Jiang, Yu-Gang Shanghai Collaborative Innovation Center of Intelligent Visual Computing School of Computer Science Fudan University China Tomorrow Advance Life China University of Science and Technology of China China

Text irregularities pose significant challenges to scene text recognizers. Thin-Plate Spline (TPS)based rectification is widely regarded as an effective means to deal with them. Currently, the calculation of TPS transformation parameters purely depends on the quality of regressed text borders. It ignores the text content and often leads to unsatisfactory rectified results for severely distorted text. In this work, we introduce TPS++, an attention-enhanced TPS transformation that incorporates the attention mechanism to text rectification for the first time. TPS++ formulates the parameter calculation as a joint process of foreground control point regression and content-based attention score estimation, which is computed by a dedicated designed gated-attention block. TPS++ builds a more flexible content-aware rectifier, generating a natural text correction that is easier to read by the subsequent recognizer. Moreover, TPS++ shares the feature backbone with the recognizer in part and implements the rectification at feature-level rather than image-level, incurring only a small overhead in terms of parameters and inference time. Experiments on public benchmarks show that TPS++ consistently improves the recognition and achieves state-of-the-art accuracy. Meanwhile, it generalizes well on different backbones and recognizers. Code is at https://***/simplify23/TPS PP. Copyright © 2023, The Authors. All rights reserved.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Learning to Rank Patches for Unbiased Image Redundancy Reduction

arXiv

引用

arXiv 2024年

作者： Luo, Yang Chen, Zhineng Zhou, Peng Wu, Zuxuan Gao, Xieping Jiang, Yu-Gang School of Computer Science Shanghai Collaborative Innovation Center of Intelligent Visual Computing Fudan University China University of Maryland College Park United States College of Information Science and Engineering Hunan Normal University China

Images suffer from heavy spatial redundancy because pixels in neighboring regions are spatially correlated. Existing approaches strive to overcome this limitation by reducing less meaningful image regions. However, current leading methods rely on supervisory signals. They may compel models to preserve content that aligns with labeled categories and discard content belonging to unlabeled categories. This categorical inductive bias makes these methods less effective in real-world scenarios. To address this issue, we propose a self-supervised framework for image redundancy reduction called Learning to Rank Patches (LTRP). We observe that image reconstruction of masked image modeling models is sensitive to the removal of visible patches when the masking ratio is high (e.g., 90%). Building upon it, we implement LTRP via two steps: inferring the semantic density score of each patch by quantifying variation between reconstructions with and without this patch, and learning to rank the patches with the pseudo score. The entire process is self-supervised, thus getting out of the dilemma of categorical inductive bias. We design extensive experiments on different datasets and tasks. The results demonstrate that LTRP outperforms both supervised and other self-supervised methods due to the fair assessment of image content. Code is available at https://***/irsLu/ltrp. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

An Iterative Optimizing Framework for Radiology Report Summarization With ChatGPT

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第8期5卷 4163-4175页

作者： Ma, Chong Wu, Zihao Wang, Jiaqi Xu, Shaochen Wei, Yaonai Liu, Zhengliang Zeng, Fang Jiang, Xi Guo, Lei Cai, Xiaoyan Zhang, Shu Zhang, Tuo Zhu, Dajiang Shen, Dinggang Liu, Tianming Li, Xiang Northwestern Polytechnical University School of Automation Xi'an710072 China University of Georgia School of Computing AthensGA30602 United States Northwestern Polytechnical University School of Computer Science Xi'an710072 China Massachusetts General Hospital Department of Radiology BostonMA02114 United States University of Electronic Science and Technology of China Clinical Hospital of Chengdu Brain Science Institute MOE Key Lab for Neuroinformation School of Life Science and Technology Chengdu611731 China The University of Texas at Arlington Department of Computer Science and Engineering ArlingtonVA76019 United States ShanghaiTech University School of Biomedical Engineering Shanghai201210 China Shanghai United Imaging Intelligence Company Ltd. Department of Research and Development Shanghai200030 China Shanghai Clinical Research and Trial Center Shanghai201210 China

The 'Impression' section of a radiology report is a critical basis for communication between radiologists and other physicians. Typically written by radiologists, this part is derived from the 'Findings' section, which can be laborious and error-prone. Although deep-learning-based models, such as bidirectional encoder representation from transformers (BERT), have achieved promising results in automatic impression generation (AIG), such models often require substantial amounts of medical data and have poor generalization performance. Recently, large language models (LLMs) like Chat Generative Pre-trained Transformer (ChatGPT) have shown strong generalization capabilities and performance, but their performance in specific domains, such as radiology, remains under-investigated and potentially limited. To address this limitation, we propose ImpressionGPT, leveraging the contextual learning capabilities of LLMs through our dynamic prompt and iterative optimization algorithm to accomplish the AIG task. ImpressionGPT initially employs a small amount of domain-specific data to create a dynamic prompt, extracting contextual semantic information closely related to the test data. Subsequently, the iterative optimization algorithm automatically evaluates the output of LLMs and provides optimization suggestions, continuously refining the output results. The proposed ImpressionGPT model achieves superior performance of AIG task on both the Medical Information Mart for Intensive Care - Chest X-ray database (MIMIC-CXR) and Open Access Biomedical Image Search Engine (OpenI) datasets without requiring additional training data or fine-tuning the LLMs. This work presents a paradigm for localizing LLMs that can be applied in a wide range of similar application scenarios, bridging the gap between general-purpose LLMs and the specific language processing needs of various domains. © 2020 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Enhanced prairie dog optimization with Levy flight and dynamic opposition-based learning for global optimization and engineering design problems

引用

Neural computing and Applications 2024年第19期36卷 11137-11170页

作者： Biswas, Saptadeep Shaikh, Azharuddin Ezugwu, Absalom El-Shamir Greeff, Japie Mirjalili, Seyedali Bera, Uttam Kumar Abualigah, Laith Department of Mathematics National Institute of Technology Agartala Tripura Agartala India Unit for Data Science and Computing North-West University 11 Hoffman Street Potchefstroom2520 South Africa Faculty of Natural and Agricultural Sciences School of Computer Science and Information Systems North-West University Vanderbijlpark South Africa Centre for Artificial Intelligence Research and Optimization Torrens University Australia Fortitude Valley BrisbaneQLD4006 Australia Research Center University of Tabuk Tabuk71491 Saudi Arabia Computer Science Department Al al-Bayt University Mafraq25113 Jordan Hourani Center for Applied Scientific Research Al-Ahliyya Amman University Amman19328 Jordan Applied Science Research Center Applied Science Private University Amman11931 Jordan Department of Electrical and Computer Engineering Lebanese American University Byblos13-5053 Lebanon School of Engineering and Technology Sunway University Malaysia Petaling Jaya27500 Malaysia College of Engineering Yuan Ze University Taoyuan32003 Taiwan MEU Research Unit Middle East University Amman11831 Jordan

This study proposes a new prairie dog optimization algorithm version called EPDO. This new version aims to address the issues of premature convergence and slow convergence that were observed in the original PDO algorithm. To improve performance, several modifications are introduced in EPDO. First, a dynamic opposite learning strategy is employed to increase the diversity of the population and prevent premature convergence. This strategy helps the algorithm avoid falling into local optima and promotes global optimization. Additionally, the Lévy dynamic random walk technique is utilized in EPDO. This modified Lévy flight with random walk reduces the algorithm’s running time for the test function’s ideal value, accelerating its convergence. The proposed approach is evaluated using 33 benchmark problems from CEC 2017 and compared against seven other comparative techniques: GWO, MFO, ALO, WOA, DA, SCA, and RSA. Numerical results demonstrate that EPDO produces good outcomes and performs well in solving benchmark problems. To further validate the results and assess reliability, the authors employ average rank tests, the measurement of alternatives, and ranking according to the compromise solution (MARCOS) method, as well as a convergence report of EPDO and other algorithms. Furthermore, the effectiveness of the EPDO algorithm is demonstrated by applying it to five design problems. The results indicate that EPDO achieves impressive outcomes and proves its capability to address practical issues. The algorithm performs well in solving benchmark and practical design problems, as supported by the numerical results and validation methods used in the study. © The Author(s) 2024.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

Learning Photometric Feature Transform for Free-Form Object Scan

引用

IEEE Transactions on visualization and computer Graphics 2024年 PP卷 PP页

作者： Feng, Xiang Kang, Kaizhang Pei, Fan Ding, Huakeng You, Jinjiang Tan, Ping Zhou, Kun Wu, Hongzhi Zhejiang University State Key Lab of CAD & CG Hangzhou310058 China King Abdullah University of Science and Technology Visual Computing Center Thuwal23955-6900 Saudi Arabia The Hong Kong University of Science and Technology Department of Electronic and Computer Engineering SAR Hong Kong Hong Kong

We propose a novel framework to automatically learn to aggregate and transform photometric measurements from multiple unstructured views into spatially distinctive and view-invariant low-level features, which are subsequently fed to a multi-view stereo pipeline to enhance 3D reconstruction. The illumination conditions during acquisition and the feature transform are jointly trained on a large amount of synthetic data. We further build a system to reconstruct both the geometry and anisotropic reflectance of a variety of challenging objects from hand-held scans. The effectiveness of the system is demonstrated with a lightweight prototype, consisting of a camera and an array of LEDs, as well as an off-the-shelf tablet. Our results are validated against reconstructions from a professional 3D scanner and photographs, and compare favorably with state-of-the-art techniques. © 1995-2012 IEEE.

关键词： Photometry

来源：评论

学校读者我要写书评

暂无评论

SDN control plane security: Attacks and mitigation techniques 2021

SDN control plane security: Attacks and mitigation technique...

引用

4th International Conference on Networking, Information Systems and Security, NISS 2021

作者： Fatima, Kiran Zahoor, Kanwal Bawany, Narmeen Zakaria Center for Computing Research Department of Computer Science and Software Engineering Jinnah University for Women

ISBN: (纸本)9781450388719

Traditional networks are complex and hard to manage due to many reasons such as manual configuration requirements of dedicated devices, lack of flexibility and a non-dynamic approach. To overcome these limitations and to meet the challenges of modern networks a new networking paradigm Software Defined Networking (SDN) has been introduced. SDN presents a centralized and completely dynamic environment which provides flexibility and programmability in networks. It enables the network to be controlled centrally and intelligently using multiple software applications. SDN being in its infancy, brings along new challenges. Standardization of various interfaces, scalability, compatibility of contrasting or divergent networks, and vulnerability issues are few of them. This paper discusses various vulnerabilities and possible attacks on every layer of an SDN and focuses on control plane attacks. Further, it presents a comprehensive survey on numerous attacks on the brain of an SDN i.e. the control plane along with existing solutions. The study concludes that despite the challenges that are worth debating, SDN has many characteristics that make it an ideal candidate for future networks. © 2021 ACM.

关键词： Attacks on control plane SDN security Software defined network (SDN) Vulnerabilities of SDN

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：