检索结果-内蒙古大学图书馆

TechRxiv 2021年

作者： Zhang, Zhao Wei, Yanyan Zhang, Haijun Yang, Yi Yan, Shuicheng Wang, Meng School of Computer Science and Information Engineering Hefei University of Technology Hefei230009 China Key Laboratory of Knowledge Engineering with Big Data Ministry of Education Hefei University of Technology Hefei230009 China Shenzhen China Centre for Artificial Intelligence University of Technology Sydney SydneyNSW Australia Department of Electrical and Computer Engineering National University of Singapore Singapore Hefei University of Technology China

Single Image Deraining task aims at recovering the rain-free background from an image degraded by rain streaks and rain accumulation. For the powerful fitting ability of deep neural networks and massive training data, data-driven deep SID methods obtained significant improvement over traditional ones. Current SID methods usually focus on improving the deraining performance by proposing different kinds of deraining networks, while neglecting the interpretation of the solving process. As a result, the generalization ability may still be limited in real-world scenarios, and the deraining results also cannot effectively improve the performance of subsequent high-level tasks (e.g., object detection). To explore these issues, we in this paper re-examine the three important factors (i.e., data, rain model and network architecture) for the SID problem, and specifically analyze them by proposing new and more reasonable criteria (i.e., general vs. specific, synthetical vs. mathematical, black-box vs. white-box). We also study the relationship of the three factors from a new perspective of data, and reveal two different solving paradigms (explicit vs. implicit) for the SID task. We further discuss the current mainstream data-driven SID methods from five aspects, i.e., training strategy, network pipeline, domain knowledge, data preprocessing, and objective function, and some useful conclusions are summarized by statistics. Besides, we profoundly studied one of the three factors, i.e., data, and measured the performance of current methods on different datasets through extensive experiments to reveal the effectiveness of SID data. Finally, with the comprehensive review and in-depth analysis, we draw some valuable conclusions and suggestions for future research. © 2021, CC BY.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Queer in HCI: Strengthening the Community of LGBTQIA+ Researchers and Research

Queer in HCI: Strengthening the Community of LGBTQIA+ Resear...

引用

2021 CHI Conference on Human Factors in Computing Systems: Making Waves, Combining Strengths, CHI EA 2021

作者： Devito, Michael Ann Lustig, Caitlin Simpson, Ellen Allison, Kimberley Chuanromanee, Tya Spiel, Katta Ko, Amy Rode, Jennifer Dym, Brianna Muller, Michael Klaus Scheuerman, Morgan Marie Walker, Ashley Brubaker, Jed Ahmed, Alex Department of Information Science University of Colorado United States Human Centered Design and Engineering University of Washington United States School of Information Studies Syracuse University United States Department of Psychology Macquarie University Australia University of Notre Dame United States Human-Computer Interaction Group Tu Wien Austria The Information School University of Washington United States Knowledge Lab University College London United Kingdom Department of Information Science University of Colorado Boulder United States Ai Interactions Ibm Research United States Information Science University of Colorado Boulder United States Pitch Lab Northwestern University United States University of Colorado Boulder United States Carnegie Mellon University United States

ISBN: (纸本)9781450380959

As Queer Human-computer Interaction (HCI) becomes an established part of the larger field, both in terms of research on and with queer populations and in terms of employing queering theories and methods, the role of queer researchers has become a timely topic of discussion. However, these discussions have largely centered around member-researcher status and positionality when working with queer populations. Based on insights gathered at multiple ACM events over the past two years, we identified two pressing issues: (1) we need to better support queer people doing HCI research not specific to queer populations, and (2) we need to identify how to best support member-researchers in leading Queer HCI while including collaborators beyond the queer community. This Special Interest Group (SIG) aims to directly address these challenges by convening a broad community of queer researchers and allies, working not only on explicitly-queer topics but across a broad range of HCI topics. © 2021 Owner/Author.

关键词： Computation theory

来源：评论

学校读者我要写书评

暂无评论

On multi-objective minimum spanning tree under the framework of uncertainty theory

引用

AIP Conference Proceedings 2023年第1期2851卷

作者： Swapna Halder Saibal Majumder Arindam Biswas Bijoy Kumar Mandal Sheng-Lung Peng Department of Computer Science and Engineering St. Thomas College of Engineering & Technology Kolkata West Bengal India Centre for IOT and AI Integration with Education -Industry-Agriculture Kazi Nazrul University Asansol West Bengal India Department of Computer Science and Engineering (Data Science) Dr. B. C. Roy Engineering College Durgapur West Bengal India School of Mines and Metallurgy Kazi Nazrul University Asansol West Bengal India Department of Computer Science and Engineering NSHM Knowledge Campus Durgapur West Bengal India Department of Creative Technologies and Product Design National Taipei University of Business Taoyuan Taiwan

Aminimum spanning tree with multiple objectives is one type of NP hard problem, and it has a wide application area in ourdaily life. Modelling real world problems, requires many associated parameters which are not well-defined and are indeterminate in nature. Thus, it is rational to consider these indeterminate parameters while modelling real life problems. This article, investigates onthe study of minimum spanning tree with multiple objectives which are uncertain in nature. The proposed multiple objectives minimum spanning tree has two uncertain parameters associated with it, they are time and cost. Both of these parameters are indeterminate in nature and characterizedas uncertain variables. The expected value model (EVM) of multiple objectives minimum spanning tree is formulatedin this study and convex combination method is used to solve this problem. Finally to achieve the nondominated solutions of this problem, we have solved the EVM by varying the related weights of its objectives.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Curvature regularization to prevent distortion in graph embedding

arXiv

引用

arXiv 2020年

作者： Pei, Hongbin Wei, Bingzhe Zhang, Chunxu Chang, Kevin Chen-Chuan Yang, Bo College of Computer Science and Technology Jilin University China Department of Electrical and Computer Engineering University of Illinois at Urbana-Champaign United States Department of Computer Science University of Illinois at Urbana-Champaign United States Key Laboratory of Symbolic Computation Knowledge Engineering of Ministry of Education China

Recent research on graph embedding has achieved success in various applications. Most graph embedding methods preserve the proximity in a graph into a manifold in an embedding space. We argue an important but neglected problem about this proximity-preserving strategy: Graph topology patterns, while preserved well into an embedding manifold by preserving proximity, may distort in the ambient embedding Euclidean space, and hence to detect them becomes difficult for machine learning models. To address the problem, we propose curvature regularization, to enforce flatness for embedding manifolds, thereby preventing the distortion. We present a novel angle-based sectional curvature, termed ABS curvature, and accordingly three kinds of curvature regularization to induce flat embedding manifolds during graph embedding. We integrate curvature regularization into five popular proximity-preserving embedding methods, and empirical results in two applications show significant improvements on a wide range of open graph datasets. Copyright © 2020, The Authors. All rights reserved.

关键词： Topology

来源：评论

学校读者我要写书评

暂无评论

ARCH-COMP20 category report: Continuous and hybrid systems with nonlinear dynamics 7th

ARCH-COMP20 category report: Continuous and hybrid systems w...

引用

7th International Workshop on Applied Verification of Continuous and Hybrid Systems, ARCH 2020

作者： Geretti, Luca Dit Sandretto, Julien Alexandre Althoff, Matthias Benet, Luis Chapoutot, Alexandre Chen, Xin Collins, Pieter Forets, Marcelo Freire, Daniel Immler, Fabian Kochdumper, Niklas Sanders, David P. Schilling, Christian Department of Computer Science University of Verona Verona Italy ENSTA Paris Institut Polytechnique de Paris Palaiseau France Technische Universität München Munich Germany Mexico University of Dayton DaytonOH United States Department of Data Science and Knowledge Engineering Maastricht University Maastricht Netherlands Universidad de la República Montevideo Uruguay Computer Science Department Carnegie Mellon University United States Mexico City Mexico Department of Mathematics Massachusetts Institute of Technology CambridgeMA United States IST Austria Klosterneuburg Austria

We present the results of a friendly competition for formal verification of continuous and hybrid systems with nonlinear continuous dynamics. The friendly competition took place as part of the workshop Applied Verification for Continuous and Hybrid Systems (ARCH) in 2020. This year, 6 tools Ariadne, CORA, DynIbex, Flow*, Isabelle/HOL, and JuliaReach (in alphabetic order) participated. These tools are applied to solve reachability analysis problems on six benchmark problems, two of them featuring hybrid dynamics. We do not rank the tools based on the results, but show the current status and discover the potential advantages of different tools. © 2020 EasyChair. All rights reserved.

关键词： Hybrid systems

来源：评论

学校读者我要写书评

暂无评论

A Taxonomy of Online Marketing Methods

SSRN

引用

SSRN 2020年

作者： Camilleri, Mark Anthony Hajarian, Mohammad Díaz, Paloma Aedo, Ignacio Computer Science and Engineering Department Universidad Carlos III de Madrid Spain Department of Computer Engineering Basir Institute of Higher Education Abyek Iran Department of Corporate Communication Faculty of Media and Knowledge Sciences University of Malta Malta Malta

This chapter presents a systematic review of over thirty (30) types of online marketing methods. It describes different methods like email marketing, social network marketing, in-game marketing and augmented reality marketing, among other approaches. The researchers discuss that the rationale for using these online marketing strategies is to increase brand awareness, customer centric marketing and consumer loyalty. They shed light on various personalization methods including recommendation systems and user generated content in their taxonomy of online marketing terms. Hence, they explain how these online marketing methods are related to each other. The researchers contend that the boundaries between online marketing methods have not been clarified enough within the academic literature. Therefore, this chapter provides a better understanding of different online marketing methods. A review of the literature suggests that the ‘oldest’ online marketing methods including the email and the websites are still very relevant for today’s corporate communication. In conclusion, the researchers put forward their recommendations for future research about contemporary online marketing methods. © 2020, The Authors. All rights reserved.

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

Machine Memory Intelligence: Inspired by Human Memory Mechanisms

引用

engineering 2025年

作者： Qinghua Zheng Huan Liu Xiaoqing Zhang Caixia Yan Xiangyong Cao Tieliang Gong Yong-Jin Liu Bin Shi Zhen Peng Xiaocen Fan Ying Cai Jun Liu School of Computer Science and Technology Xi’an Jiaotong University Xi’an 710049 China Shaanxi Provincial Key Laboratory of Big Data Knowledge Engineering Xi’an Jiaotong University Xi’an 710049 China Translational Research Institute of Brain and Brain-Like Intelligence Shanghai Fourth People’s Hospital Shanghai 200434 China School of Medicine Tongji University Shanghai 200092 China Department of Computer Science and Technology Tsinghua University Beijing 100084 China Department of Computer Science Iowa State University Ames IA 50011 USA

Large models, exemplified by ChatGPT, have reached the pinnacle of contemporary artificial intelligence (AI). However, they are plagued by three inherent drawbacks: excessive training data and computing power consumption, susceptibility to catastrophic forgetting, and a deficiency in logical reasoning capabilities within black-box models. To address these challenges, we draw insights from human memory mechanisms to introduce “machine memory,” which we define as a storage structure formed by encoding external information into a machine-representable and computable format. Centered on machine memory, we propose the brand-new machine memory intelligence (M 2 I) framework, which encompasses representation, learning, and reasoning modules and loops. We explore the key issues and recent advances in the four core aspects of M 2 I, including neural mechanisms, associative representation, continual learning, and collaborative reasoning within machine memory. M 2 I aims to liberate machine intelligence from the confines of data-centric neural networks and fundamentally break through the limitations of existing large models, driving a qualitative leap from weak to strong AI.

关键词： Machine memory intelligence Neural mechanism Associative representation Continual learning Collaborative reasoning

来源：评论

学校读者我要写书评

暂无评论

Underwater acoustic intelligent spectrum sensing with multimodal data fusion: An Mul-YOLO approach

引用

Future Generation computer Systems 2025年 173卷

作者： Li, Yufang Zhang, Liliang Wang, Kai Xu, Lingwei Gulliver, T. Aaron Department of Information Science and Technology Qingdao University of Science and Technology Qingdao266061 China Xiangyang Sub-center of National Engineering Research Center for Water Transport Safety Hubei University of Arts and Science Xiangyang441053 China Key Laboratory of Symbolic Computation and Knowledge Engineering of Ministry of Education Jilin University Changchun130012 China Nanning530006 China Department of Electrical and Computer Engineering University of Victoria VictoriaBC V8W 2Y2 Canada

Realizing the Ocean Internet of Things (OIoT) requires diverse and comprehensive real-time marine data. This creates significant demands on spectrum resources for effective underwater communication. Coexisting users in the OIoT can generate massive amounts of data, which results in competition for underwater acoustic spectrum. To address the problem of poor utilization of this spectrum in complex and dynamic ocean environments, this paper proposes an intelligent spectrum sensing scheme based on multimodal data fusion. First, the system obtains time series data for the underwater acoustic signals and a wavelet transform is used to obtain the corresponding image data. The time series and image data constitute multimodal data that provide a more comprehensive time and space perspective and improve the diversity of features. Then, unsupervised learning with a Denoising Autoencoder is used to extract high-quality features from the time series data. Finally, a parallel dual Backbone YOLO network is constructed to compensate for the inability of traditional YOLO to extract multimodal features. One branch captures key temporal features through a network built with deep separable convolutions, while the other branch captures key spatial features using an improved CSPDarknet. This Mul-YOLO network can extract hierarchical structure information from underwater acoustic signals and integrate the diverse multilevel features of the data to achieve accurate spectrum sensing. Compared with Convolutional Neural Network (CNN), ResNet, Swin-Transformer, ConvNext and YOLOv5 algorithms, the average detection probability of the Mul-YOLO algorithm is increased by about 5.9% to 18.9%, and the average false alarm probability is optimized by about 7% to 12.7% in the range of signal-to-noise ratio from −12 dB to 0 dB. The results given show that the proposed algorithm can detect spectrum holes with high accuracy and effectively avoid interference between users. © 2025 Elsevier B.V.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Part-of-Speech Tagging to Standardize Central-Kurdish Language: A Research Guide for Kurdish Natural Language Processing Tasks

arXiv

引用

arXiv 2025年

作者： Sabr, Shadan Shukr Mustafa, Nazira Sabr Omar, Talar Sabah Rasool, Salah Hwayyiz Omer, Nawzad Anwer Hamad, Darya Sabir Shams, Hemin Abdulhameed Kareem, Omer Mahmood Abdullah, Rozhan Noori Abdullah, Khabat Atar Mohammad, Mahabad Azad Al-Raghefy, Haneen Asaad, Safar M. Mohammed, Sara Jamal Ali, Twana Saeed Shawrow, Fazil Maghdid, Halgurd S. Department of Kurdish Language Faculty of Education Koya University Danielle Mitterrand Boulevard Kurdistan Region KoyaKOY45 Iraq Department of Computer Science Faculty of Health and Science Koya University Koya Kurdistan Region KOY45 Iraq Department of Software Engineering Faculty of Engineering Koya University Danielle Mitterrand Boulevard Kurdistan Region KoyaKOY45 Iraq Department of Computer Engineering College of Engineering Knowledge University Erbil44001 Iraq Department of English language Faculty of Education Koya University Danielle Mitterrand Boulevard Kurdistan Region KoyaKOY45 Iraq Department of Computer Engineering College of Engineering University of Sulaimani Region Kurdistan Iraq Department of Engineering Research Center Deanship of R&D Centers Koya University Danielle Mitterrand Boulevard Kurdistan Region KoyaKOY45 Iraq

The field of natural language processing (NLP) has dramatically expanded within the last decade. Many human-being applications are conducted daily via NLP tasks, starting from machine translation, speech recognition, text generation and recommendations, Part-of-Speech tagging (POS), and Named-Entity Recognition (NER). However, low-resourced languages, such as the Central-Kurdish language (CKL), mainly remain unexamined due to shortage of necessary resources to support their development. The POS tagging task is the base of other NLP tasks;for example, the POS tag set has been used to standardized languages to provide the relationship between words among the sentences, followed by machine translation and text recommendation. Specifically, for the CKL, most of the utilized or provided POS tagsets are neither standardized nor comprehensive. To this end, this study presented an accurate and comprehensive POS tagset for the CKL to provide better performance of the Kurdish NLP tasks. The article also collected most of the POS tags from different studies as well as from Kurdish linguistic experts to standardized part-of-speech tags. The proposed POS tagset is designed to annotate a large CKL corpus and support Kurdish NLP tasks. The initial investigations of this study via comparison with the Universal Dependencies framework for standard languages, show that the proposed POS tagset can streamline or correct sentences more accurately for Kurdish NLP tasks. © 2025, CC BY.

关键词： Calibration

来源：评论

学校读者我要写书评

暂无评论

Web-based teamwork: Distributed software development course under Covid-19 15

Web-based teamwork: Distributed software development course ...

引用

15th International Conference on computer science and Education, ICCSE 2020

作者： Zhang, Rui Mestre, Pedro Serodio, Carlos Prada, Marilia Gao, Wenjuan Jilin University Key Lab of Symbolic Computation and Knowledge Engineering Chinese Ministry of Education College of Computer Science and Technology Changchun130012 China University of Minho Centro Algoritmi Guimaraes4800-058 Portugal Department of Social and Organizational Psychology Lisboa Portugal Library of Changchun University Changchun130022 China

ISBN: (纸本)9781728172675

In a increasingly globalized world, it is very important to help students to acquire the hard and soft skills needed to cope with the challenges they will face when working in such environments. However, even though students find this subject interesting and volunteer for it, it is hard, even impossible to teach college students such a distributed fashion of teamwork. In this paper, a case study is provided to illustrate the methodology and experiences of a joint course, distributed software development, of multiple universities from Asia, Europe, North and South Americas. The results show that student can get the spirit, effective communication for such web-based teamwork environment and achieve software project development. The recent developments because of the Covid-19 pandemic are the facts that now students have to cooperate remotely with each other not only across continents but also inside their own city or country. It has increased the awareness of the need for this kind of training and effectively improved the interactions between team elements in different countries and improved the students' feeling of belonging to their team. © 2020 IEEE.

关键词： Students

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：