检索结果-内蒙古大学图书馆

32nd British Machine Vision Conference, BMVC 2021

作者： Xiu, Haoyi Liu, Xin Wang, Weimin Kim, Kyoung-Sook Shinohara, Takayuki Chang, Qiong Matsuoka, Masashi Department of Architecture and Building Engineering Tokyo Institute of Technology Tokyo Japan Artificial Intelligence Research Center AIST Tokyo Japan DUT-RU International School of Information Science and Engineering Dalian University of Technology Dalian China Department of Computer Science Tokyo Institute of Technology Tokyo Japan

We present a simple but effective attention named the unary-pairwise attention (UPA) for modeling the relationship between 3D point clouds. Our idea is motivated by the analysis that the standard self-attention (SA) that operates globally tends to produce almost the same attention maps for different query positions, revealing difficulties for learning query-independent and query-dependent information jointly. Therefore, we reformulate the SA and propose query-independent (Unary) and query-dependent (Pairwise) components to facilitate the learning of both terms. In contrast to the SA, the UPA ensures query dependence via operating locally. Extensive experiments show that the UPA outperforms the SA consistently on various point cloud understanding tasks including shape classification, part segmentation, and scene segmentation. Moreover, simply equipping the popular PointNet++ method with the UPA even outperforms or is on par with the state-of-the-art attention-based approaches. In addition, the UPA systematically boosts the performance of both standard and modern networks when it is integrated into them as a compositional module. © 2021. The copyright of this document resides with its authors.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Impurity explicit optimal Machine learning and statistical perfect construction for air quality prediction

Impurity explicit optimal Machine learning and statistical p...

引用

Networking and Communications (ICNWC), International Conference on

作者： Nareshkumar R R. Shalinikumari S. Sri Nandhini Kowsalya Vijay Anand P Ajmal Mohamed S. Gayathri Department of Networking and Communications School of Computing College of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Tamilnadu India Department of Architecture Bharath Institute of Higher Education and Research Selaiyur Chennai Tamilnadu India Department of Information Technology Veltech Multitech Dr.Rangarajan Dr.Sakunthala Engineering College Chennai Tamilnadu India Department of Artificial Intelligence and Data Science CMR Institute of Technology Bengaluru India Department of Computer Science and Engineering Saveetha School of Engineering Chennai India Department of Computer Science and Engineering K. Ramakrishnan College of Technology Trichy Tamilnadu India

ISBN: (数字)9798350365269

ISBN: (纸本)9798350365276

The air quality index (AQI) is a metric used to report air quality levels. There has been a substantial rise in the level of air pollution in Indian cities. Multiple methodologies exist for formulating a mathematical equation to ascertain the air quality index. Multiple studies have established a correlation between exposure to air pollution and negative health effects in the general population. The objective of this study is to determine the optimal approach for predicting AQI in order to aid in climate regulation. Nine separate Machine learning (ML) algorithms have been employed in the suggested study to ascertain the AQI. The use of the SMOTE algorithm in the datasets in ML resulted in improved accuracy when comparing the outcomes. Furthermore, all of the implementations have been thoroughly documented using graphs and metrics, which clearly illustrate the differences in outcomes and aid in identifying the specific factors that led to the improvement in accuracy.

关键词： Measurement Machine learning algorithms Urban areas Sociology Machine learning Predictive models Air pollution

来源：评论

学校读者我要写书评

暂无评论

Metaverse for Education: Developments, Challenges, and Future Direction

引用

computer Applications in engineering Education 2025年第3期33卷

作者： Chamola, Vinay Peelam, Mritunjay Shall Mittal, Uday Hassija, Vikas Singh, Anushka Pareek, Ritawari Mangal, Poorvi Sangwan, Devika de Albuquerque, Victor Hugo C. Mahmud, Mufti Brown, David J. Department of Electrical and Electronics Engineering Internet of Things Research Group APPCAIR BITS-Pilani Rajasthan Pilani India Department of Electrical and Electronics Engineering BITS-Pilani Rajasthan Pilani India School of Computer Engineering Kalinga Institute of Industrial Technology Odisha Bhubaneswar India Department of Computer Science and Engineering Jaypee Institute of Information Technology Uttar Pradesh Noida India Department of Humanities and Social Sciences BITS-Pilani Rajasthan Pilani India Fortaleza Brazil Department of Computer Science Computing and Informatics Research Centre Medical Technologies Innovation Facility at Nottingham Trent University Clifton Lane Nottingham United Kingdom Department of Computer Science Computing and Informatics Research Centre at Nottingham Trent University Clifton Lane Nottingham United Kingdom

The rapid advancements in digital technologies such as artificial intelligence (AI), virtual reality (VR), augmented reality (AR), mixed reality (MR), extended reality (XR), and the internet of things (IoT) have revolutionized various sectors, including education. Metaverse, a convergence of these transformative technologies, offers immersive, personalized, and interactive experiences, making it a powerful tool in modern education. This paper explores the Metaverse's role in enhancing education by examining its architecture, types, and components while addressing practical implementation challenges, and follows a structured review protocol to ensure a comprehensive analysis, including systematic research, paper selection, and a critical examination of relevant studies from reputable databases such as Google Scholar, IEEE Xplore, ACM, and Springer. The research objectives focus on evaluating the Metaverse's applications in education, ethical challenges, technological limitations, and potential strategies for sustainable integration. Key research questions address the need for Metaverse adoption in education, its benefits, challenges, and future directions. The Metaverse cultivates essential skills such as empathy, ethical reasoning, and effective communication by providing students with customized, immersive learning environments. However, ethical concerns, technical barriers, and infrastructural costs pose significant obstacles to its widespread adoption. It discusses strategies to solve these barriers, explores applications in distance learning, and proposes future research directions to create scalable and sustainable educational models in the Metaverse. Through this structured inquiry, the paper establishes the Metaverse as a transformative force in education, blending technological innovation with instructional advancement. © 2025 Wiley Periodicals LLC.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Fine-grained Retrieval Prompt Tuning

arXiv

引用

arXiv 2022年

作者： Wang, Shijie Chang, Jianlong Wang, Zhihui Li, Haojie Ouyang, Wanli Tian, Qi International School of Information Science & Engineering Dalian University of Technology China Huawei Cloud & AI China College of Computer and Engineering Shandong University of Science and Technology China SenseTime Computer Vision Research Group The University of Sydney Australia

Fine-grained object retrieval aims to learn discriminative representation to retrieve visually similar objects. However, existing top-performing works usually impose pairwise similarities on the semantic embedding spaces or design a localization sub-network to continually fine-tune the entire model in limited data scenarios, thus resulting in convergence to suboptimal solutions. In this paper, we develop Fine-grained Retrieval Prompt Tuning (FRPT), which steers a frozen pre-trained model to perform the fine-grained retrieval task from the perspectives of sample prompting and feature adaptation. Specifically, FRPT only needs to learn fewer parameters in the prompt and adaptation instead of fine-tuning the entire model, thus solving the issue of convergence to suboptimal solutions caused by fine-tuning the entire model. Technically, a discriminative perturbation prompt (DPP) is introduced and deemed as a sample prompting process, which amplifies and even exaggerates some discriminative elements contributing to category prediction via a content-aware inhomogeneous sampling operation. In this way, DPP can make the fine-grained retrieval task aided by the perturbation prompts close to the solved task during the original pre-training. Thereby, it preserves the generalization and discrimination of representation extracted from input samples. Besides, a category-specific awareness head is proposed and regarded as feature adaptation, which removes the species discrepancies in features extracted by the pre-trained model using category-guided instance normalization. And thus, it makes the optimized features only include the discrepancies among subcategories. Extensive experiments demonstrate that our FRPT with fewer learnable parameters achieves the state-of-the-art performance on three widely-used fine-grained datasets. © 2022, CC0.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Deep Multi-View Multiclass Twin Support Vector Machines

SSRN

引用

SSRN 2022年

作者： Xie, Xijiong Li, Yanfeng Sun, Shiliang The school of Information Science and Engineering Ningbo University China The School of Computer Science and Technology The Head of the Pattern Recognition Machine Learning Research Group East China Normal University China

Multi-view learning (MVL) is a rapidly evolving direction in the field of machine learning. Despite the positive results, most algorithms that combine multi-view learning with twin support vector machines (TSVM) focus on the traditional machine learning domain. No method has been accomplished for combining MVL, TSVM, and deep learning. In this paper, we propose two novel multi-view deep models to solve the multiclass classification problem, namely deep multi-view twin support vector machines (DMvTSVM) based on deep neural network (DNN) and auto-encoder (AE) network. They find two non-parallel hyperplanes such that each hyperplane is as close to its own class as possible while being as far away from the other class as possible. Meanwhile, we apply similarity regularization to the Deep TSVM classifier output for each view to learn consensus information between views and use this to refine the combined weights of the deep model and TSVM. Finally, the new models employ the one − vs − rest strategy to allow the DMvTSVM classifier to solve the multiclass classification problems. In the experiments, the proposed methods are compared with existing state-of-the-art algorithms to prove effective. © 2022, The Authors. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Towards a Unified Approach to Homography Estimation Using Image Features and Pixel Intensities

arXiv

引用

arXiv 2022年

作者： Nogueira, Lucas de Paiva, Ely C. Silveira, Geraldo School of Mechanical Engineering University of Campinas Campinas SP Brazil Robotics and Computer Vision Research Group Center for Information Technology Renato Archer Campinas SP Brazil

The homography matrix is a key component in various vision-based robotic tasks. Traditionally, homography estimation algorithms are classified into feature- or intensity-based. The main advantages of the latter are their versatility, accuracy, and robustness to arbitrary illumination changes. On the other hand, they have a smaller domain of convergence than the feature-based solutions. Their combination is hence promising, but existing techniques only apply them sequentially. This paper proposes a new hybrid method that unifies both classes into a single nonlinear optimization procedure, applies the same minimization method, and uses the same homography parametrization and warping function. Experimental validation using a classical testing framework shows that the proposed unified approach has improved convergence properties compared to each individual class. These are also demonstrated in a visual tracking application. As a final contribution, our ready-to-use implementation of the algorithm is made publicly available to the research community. © 2022, CC BY.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Rethinking Self-Supervised Learning for Time Series Forecasting: A Temporal Perspective

SSRN

引用

SSRN 2024年

作者： Zhao, Shubao Li, Zengxiang Zhou, Xinxing Jin, Ming Hou, Zhaoxiang Yang, Chengyi Wen, Qingsong Wang, Yi Wen, Yanlong Yuan, Xiaojie Digital Research Insitute ENN Group Beijing China College of Computer Science Nankai University Tianjin China School of Information and Communication Technology Griffith University Nathan Australia Squirrel AI Bellevue United States Department of Electrical and Engineering The University of Hong Kong Hong Kong

Self-supervised learning, including contrastive learning and masked modeling, has garnered significant attention for its ability to learn meaningful representations. Recent efforts have enhanced time series forecasting by introducing advanced self-supervised pre-training methods. However, these efforts have faced limitations due to two primary drawbacks. Firstly, these approaches often borrow techniques from vision and language domains without adequately addressing the unique temporal dependencies inherent in time series data. Secondly, different pre-training strategies lack an organic combination to build a more powerful feature extractor. To address these issues, we propose TempSSL, a self-supervised learning framework for time series forecasting. TempSSL divides the time series data into context (history data) and target (future data), employing two pre-training strategies: (1) Temporal Masked Modeling (TMM) designed to capture temporal dependencies by reconstructing future time series based on historical context;(2) Temporal Contrastive Learning (TCL) employs context and target as positive samples to enhance discriminative representations and mitigate distribution shifts within the time series. TempSSL's innovation lies in two key aspects. Firstly, it underscores the importance of temporal dependencies for time series forecasting by designing specific pre-training tasks. Secondly, it effectively integrates contrastive learning and masked modeling, leveraging their respective strengths to develop time series representation with strong instance discriminability and local perceptibility. Extensive experiments conducted on seven mainstream datasets demonstrate that TempSSL significantly outperforms contemporary self-supervised and end-to-end learning methods by a considerable margin of 1.92~78.12\%. The effectiveness of TempSSL is further demonstrated through its application in natural gas demand forecasting. © 2024, The Authors. All rights reserved.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Segmentation and Multi-facet Classification of Individual Logs in Wooden Piles 18th

Segmentation and Multi-facet Classification of Individual Lo...

引用

18th International Conference on computer Aided Systems Theory, EUROCAST 2022

作者： Praschl, Christoph Auersperg-Castell, Philipp Forster-Heinlein, Brigitte Zwettler, Gerald Adam Research Group Advanced Information Systems and Technology Research and Development Department University of Applied Sciences Upper Austria Hagenberg Austria Department of Software Engineering School of Informatics Communications and Media University of Applied Sciences Upper Austria Hagenberg Austria Bluedynamics Auersperg-Castell KG Kritzing 31 Freinberg Austria Faculty of Computer Science and Mathematics University of Passau Passau Germany

ISBN: (纸本)9783031253119

The inspection of products and assessment of quality is connected with high costs and time effort in many industrial domains. This also applies to the forestry industry. Utilizing state-of-the-art deep learning models allows automizing the analysis of wooden piles in a vision-based manner. In this work, a parallel two-step approach is presented for the segmentation and multi-facet classification of individual logs, according to the wood type and quality. The present approach is based on a preliminary log localization step and like this allows determining the quality, volume and also the value of individual logs, respectively the whole wooden pile. Using a YOLOv4 model for wood species classification for douglas firs, pines and larches results in an accuracy of 74.53%, while a quality classification model for spruce logs reaches 86.58%. In addition to that, the trained U-NET segmentation model reaches an accuracy of 93%. In the future, the underlying data set and models will be further improved and integrated to a mobile application for the on site analysis of wooden piles by foresters. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Experimental Demonstration of Tissue-Independent Camera Integrated Antenna for WCE

Experimental Demonstration of Tissue-Independent Camera Inte...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Muhammad Qamar Kamil Yavuz Kapusuz Mohamed A. Thaha Akram Alomainy Queen Mary University of London: School of Electronic Engineering and Computer Science London UK Department of Information Technology IDLab/EM Group Ghent University-imec Ghent Belgium National Bowel Research Centre Blizard Institute Barts and the London School of Medicine & Dentistry Queen Mary University of London London UK

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

For unobtrusive camera integration and robust gastrointestinal (GI) tract performance, a tissue-independent planar stacked meandered antenna along an annular ring substrate is proposed for the 401 MHz medical device radio communications service (MedRadio) band. The proposed topology is showcased through conventional printed circuit board (PCB) technology. Measurement results validate the direct camera integration and excellent tissue-independent performance in terms of impedance matching and radiation.

关键词： Performance evaluation Impedance measurement Medical devices Impedance matching Printed circuits Cameras Topology

来源：评论

学校读者我要写书评

暂无评论

Blockchain-based security solutions for IOT networks: Analysing efficacy and implementation challenges

Blockchain-based security solutions for IOT networks: Analys...

引用

Pervasive Computational Technologies (ICPCT), International Conference on

作者： Gotte Ranjith Kumar Chamaraju Y S Umar M Mulani R. Naveenkumar Auadhati Datta Budesh Kanwer School of CS & AI SR University Warangal Telangana India Department of Electronics & Communication Engineering Govt CPC Polytechnic Mysore Karnataka KJ College of Engineering and Management Research Pune Department of Computer Science and Engineering Chandigarh Colleges of Engineering Chandigarh Group of Colleges Jhanjeri Mohali Punjab India Department of Management Studies Vignan's Institute of Information Technology Duvvada Andhra Pradesh Poornima Institute of Engineering and Technology Jaipur Rajasthan

ISBN: (数字)9798331508685

ISBN: (纸本)9798331519476

Blockchain innovation has gathered significant attention from both scholars and industry professionals after years of development. This technology enables the creation of smart contracts, which facilitate automated deal execution among users. Today, blockchain is also employed as a specialized infrastructure in some IT applications, helping prevent data duplication, similar to how Bitcoin and other cryptocurrencies manage transaction records. Bitcoin records, for instance, are exceptionally secure as the currency circulates across hundreds of thousands of servers, making it nearly impossible to alter. For a successful breach, an attacker would need to manipulate records on 51% of these servers simultaneously. In contrast, private data stored on single servers, such as those managed by Amazon and Google, are more vulnerable to cyberattacks. In this paper, the study propose leveraging blockchain to address security concerns in the Internet of Things. The study identifies and categorizes common security challenges, with a focus on data privacy issues, as well as the protocols used for network organization, communication, and management. Following this, the study outline security solutions for IoT and illustrate scenarios in which blockchain is applied within IoT applications.

关键词： Technological innovation Computational modeling Clustering algorithms Authentication Bitcoin Blockchains Internet of Things Security Servers Load modeling

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：