检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer Vision (WACV)

作者： Mingxian Li Hao Sun Yingtie Lei Xiaofeng Zhang Yihang Dong Yilin Zhou Zimeng Li Xuhang Chen School of Computer Science and Engineering Huizhou University Department of Computer Science and Engineering The Ohio State University School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shenzhen Institute of Advanced Technology Chinese Academy of Sciences School of Electronic and Communication Engineering Shenzhen Polytechnic University

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Document images are often degraded by various stains, significantly impacting their readability and hindering downstream applications such as document digitization and analysis. The absence of a comprehensive stained document dataset has limited the effectiveness of existing document enhancement methods in removing stains while preserving fine-grained details. To address this challenge, we construct StainDoc, the first large-scale, high-resolution (2145 x 2245) dataset specifically designed for document stain removal. StainDoc comprises over 5,000 pairs of stained and clean document images across multiple scenes. This dataset encompasses a diverse range of stain types, severities, and document backgrounds, facilitating robust training and evaluation of document stain removal algorithms. Furthermore, we propose StainRestorer, a Transformer-based document stain removal approach. StainRestorer employs a memory-augmented Transformer architecture that captures hierarchical stain representations at part, instance, and semantic levels via the DocMemory module. The Stain Removal Transformer (SRTransformer) leverages these feature representations through a dual attention mechanism: an enhanced spatial attention with an expanded receptive field, and a channel attention captures channel-wise feature importance. This combination enables precise stain removal while preserving document content integrity. Extensive experiments demonstrate StainRestorer's superior performance over state-of-the-art methods on the Stain-Doc dataset and its variants *** and ***, establishing a new benchmark for document stain removal. Our work highlights the potential of memory-augmented Transformers for this task and contributes a valuable dataset to advance future research.

关键词： Training Deep learning computer vision Text analysis Attention mechanisms Semantics Memory architecture Benchmark testing Transformers Image restoration

来源：评论

学校读者我要写书评

暂无评论

Applied Virtual Reality in 3D Geometry 7

Applied Virtual Reality in 3D Geometry

引用

7th South-East Europe Design Automation, computer engineering, computer Networks and Social Media Conference, SEEDA-CECNSM 2022

作者： Sakkas, Konstantinos Tsogka, Alexandra Giannakeas, Nikolaos Tzimourta, Katerina D. Tzallas, Alexandros T. Glavas, Euripidis University of Ioannina Department of Informatics and Telecommunication Arta Greece University of Western Macedonia Dept. of Electrical and Computer Engineering Kozani Greece

ISBN: (数字)9798350398588

ISBN: (纸本)9798350398588

The development of Virtual Reality technologies has improved people's daily lives in many sections. Nowadays, it is applied in fields such as Health, Work, Telecommuting and in a large number of other sectors. Education from different perspectives is something that constantly concerns researchers and virtual reality developers, which is why we come across a series of virtual reality applications for situation simulation and student education. Mathematics and especially geometry which is interrelated with the concept of the implementation of applications in three-dimensional space, as well as VR applications, from the perspective of learning are often considered complicated as there are three-dimensional objects that are not easily perceived only through a book. In this paper we examine how through virtual reality geometric concepts can be better understood but at the same time to examine geometric shapes from different angles and perspectives. © 2022 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Leveraging LLM in Genetic Programming Hyper-heuristics for Dynamic Microservice Deployment 37th

Leveraging LLM in Genetic Programming Hyper-heuristics for...

引用

37th Australasian Joint Conference on Artificial Intelligence, AJCAI 2024

作者： Fang, Zhengxin Ma, Hui Chen, Gang Hartmann, Sven Wang, Chen Centre for Data Science and Artificial Intelligence and School of Engineering and Computer Science Victoria University of Wellington Wellington New Zealand Department of Informatics Clausthal University of Technology Clausthal-Zellerfeld Germany National Institute of Water and Atmospheric Research Wellington New Zealand

ISBN: (纸本)9789819603473

Microservice deployment in cloud computing is a challenging combinatorial optimization problem due to the complex dependencies among microservices and the intricate trade-offs among different QoS requirements, e.g., minimizing Energy Consumption (EC) vs. minimizing Communication Overhead (CO). Recently, some hyper-heuristics methods, particularly Genetic Programming Hyper-Heuristics (GPHH), have been proposed to automatically generate heuristics for solving dynamic microservice deployment problems. Meanwhile, Large Language Models (LLMs) are becoming popular for solving various domain-specific problems thanks to their strong ability to learn problem-related knowledge. However, hybridizing GPHH with LLM by combining their abilities in solving complex optimization problems remains unexplored. In this paper, we propose an LLM-enhanced Genetic Programming Hyper-Heuristic (LLM-GPHH) algorithm to evolve heuristics for the dynamic deployment of applications composed of microservices, to jointly optimize EC and CO. Our experiments on real-world datasets demonstrate the effectiveness of the newly proposed LLM-GPHH. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Genetic programming

来源：评论

学校读者我要写书评

暂无评论

Deformable Objects Perception is Just a Few Clicks Away – Dense Annotations from Sparse Inputs

Deformable Objects Perception is Just a Few Clicks Away – D...

引用

IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

作者： Alessio Caporali Kevin Galassi Matteo Pantano Gianluca Palli Department of Electrical Electronic and Information Engineering University of Bologna Bologna Italy Department of Electrical and Computer Engineering Technical University of Munich Munich Germany

ISBN: (数字)9798350377705

ISBN: (纸本)9798350377712

Deformable Objects (DOs), e.g. clothes, garments, cables, wires, and ropes, are pervasive in our everyday environment. Despite their importance and widespread presence, many limitations exist when deploying robotic systems to interact with DOs. One source of challenges arises from their complex perception. Deep learning algorithms can address these issues; however, extensive training data is usually required. This paper introduces a method for efficiently labeling DOs in images at the pixel level, starting from sparse annotations of key points. The method allows for the generation of a real-world dataset of DO images for segmentation purposes with minimal human effort. The approach comprises three main steps. First, a set of images is collected by a camera-equipped robotic arm. Second, a user performs sparse annotation via key points on just one image from the collected set. Third, the initial sparse annotations are converted into dense labels ready for segmentation tasks by leveraging a foundation model in zero-shot settings. Validation of the method on three different sets of DOs, comprising cloth and rope-like objects, showcases its practicality and efficiency. Consequently, the proposed method lays the groundwork for easy DO labeling and the seamless integration of deep learning perception of DOs into robotic agents.

关键词： Deep learning Image segmentation Annotations Foundation models Wires Clothing Training data Manipulators Labeling Intelligent robots

来源：评论

学校读者我要写书评

暂无评论

Emotionally Challenging Games Can Satisfy Older Adults' Psychological Needs: From Empirical Study to Design Guidelines 25

Emotionally Challenging Games Can Satisfy Older Adults' Psyc...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI 2025

作者： Zhou, Min Peng, Xiaolan Liu, Binjie Denisova, Alena Barathi, Soumya C. Li, Zhuying Xie, Xurong Huang, Jin Tian, Feng Institute of Software Chinese Academy of Sciences Beijing China Department of Computer Science University of York York United Kingdom School of Computer Science and Informatics Cardiff University Cardiff United Kingdom School of Computer Science and Engineering Southeast University Nanjing China

ISBN: (纸本)9798400713941

Older adults often struggle to meet their psychological needs due to retirement and living alone. Recent studies suggest that games featuring emotional challenge (EC) can help fulfill basic psychological needs such as autonomy, competence, and relatedness by facilitating emotional exploration. However, it remains unclear whether older adults can benefit from EC games, whether they find this genre enjoyable, and how these games should be designed to better meet their needs. This work explores older adults' experiences and perceptions of playing EC games through two studies. The first study involved playing Detroit: Become Human, revealing that older adults derived multifaceted psychological experiences from playing the game. The second study involved a custom-designed game scenario tailored to older adults, demonstrating that meaningful choices significantly influenced autonomy need satisfaction. Based on these findings, we offer five design guidelines for developing EC games that satisfy psychological needs of older adults. © 2025 Copyright held by the owner/author(s). Publication rights licensed to ACM.

关键词： Design Guidelines Emotional Challenge Older Adults Psychological Need Satisfaction Video Games

来源：评论

学校读者我要写书评

暂无评论

Deep Learning for Speaker Recognition: A Comparative Analysis of 1D-CNN and LSTM Models Using Diverse Datasets

Deep Learning for Speaker Recognition: A Comparative Analysi...

引用

Electrics and computer (INTCEC), Interdisciplinary Conference on

作者： Hiwa Hassanzadeh Jihad Anwar Qadir Saman Muhammad Omer Mohammed Hussein Ahmed Edris Khezri Department of Software and Informatics Engineering University of Raparin Rania Kurdistan Region Iraq Department of Computer Engineering Boukan Branch Islamic Azad University Boukan Iran

ISBN: (数字)9798350349450

ISBN: (纸本)9798350349467

Speaker recognition is a vital component of identity verification and security systems that has made significant progress through the use of deep neural networks. This article examines the comparative performance of two neural network models, namely a one-dimensional convolutional neural network (1D-CNN) and a long short-term memory (LSTM-based) network in identifying individuals based on their recorded voices. The article uses three diverse datasets, including the Raparin Artificial Intelligent Lab (RAIL) dataset, which was created locally, and two public datasets, namely the TIMIT dataset and the Jordan dataset. The results show that the proposed 1D-CNN model consistently outperforms the LSTM model and has a significant accuracy rate, especially in the RAIL dataset, which achieves an accuracy of over 95.22%. This study emphasizes the potential of deep learning algorithms in improving sound-based identity recognition and highlights its effects on system security and communications.

关键词： Rails Deep learning Analytical models Electric potential Accuracy Speaker recognition Noise measurement

来源：评论

学校读者我要写书评

暂无评论

A Stacking Approach Based on Machine Learning Techniques for Lungs Cancer Prediction in Healthcare Systems 20

A Stacking Approach Based on Machine Learning Techniques for...

引用

20th International computer Conference on Wavelet Active Media Technology and Information Processing, ICCWAMTIP 2023

作者： Haq, Amin Ul Li, Jian Ping Hussain, Khalid Saboor, Abdus Khan, Tahir School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China Mohi-Ud-Din Islamic University Computer Science Department AJ and Kashmir Pakistan Abasyn University Peshawar Peshawar Pakistan

ISBN: (纸本)9798350318982

Lung cancer poses a serious risk to life and causes death of both males and females in the world. Survival rate and reduced death rate can be improved if breathed at the first stage. The proposed approach utilizes machine-learning techniques such as ensemble learning techniques known as stacking to enhance the predictive accuracy of a classification model. The methodology used dataset downloaded from Kaggle website, which contain 16 attributes and 309 records. We divide the dataset into train and test sets. The model is train the multiple diverse base models, by using various algorithms, such as Random Forest, AdBoost, SVM, Decision Tree are used as base models are then employed to generate predictions on a validation dataset. Subsequently, a meta-model, exemplified by Logistic Regression, will train from base model predictions. By taking the outputs of the base models used as input for the meta-model, the ensemble stacking classifier creates a more robust and accurate model. The effectiveness of this ensemble or Stacking model or Lung cancer diagnosis (SLCD) will demonstrate through evaluating its performance on a testing dataset, resulting in an accuracy score that validates its potential to enhance predictive outcomes compared to individual models. The approach serves as a practical strategy that will leverage the strengths of the Stacking Lung Cancer diagnosis (SLCD) model to achieve superior predictive performance and will predict whether lung cancer is present or not in both males and females. The performance of our model will be measured by using performance matrices such as accuracy, precision, recall, F1 Scope. The propose model will easily incorporating in electronic-healthcare systems for early diagnosis Lung cancer to ensure proper treatment and recovery. © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Distributed Average Consensus via Noisy and Non-Coherent Over-the-Air Aggregation

arXiv

引用

arXiv 2024年

作者： Yang, Huiwen Chen, Xiaomeng Huang, Lingying Dey, Subhrakanti Shi, Ling The Department of Electronic and Computer Engineering Hong Kong University of Science and Technology 00852 Hong Kong The School of Electrical and Electronic Engineering Nanyang Technological University Singapore The Department of Electrical Engineering Uppsala University Uppsala Sweden

Over-the-air aggregation has attracted widespread attention for its potential advantages in task-oriented applications, such as distributed sensing, learning, and consensus. In this paper, we develop a communication-efficient distributed average consensus protocol by utilizing over-the-air aggregation, which exploits the superposition property of wireless channels rather than combat it. Noisy channels and non-coherent transmission are taken into account, and only half-duplex transceivers are required. We prove that the system can achieve average consensus in mean square and even almost surely under the proposed protocol. Furthermore, we extend the analysis to the scenarios with time-varying topology. Numerical simulation shows the effectiveness of the proposed protocol. Copyright © 2024, The Authors. All rights reserved.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

Rectenna-Based Wireless Power Transfer for Implantable Bioelectronic Devices

Rectenna-Based Wireless Power Transfer for Implantable Bioel...

引用

2024 IEEE International Women in engineering (WIE) Conference on Electrical and computer engineering, WIECON-ECE 2024

作者： Salehin, Sultanus Islam, Akib Jayed Pranta, Swapnil Das, Nobel Paul, Shreya Ul Alam, Sayem Pavel, Tanvir Ahamed Uddin, Arafat The University of Alabama Department of Ece Tuscaloosa United States Norwegian University of Science and Technology Computational Colour & Spectral Imaging Gjφvik Norway Port City International University Electrical and Electronic Engineering Chattogram Bangladesh National Institute of Technology Electrical and Electronics Engineering Tamil Nadu Trichy India The University of Alabama Electrical and Computer Engineering Tuscaloosa United States

ISBN: (纸本)9798331535476

Implantable medical devices (IMDs), such as pacemakers, neurostimulators, and drug delivery systems, are being revolutionized by advancements in radio frequency (RF)-based wireless power transfer (WPT). This study focuses on the design and optimization of implantable rectennas, which convert electromagnetic radiation into DC power for IMDs. Key considerations include operating frequency, antenna dimensions, biocompatibility, and power conversion efficiency. A comprehensive human tissue model, incorporating safety parameters such as Specific Absorption Rate (SAR), is proposed to evaluate antenna performance in realistic conditions. The results highlight an impressive 88.65% RF-to-DC conversion efficiency, achieved through innovations in material science and advanced 3D printing techniques. These advancements not only improve the compactness and efficiency of rectennas but also open new possibilities for enhancing the reliability and safety of biomedical power systems. © 2024 IEEE.

关键词： Rectennas

来源：评论

学校读者我要写书评

暂无评论

Vessels Segmentation in Angiograms Using Convolutional Neural Network: A Deep Learning Based Approach

引用

computer Modeling in engineering & Sciences 2023年第7期136卷 241-255页

作者： Sanjiban Sekhar Roy Ching-Hsien Hsu Akash Samaran Ranjan Goyal Arindam Pande Valentina E.Balas School of Computer Science and Engineering Vellore Institute of TechnologyVellore632014India Department of Computer Science and Information Engineering Asia UniversityTaichung41354Taiwan Department of Medical Research China Medical University HospitalChina Medical UniversityTaichung406Taiwan Guangdong-Hong Kong-Macao Joint Laboratory for Intelligent Micro-Nano Optoelectronic Technology School of Mathematics and Big DataFoshan UniversityFoshan528000China Medica Superspecialty Hospital Kolkata700099India Automation and Applied Informatics Aurel Vlaicu University of AradArad310130Romania

Coronary arterydisease(CAD)has become a significant causeof heart attack,especially amongthose 40yearsoldor *** is a need to develop new technologies andmethods to deal with this *** researchers have proposed image processing-based solutions for CADdiagnosis,but achieving highly accurate results for angiogram segmentation is still a *** different types of angiograms are adopted for CAD *** paper proposes an approach for image segmentation using ConvolutionNeuralNetworks(CNN)for diagnosing coronary artery disease to achieve state-of-the-art *** have collected the 2D X-ray images from the hospital,and the proposed model has been applied to *** augmentation has been performed in this research as it’s the most significant task required to be initiated to increase the dataset’s ***,the images have been enhanced using noise removal techniques before being fed to the CNN model for segmentation to achieve high *** the output,different settings of the network architecture undoubtedly have achieved different accuracy,among which the highest accuracy of the model is 97.61%.Compared with the other models,these results have proven to be superior to this proposed method in achieving state-of-the-art results.

关键词： Angiogram convolution neural network coronary artery disease diagnosis of CAD image segmentation

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：