检索结果-南通市图书馆

High-Confidence Computing 2024年第2期4卷 33-49页

作者： Lakshmi Priya Rachakonda Madhuri Siddula Vanlin Sathya Department of Computer Science North Carolina A&T State UniversityGreensboro 27401USA Celona inc. San Francisco 95008USA

The emergence of the Internet of Things(IoT)has triggered a massive digital transformation across numerous *** transformation requires efficient wireless communication and connectivity,which depend on the optimal utilization of the available spectrum *** the limited availability of spectrum resources,spectrum sharing has emerged as a favored solution to empower IoT deployment and connectivity,so adequate planning of the spectrum resource utilization is thus essential to pave the way for the next generation of IoT applications,inc.uding 5G and *** article presents a comprehensive study of prevalent wireless technologies employed in the field of the spectrum,with a primary focus on spectrum-sharing solutions,inc.uding shared *** highlights the associated security and privacy concerns when the IoT devices access the shared *** survey examines the benefits and drawbacks of various spectrum-sharing technologies and their solutions for various IoT ***,it identifies future IoT obstacles and suggests potential research directions to address them.

关键词： Spectrum sharing IoT devices Security Privacy

Semantic segmentation via pixel-to-center similarity calculation

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

CAAI Transactions on Intelligence Technology 2024年第1期9卷 87-100页

作者： Dongyue Wu Zilin Guo Aoyan Li Changqian Yu Nong Sang Changxin Gao National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and AutomationHuazhong University of Science and TechnologyWuhanChina Meituan inc. BeijingChina

Sinc. the fully convolutional network has achieved great success in semantic segmentation,lots of works have been proposed to extract discriminative pixel ***,the authors observe that existing methods still suffer from two typical challenges:(i)The intra-class feature variation between different scenes may be large,leading to the difficulty in maintaining the consistency between same-class pixels from different scenes;(ii)The inter-class feature distinc.ion in the same scene could be small,resulting in the limited performance to distinguish different classes in each *** authors first rethink se-mantic segmentation from a perspective of similarity between pixels and class *** weight vector of the segmentation head represents its corresponding semantic class in the whole dataset,which can be regarded as the embedding of the class ***,the pixel-wise classification amounts to computing similarity in the final feature space between pixels and the class *** this novel view,the authors propose a Class Center Similarity(CCS)layer to address the above-mentioned challenges by generating adaptive class centers conditioned on each scenes and supervising the similarities between class *** CCS layer utilises the Adaptive Class Center Module to generate class centers conditioned on each scene,which adapt the large intra-class variation between different *** designed Class Distance Loss(CD Loss)is introduced to control both inter-class and intra-class distances based on the predicted center-to-center and pixel-to-center ***,the CCS layer outputs the processed pixel-to-center similarity as the segmentation *** experiments demonstrate that our model performs favourably against the state-of-the-art methods.

关键词： computer vision deep neural networks image segmentation scene understanding

Enhanced fatigue resistance of ferroelectric Al0.65Sc0.35N deposited by physical vapor deposition

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China(Information Sciences) 2024年第5期67卷 335-336页

作者： Yang LI Danyang YAO Yan LIU Zhi JIANG Ruiqing WANG Xu RAN Jiuren ZHOU Qikun WANG Guoqiang WU Genquan HAN School of Microelectronics Xidian University Hangzhou Institute of Technology Xidian University Ultratrend Technologies inc. Emerging Device and Chip Laboratory Institute of Technological Sciences Wuhan University

Aluminum scandium nitride(AlScN), a Ⅲ-Ⅴ ternary semiconductor, has been recognized as an innovative and promising ferroelectric material in emerging research. Among the characteristics of ferroelectric material, fatigue resistance is a critical measure of the endurance of ferroelectric films and represents an inherent challenge in the pursuit of practical applications.

关键词： Physical vapor deposition

Few-Shot Graph Classification with Structural-Enhanced Contrastive Learning for Graph Data Copyright Protection

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第2期29卷 605-616页

作者： Kainan Zhang DongMyung Shin Daehee Seo Zhipeng Cai Department of Computer Science Georgia State UniversityAtlantaGA 30303USA LSWare inc. Seoul 08504Republic of Korea College of Intelligence Information Engineering Sangmyung UniversitySeoul 03016Republic of Korea

Open-source licenses can promote the development of machine learning by allowing others to access,modify,and redistribute the training ***,not all open-source licenses may be appropriate for data sharing,as some may not provide adequate protections for sensitive or personal information such as social network ***,some data may be subject to legal or regulatory restrictions that limit its sharing,regardless of the licensing model ***,obtaining large amounts of labeled data can be difficult,time-consuming,or expensive in many real-world ***-shot graph classification,as one application of meta-learning in supervised graph learning,aims to classify unseen graph types by only using a small amount of labeled ***,the current graph neural network methods lack full usage of graph structures on molecular graphs and social network *** structural features are known to correlate with molecular properties in chemistry,structure information tends to be ignored with sufficient property information ***,the common binary classification task of chemical compounds is unsuitable in the few-shot setting requiring novel ***,this paper focuses on the graph classification tasks of a social network,whose complex topology has an uncertain relationship with its nodes'*** two multi-class graph datasets with large node-attribute dimensions constructed to facilitate the research,we propose a novel learning framework that integrates both meta-learning and contrastive learning to enhance the utilization of graph topological *** experiments demonstrate the competitive performance of our framework respective to other state-of-the-art methods.

关键词： few-shot learning contrastive learning data copyright protection

Lightweight Super-Resolution Model for Complete Model Copyright Protection

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Tsinghua Science and Technology 2024年第4期29卷 1194-1205页

作者： Bingyi Xie Honghui Xu YongJoon Joe Daehee Seo Zhipeng Cai Department of Computer Science Georgia State UniversityAtlantaGA 30303USA LSWare inc. Seoul 08504Republic of Korea College of Intelligence Information Engineering Sangmyung UniversityRepublic of KoreaSeoul 03016

Deep learning based techniques are broadly used in various applications, which exhibit superior performance compared to traditional methods. One of the mainstream topics in computer vision is the image super-resolution task. In recent deep learning neural networks, the number of parameters in each convolution layer has inc.eased along with more layers and feature maps, resulting in better image super-resolution performance. In today’s era, numerous service providers offer super-resolution services to users, providing them with remarkable convenience. However, the availability of open-source super-resolution services exposes service providers to the risk of copyright infringement, as the complete model could be vulnerable to leakage. Therefore, safeguarding the copyright of the complete model is a non-trivial concern. To tackle this issue, this paper presents a lightweight model as a substitute for the original complete model in image super-resolution. This research has identified smaller networks that can deliver impressive performance, while protecting the original model’s copyright. Finally, comprehensive experiments are conducted on multiple datasets to demonstrate the superiority of the proposed approach in generating super-resolution images even using lightweight neural networks.

关键词： lightweight adversarial learning image super-resolution copyright protection

A Survey of Multimodal Controllable Diffusion Models

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Computer Science & Technology 2024年第3期39卷 509-541页

作者：江锐郑光聪李藤杨天瑞王井东李玺 College of Computer Science and Technology Zhejiang UniversityHangzhou310007China Department of Mathematics Nanjing UniversityNanjing 210023China Baidu Visual Technology Department Baidu Inc.Beijing 100085China IEEE

Diffusion models have recently emerged as powerful generative models,producing high-fidelity samples across *** this,they have two key challenges,inc.uding improving the time-consuming iterative generation process and controlling and steering the generation *** surveys provide broad overviews of diffusion model ***,they lack comprehensive coverage specifically centered on techniques for controllable *** survey seeks to address this gap by providing a comprehensive and coherent review on controllable generation in diffusion *** provide a detailed taxonomy defining controlled generation for diffusion *** generation is categorized based on the formulation,methodologies,and evaluation *** enumerating the range of methods researchers have developed for enhanced control,we aim to establish controllable diffusion generation as a distinc. subfield warranting dedicated *** this survey,we contextualize recent results,provide the dedicated treatment of controllable diffusion model generation,and outline limitations and future *** demonstrate applicability,we highlight controllable diffusion techniques for major computer vision tasks *** consolidating methods and applications for controllable diffusion models,we hope to catalyze further innovations in reliable and scalable controllable generation.

关键词： diffusion model controllable generation application personalization

Hydrogen embrittlement of retrogression-reaged 7xxx-series aluminum alloys——a comprehensive review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Science China Materials 2024年第11期67卷 3468-3490页

作者： Mohamed Qassem Amir Ershad Fanaei Mousa Javidani Department of Applied Science University of Québec at Chicoutimi Canadian Materials Testing Bureau inc.

Hydrogen embrittlement remains a crucial concern in industries that rely on high-strength *** to hydrogen poses a significant threat to the mechanical integrity of such *** review article briefly discusses the fundamentals of hydrogen embrittlement,inc.uding its mechanisms and the effects of various factors,such as chemical composition and environmental *** heat treatments have been developed to eliminate the risk of hydrogen *** various suggested heat treatments,the retrogression-reaging(RRA) treatment has proven effective in optimizing the balance between mechanical properties and resistance to hydrogen *** review highlights the role of RRA treatment in modifying the microstructure of Al-Zn-Mg alloys to enhance their ability to resist hydrogen embrittlement,building on existing *** interesting aspect explored in this article is the intricate relationship between pre-deformation and subsequent RRA ***,the review discusses the use of RRA as a post-weld heat treatment to mitigate the susceptibility of weldments to hydrogen embrittlement.A comprehensive exploration of these topics is beneficial for a thorough understanding of the multifaceted functions of RRA ***,despite its advantages,the widespread adoption of RRA treatment in the industry is hindered by certain *** review addresses these challenges,offering insights into the latest strategies to overcome them.

关键词： retrogression-reaging treatment hydrogen embrittlement pre-deformation weldments

State of the art of lightweight aggregates used in lightweight refractories for working lining of high-temperature furnaces

同方期刊数据库评论

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2024年第6期31卷 1320-1343页

作者： Wei Zhang Wen-yong Dai Shenyang National Laboratory for Materials Science Institute of Metal ResearchChinese Academy of SciencesShenyang 110016LiaoningChina Research and Development Department AGC Plibrico(Dalian)Industries Inc.Dalian 116600LiaoningChina

Lightweight refractories for the working lining of high-temperature furnaces play an important role in the smelting of advanced steels and *** prepare lightweight refractories for the working lining of high-temperature furnaces,the synthesis of lightweight aggregates is the ***,the research on the synthesis of lightweight aggregates with high service temperature,low thermal conductivity,high strength,and good slag resistance has received widespread *** available literature on the synthesis of lightweight aggregates was summarized,inc.uding corundum,mullite,mullite-corundum,spinel,corundum-spinel,cordierite,cordierite-mullite,calcium hexaluminate,corundum-calcium hexaluminate,bauxite,magnesia,magnesia-based,and forsterite-based ***,the future development trend of lightweight aggregates was proposed.

关键词： Lightweight aggregate Lightweight refractory Working lining Apparent porosity Closed porosity Thermal conductivity Pore-forming approach

Advanced Electrical Motors and Control Strategies for High-quality Servo Systems-A Comprehensive Review

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Chinese Journal of Electrical Engineering 2024年第1期10卷 63-85页

作者： Ming Cheng Jiawei Zhou Wei Qian Bo Wang Chenchen Zhao Peng Han School of Electrical Engineering Southeast UniversityNanjing 210096China ESTUN Automation Co. Ltd.Nanjing 211106China Ansys Inc.San JoseCA 95134USA

Recent technological advancements have propelled remarkable progress in servo systems,resulting in their extensive utilization across various high-end applications.A comprehensive review of high-quality servo system technologies,focusing specifically on electrical motor topologies and control strategies is *** terms of motor topology,this study outlines the mainstream servo motors used across different periods,as well as the latest theories and technologies surrounding contemporary servo *** terms of control strategies,two well-established approaches are presented:field-oriented control and direct torque ***,it discusses advanced control strategies employed in servo systems,such as model predictive control(MPC)and fault tolerance control,among others.

关键词： Servo system servo motor control strategy magnetic field modulation

TextFormer: A Query-based End-to-end Text Spotter with Mixed Supervision

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Machine Intelligence Research 2024年第4期21卷 704-717页

作者： Yukun Zhai Xiaoqiang Zhang Xiameng Qin Sanyuan Zhao Xingping Dong Jianbing Shen School of Computer Science Beijing Institute of TechnologyBeijing 100081China Department of Computer Vision Technology Baidu Inc.Beijing 100193China

End-to-end text spotting is a vital computer vision task that aims to integrate scene text detection and recognition into a unified *** methods heavily rely on region-of-interest(Rol)operations to extract local features and complex post-processing steps to produce final *** address these limitations,we propose TextFormer,a query-based end-to-end text spotter with a transformer ***,using query embedding per text instance,TextFormer builds upon an image encoder and a text decoder to learn a joint semantic understanding for multitask *** allows for mutual training and optimization of classification,segmentation and recognition branches,resulting in deeper feature sharing without sacrificing flexibility or ***,we design an adaptive global aggregation(AGG)module to transfer global features into sequential features for reading arbitrarilyshaped texts,which overcomes the suboptimization problem of Rol ***,potential corpus information is utilized from weak annotations to full labels through mixed supervision,further improving text detection and end-to-end text spotting *** experiments on various bilingual(i.e.,English and Chinese)benchmarks demonstrate the superiority of our *** on the TDA-ReCTS dataset,TextFormer surpasses the state-of-the-art method in terms of 1-NED by 13.2%.

关键词： End-to-end text spotting arbitrarily-shaped texts transformer mixed supervision multitask modeling.