检索结果-内蒙古大学图书馆

35th IEEE International Symposium on Personal, Indoor and Mobile Radio Communications, PIMRC 2024

作者： Yu, Zhiyong Cheng, Hei Victor Yang, Zhanpeng Liu, Xin Jiang, Yuning Zhou, Yong Shi, Yuanming ShanghaiTech University School of Information Science and Technology Shanghai201210 China Aarhus University Department of Electrical and Computer Engineering Denmark Automatic Control Laboratory Switzerland

ISBN: (纸本)9798350362244

Artificial intelligence (AI) is critical in evolving 5G and developing 6G networks, running on edge devices, and solving resource management challenges. The burgeoning number of edge devices draws attention to the potential of low-earth orbit (LEO) satellite networks with their onboard computing capabilities for edge inference. This paper explores LEO scenarios where multiple remote sensing edge AI inference tasks concurrently process data from a single source. However, due to there being parts with the same functions between different AI applications, traditional monolithic edge AI architecture must be deployed repeatedly and falls short in efficiently harnessing the heterogeneous resources of LEO satellite networks. To solve this problem, we utilize the microservice architecture to decouple a single AI application into several independent microservices to reuse these same functions. However, due to the high latency caused by multiple microservices' communication, we need to design a deployment strategy to fully utilize resources to reduce the service latency. We present a microservice deployment model to minimize the total service latency across all AI applications and meet resource constraints with the constraints of hardware, energy, and memory limitations. This latency optimization problem is rewritten as a Markov decision process (MDP) to effectively deal with the challenge posed by the time-varying transmission rate caused by satellite mobility. To increase the training data utilization, we employ a Proximal Policy Optimization (PPO) based reinforcement learning algorithm to meet the dynamic environment challenge. Finally, we obtain a sub-optimal solution with minimal accuracy loss and an acceptable solution time. © 2024 IEEE.

关键词： Markov processes

来源：评论

学校读者我要写书评

暂无评论

One Drop Filling (ODF) for High-Viscosity Liquid Crystal

One Drop Filling (ODF) for High-Viscosity Liquid Crystal

引用

International Symposium, Seminar, and Exhibition, Display Week 2024

作者： Huo, Yi-Peng Yuan, Zheng-Nan Sun, Zhi-Bo Tseng, Man-Chun Vashchenko, Valerii Vashchenko, Olena Srivastava, Abhishek Kumar Ho, Jacob Kwok, Hoi-Sing State Key Laboratory of Advanced Displays and Optoelectronics Technology Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Clear Water Bay Hong Kong

A new ODF machine for high-viscosity liquid crystals (LCs) is successfully constructed and tested using ferroelectric liquid crystals (FLCs). Innovatively, heating over 100°C, filling FLC in a vacuum, and sealing can automatically be done in one reaction pot. No glue leakage exists in the FLC samples. Good alignment without defect and electro-optic (EO) performance are achieved. The response time is 33 μs, and relaxation time is 27 μs. Contrast Ratio (CR)=10000:1 (@ 632 nm). This is one of the critical steps towards the commercialization of FLC-based displays and optoelectronic devices. © 2024, John Wiley and Sons Inc. All rights reserved.

关键词： Glues

来源：评论

学校读者我要写书评

暂无评论

CONTINUOUS-TIME IDENTIFICATION OF DYNAMIC STATE-SPACE MODELS BY DEEP SUBSPACE ENCODING 11

CONTINUOUS-TIME IDENTIFICATION OF DYNAMIC STATE-SPACE MODELS...

引用

11th International Conference on Learning Representations, ICLR 2023

作者： Beintema, Gerben I. Schoukens, Maarten Tóth, Roland Department of Electrical Engineering Eindhoven University of Technology Netherlands Systems and Control Laboratory Institute for Computer Science and Control Budapest Hungary

Continuous-time (CT) modeling has proven to provide improved sample efficiency and interpretability in learning the dynamical behavior of physical systems compared to discrete-time (DT) models. However, even with numerous recent developments, the CT nonlinear state-space (NL-SS) model identification problem remains to be solved in full, considering common experimental aspects such as the presence of external inputs, measurement noise, latent states, and general robustness. This paper presents a novel estimation method that addresses all these aspects and that can obtain state-of-the-art results on multiple benchmarks with compact fully connected neural networks capturing the CT dynamics. The proposed estimation method called the subspace encoder approach (SUBNET) ascertains these results by efficiently approximating the complete simulation loss by evaluating short simulations on subsections of the data, by using an encoder function to estimate the initial state for each subsection and a novel state-derivative normalization to ensure stability and good numerical conditioning of the training process. We prove that the use of subsections increases cost function smoothness together with the necessary requirements for the existence of the encoder function and we show that the proposed state-derivative normalization is essential for reliable estimation of CT NL-SS models. © 2023 11th International Conference on Learning Representations, ICLR 2023. All rights reserved.

关键词： Cost functions

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity Document Stain Removal via A Large-Scale Real-World Dataset and A Memory-Augmented Transformer

High-Fidelity Document Stain Removal via A Large-Scale Real-...

引用

2025 IEEE/CVF Winter Conference on Applications of computer Vision, WACV 2025

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

ISBN: (纸本)9798331510831

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. © 2025 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimize the One Drop Filling (ODF) operation process for Ferroelectric Liquid Crystal

Optimize the One Drop Filling (ODF) operation process for Fe...

引用

International Conference on Display Technology, 2024

Optimized ODF machine for large scale display filled by ferroelectric liquid crystals (FLCs) is developed. Fast FLC filling at high temperature (100°C) in the vacuum, and sealing can automatically be done in one reaction pot. An uniform cell with good alignment quality and electro-optical (E&O) performance are achieved which shows high contrast ratio (CR) =10000:1 and a fast response time (33 μs) at room temperature, respectively. The realized FLC cell by ODF indicates that there are no mass production barriers for large scale FLC display. © 2024 John Wiley and Sons Inc. All rights reserved.

关键词： Drops

来源：评论

学校读者我要写书评

暂无评论

Photonic Indistinguishability of the Tin-Vacancy Center in Diamond

Photonic Indistinguishability of the Tin-Vacancy Center in D...

引用

2023 Conference on Lasers and Electro-Optics, CLEO 2023

作者： Arjona, Jesús Parker, Ryan Chen, Kevin Purser, Carola Li, Linsen Michaels, Cathryn Stramma, Alexander Debroux, Remain Harris, Isaac Hayhurst, Martin Nichols, Eleanor Trusheim, Matthew Gangloff, Dorian Englund, Dirk Atature, Mete Cavendish Laboratory University of Cambridge Cambridge United Kingdom Department of Electrical Engineering and Computer Science MIT Cambridge United States

Tin-vacancy centres in diamond are spin-photon interfaces with intrinsic environmental noise insensitivity. We reveal their high optical coherence in a nanostructured environment and generate single photons with a 99.... 详细信息

ISBN: (纸本)9781957171258

关键词： Photons

来源：评论

学校读者我要写书评

暂无评论

DPT‐tracker:Dual pooling transformer for efficient visual tracking

引用

CAAI Transactions on Intelligence Technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Spatio-temporal Attention Graph Convolutions for Skeleton-based Action Recognition 23rd

Spatio-temporal Attention Graph Convolutions for Skeleton-b...

引用

22nd Scandinavian Conference on Image Analysis, SCIA 2023

作者： Le, Cuong Liu, Xin Computer Vision and Pattern Recognition Laboratory School of Engineering Science Lappeenranta-Lahti University of Technology LUT Lappeenranta Finland Computer Vision Laboratory Department of Electrical Engineering Linköping University Linköping Sweden

ISBN: (纸本)9783031314346

In skeleton-based action recognition, graph convolutional networks (GCN) have been applied to extract features based on the dynamic of the human body and the method has achieved excellent results recently. However, GCN-based techniques only focus on the spatial correlations between human joints and often overlook the temporal relationships. In an action sequence, the consecutive frames in a neighborhood contain similar poses and using only temporal convolutions for extracting local features limits the flow of useful information into the calculations. In many cases, the discriminative features can present in long-range time steps and it is important to also consider them in the calculations to create stronger representations. We propose an attentional graph convolutional network, which adapts self-attention mechanisms to respectively model the correlations between human joints and between every time steps for skeleton-based action recognition. On two common datasets, the NTU-RGB+D60 and the NTU-RGB+D120, the proposed method achieved competitive classification results compared to state-of-the-art methods. The project’s GitHub page: STA-GCN. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Guest Editorial: Special Issue on Human-Machine Fusion Decision-Making for Emergency Handling

引用

IEEE Transactions on Automation science and engineering 2025年 22卷 4427-4433页

作者： Wu, Edmond Q. Li, Jianqiang Chen, Guimin Yuce, Mehmet R. Islam, Shafiqul Ser, Javier Del Yu, Hui Liu, Peter Xiaoping Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai200240 China College of Computer and Software Engineering Shenzhen University Shenzhen518060 China State Key Laboratory for Manufacturing Xi'an Jiaotong University Xi'an710049 China Department of Electrical and Computer Systems Engineering Monash University MelbourneVIC3800 Australia Xavier University of Louisiana New OrleansLA70125 United States Tecnalia Institute Bizkaia48160 Spain School of Creative Technologies University of Portsmouth PortsmouthPO1 2UP United Kingdom Department of Systems and Computer Engineering Carleton University OttawaONKIS 5B6 Canada

来源：评论

学校读者我要写书评

暂无评论

Predictive modeling of MXene-based solar absorbers using a deep neural network

引用

Journal of the Optical Society of America B: Optical Physics 2025年第4期42卷 763-772页

作者： Waseer, Waleed Iqbal Baqir, Muhammad Abuzar Saqlain, Muhammad Mughal, Muhammad Junaid Khan, Shujaat School of Physics State Key Laboratory of Electronic Thin Films and Integrated Devices University of Electronic Science and Technology of China Chengdu China Department of Electrical Engineering COMSATS University Islamabad Sahiwal57000 Pakistan Department of Electrical and Computer Engineering COMSATS University Islamabad Islamabad45550 Pakistan Department of Computer Engineering College of Computing and Mathematics King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia SDAIA-KFUPM Joint Research Center for Artificial Intelligence King Fahd University of Petroleum & Minerals Dhahran31261 Saudi Arabia

Nanophotonic structures, such as photonic crystals, plasmonic nanostructures, and metamaterials, present transformative potential in advancing optical devices through innovative design capabilities. Among these, metamaterials—specifically metal–insulator–metal (MIM)-based absorbers—stand out for their ability to achieve high electromagnetic wave absorption across designated frequencies, proving valuable in applications ranging from solar cells to sensors. This study focuses on designing a high-efficiency MXene–SiO2–silver MIM metasurface absorber, leveraging deep learning techniques to streamline and enhance the simulation process traditionally reliant on finite-difference time-domain (FDTD) or finite-element methods (FEMs). By utilizing a deformable convolutional neural network (CNN), the proposed model predicts absorption spectra from metasurface geometries with superior accuracy and reduced computational demand while achieving dynamic spatial transformation handling. The model’s accuracy is further elucidated through Gradient-weighted Class Activation Mapping (Grad-CAM), which provides insights into the absorber’s most influential regions, supporting targeted optimization for specific applications. This deep learning approach demonstrates significant advantages over conventional methods in efficiency and adaptability, advancing the development of high-performance nanophotonic devices. © 2025 Optica Publishing Group. All rights, including for text and data mining (TDM), Artificial Intelligence (AI) training, and similar technologies, are reserved.

关键词： Time domain analysis

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：