检索结果-内蒙古大学图书馆

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Jin Han Yuta Asano Boxin Shi Yinqiang Zheng Imari Sato Graduate School of Information Science and Technology The University of Tokyo National Institute of Informatics National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University

High-fidelity radiance recovery plays a crucial role in scene information reconstruction and understanding. Conventional cameras suffer from limited sensitivity in dynamic range, bit depth, and spectral response, etc. In this paper, we propose to use event cameras with bio-inspired silicon sensors, which are sensitive to radiance changes, to recover precise radiance values. We reveal that, under active lighting conditions, the transient frequency of event signals triggering linearly reflects the radiance value. We propose an innovative method to convert the high temporal resolution of event signals into precise radiance values. The precise radiance values yields several capabilities in image analysis. We demonstrate the feasibility of recovering radiance values solely from the transient event frequency (TEF) through multiple experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Room-scale magnetoquasistatic wireless power transfer using a cavity-based multimode resonator

arXiv

引用

arXiv 2025年

作者： Sasatani, Takuya Sample, Alanson P. Kawahara, Yoshihiro Department of Electrical Engineering and Information Systems Graduate School of Engineering The University of Tokyo Bunkyo-ku Tokyo Japan Electrical Engineering and Computer Science Department University of Michigan Ann ArborMI United States

Magnetoquasistatic wireless power transfer can be used to charge and power electronic devices such as smartphones and small home appliances. However, existing coil-based transmitters, which are composed of wire conductors, have a limited range. Here, we show that multimode-quasistatic cavity resonance can provide room-scale wireless power transfer. The approach uses multidirectional, widely distributed currents on conductive surfaces that are placed around the target volume. It generates multiple, mutually unique, three-dimensional magnetic field patterns, where each pattern is attributed to different eigenmodes of a single room scale resonator. Using these modes together, a power delivery efficiency exceeding 37.1% can be achieved throughout a 3 m × 3 m × 2 m test room. With this approach, power exceeding 50 W could potentially be delivered to mobile receivers, while in accordance with safety guidelines. Copyright © 2025, The Authors. All rights reserved.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

STFormer: Learning to Explore Spot Relationships for Spatial Transcriptomics Prediction from Histology of Colorectal Cancer

STFormer: Learning to Explore Spot Relationships for Spatial...

引用

Annual International Conference of the IEEE engineering in Medicine and Biology Society (EMBC)

作者： Gan Zhan Xiuju Du Jing Liu Yinhao Li Lanfen Lin Jingsong Li Yen-Wei Chen Graduate School of Information Science and Engineering Ritsumeikan University Shiga Japan Research Center for Healthcare Data Science Zhejiang Lab Hangzhou China College of Information Science and Engineering Ritsumeikan University Shiga Japan College of Computer Science and Technology Zhejiang University Hangzhou China

ISBN: (数字)9798350371499

ISBN: (纸本)9798350371505

Spatial transcriptomics (ST) offers insights into gene expression patterns within tumor microenvironments, but its widespread application is impeded by cost constraints. To address this, predicting ST from Histology emerges as a cost-effective alternative. However, current methods such as STNet, HistoGene, and Hist2ST exhibit limitations, either overlooking stain variation across datasets or failing to well explore inter-spot correlations in scenarios with limited Whole Slide Image (WSI) data. In response, we present STFormer, a deep learning approach that incorporates the Style-Aug module to enhance feature generalization through medically-irrelevant style transfer augmentation. Additionally, the Cross-WSI Transformer module is introduced to capture Cross-WSI spot relationships efficiently. Our experimental results, conducted on both internal and external datasets, demonstrate that STFormer surpasses existing methods by a substantial margin. This showcases its potential as a powerful tool for spatial transcriptomics predictions, addressing critical gaps in current methodologies.

关键词： Deep learning Costs Correlation Histopathology Transcriptomics Colorectal cancer Transformers Gene expression Tumors Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Determination of Giving 'Tips' Using Fuzzy Logic to Determine Restaurant Customer Service Satisfaction 3

Determination of Giving 'Tips' Using Fuzzy Logic to Determin...

引用

3rd International Conference on Computational science and information Management, ICoCSIM 2019

作者： Priyanto, Dadang Zarlis, Muhammad Anggrawan, Anthony Graduate Program of Computer Science Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Department of Computer Science Faculty of Computer Science and Information Technology Universitas Sumatera Utara Medan Indonesia Informatics Engineering Universitas Bumigora Mataram Indonesia

Fuzzy logic can be used to represent obscurity based on terms such as high, old, hot, cold, and so on. Fuzzy logic can extend the range of truth values to all real numbers in intervals between 0 and 1. Numbers in this interval represent the possibility that the statement given is "true"or "wrong". The use of fuzzy logic can be used in everyday life, such as in the fields of medicine, engineering, agriculture, transportation, environmental science and also in economic and business applications. As in this study, it was used to calculate the ideal amount of 'tips' for restaurant waiters based on the service provided by restaurant waiters. The method used in this study is to use Mamdani fuzzy logic with the process of defuzzyfication using the Centroid of area (COA). The results of this study are that it can be determined the value crisp of giving tips to restaurant waiters is 45 thousand rupiah provided that the service provided for service = 7 (Excellent) and food service = 8 (Delicious).. © Published under licence by IOP Publishing Ltd.

关键词： Fuzzy logic

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv4 Infrared Image Pedestrian Detection Algorithm 6th

Improved YOLOv4 Infrared Image Pedestrian Detection Algorith...

引用

6th EAI International Conference on Machine Learning and Intelligent Communications, MLICOM 2021

作者： Tao, Jin Shi, Jianting Chen, Yinan Wang, Jiancai Graduate College Heilongjiang University of Science and Technology Harbin150022 China School of Computer and Information Engineering Heilongjiang University of Science and Technology Harbin150022 China Academic Affairs Office Heilongjiang University of Science and Technology Harbin150022 China

ISBN: (纸本)9783031044083

Because pedestrians are always in the active state, each target is at a different distance from the camera, resulting in a certain difference in the size of similar targets in the figure. Therefore, an infrared pedestrian detection algorithm is proposed in the paper based on Yolov4 algorithm. Aiming at the problems of low recognition rate and high background influence in infrared image downlink human small target detection, the network structure of YOLOv4 is optimized. Compared with YOLOv4 and YOLOv3, the mean Average Precision is improved by 0.53% and 1.05%, which improves the detection accuracy in a certain extent. © 2022, ICST Institute for computer sciences, Social Informatics and Telecommunications engineering.

关键词： Infrared imaging

来源：评论

学校读者我要写书评

暂无评论

Learning Event Guided High Dynamic Range Video Reconstruction

Learning Event Guided High Dynamic Range Video Reconstructio...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yixin Yang Jin Han Jinxiu Liang Imari Sato Boxin Shi National Key Laboratory for Multimedia Information Processing School of Computer Science Peking University National Engineering Research Center of Visual Technology School of Computer Science Peking University Graduate School of Information Science and Technology The University of Tokyo National Institute of Informatics

Limited by the trade-off between frame rate and exposure time when capturing moving scenes with conventional cameras, frame based HDR video reconstruction suffers from scene-dependent exposure ratio balancing and ghosting artifacts. Event cameras provide an alternative visual representation with a much higher dynamic range and temporal resolution free from the above issues, which could be an effective guidance for HDR imaging from LDR videos. In this paper, we propose a multimodal learning framework for event guided HDR video reconstruction. In order to better leverage the knowledge of the same scene from the two modalities of visual signals, a multimodal representation alignment strategy to learn a shared latent space and a fusion module tailored to complementing two types of signals for different dynamic ranges in different regions are proposed. Temporal correlations are utilized recurrently to suppress the flickering effects in the reconstructed HDR video. The proposed HDRev-Net demonstrates state-of-the-art performance quantitatively and qualitatively for both synthetic and real-world data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Natural Text-Driven, Multi-Attribute Editing of Facial Images with Robustness in Sparse Latent Space

Natural Text-Driven, Multi-Attribute Editing of Facial Image...

引用

Communications Technology and computer science (ACCTCS), Asia-Pacific Conference on

作者： Jianpeng Zou Kaoru Uchida Wenxin Yao Kashing Yuen Graduate School of Computer and Information Sciences Hosei University Tokyo Japan School of Software Engineering University of Science and Technology of China Hefei China

This study presents a novel text-driven method for the editing of portraits with robustness in a sparse latent space. Due to the development of GAN and the proposal of many excellent models like StyleGAN, text-driven image editing and image generation have made great progress in recent years, but the task of generating facial images under the guidance of text is still lacking in some special situations. Our model combines and makes good use of two pre-training models, CLIP2Latent and StyleGAN2, to conduct a preliminary exploration of the above task. The latent code of the input portrait is driven to be edited and manipulated in the StyleGAN latent space via a CLIP-based text-driven generation module. Finally, some promising results have been obtained, especially in the sparse region of the generator latent space and when simultaneously changing numerous attributes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

IEEE International Conference on Consumer Electronics (ICCE)

作者： Tong Liu Dongyang Xu Tiantian Zhang Shilong Zhang Jinhua Chen Keping Yu Victor C. M. Leung Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798331521165

ISBN: (纸本)9798331521172

The accelerated development of the Industrial Internet of Things (IoT) has significantly enhanced the computational efficiency and processing capabilities of Wireless Consumer Application Networks (WCAN). Despite these advancements, the performance of WCAN remains constrained by the inherent limitations in computational capacity and energy resources of wireless devices. To address these issues, this paper proposes a wireless powered-mobile edge computing system with Reconfigurable Intelligent Surface (RIS) assistance for WCAN, where wireless consumer devices can not only harvest energy from access point, but also offload computing tasks to edge server with the help of RIS. Aiming to maximize the system computation rate, a non-convex problem is developed and a block optimization with deep reinforcement learning (BO-DRL) scheme is proposed. First, the RIS phase shifts in the Wireless Power Transfer (WPT) stage and offloading stage are optimized using closed-form solutions and the gradient ascent algorithm, respectively. Subsequently, the offloading strategies are optimized using deep reinforcement learning, and a convex optimization algorithm is employed to obtain the time allocation for the WPT and offloading stages. Numerical results illustrate that the BO-DRL algorithm greatly enhances computation rate by 20% compared to without RIS.

关键词： Wireless communication Training Performance evaluation Wireless power transfer Reconfigurable intelligent surfaces Deep reinforcement learning Convex functions Resource management Servers Uplink

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning-Based Computation Rate Maximization for RIS-Aided Edge Computing in Wireless Consumer Application Networks

Deep Reinforcement Learning-Based Computation Rate Maximizat...

引用

2025 IEEE International Conference on Consumer Electronics, ICCE 2025

作者： Liu, Tong Xu, Dongyang Zhang, Tiantian Zhang, Shilong Chen, Jinhua Yu, Keping Leung, Victor C.M. Graduate School of Science and Engineering Hosei University Japan School of Information and Communications Engineering Xi'an Jiaotong University China Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Computer Science and Software Engineering Shenzhen University China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (纸本)9798331521165

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced adaptive data rate strategies for energy-efficient Internet of Things communication in LoRaWAN

引用

International Journal of Communication Systems 2025年第2期38卷

作者： Ali Lodhi, Muhammad Wang, Lei Mahmood, Khalid Farhad, Arshad Chen, Jenhui Kumari, Saru School of Software Technology Dalian University of Technology Dalian China Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Douliu Taiwan Department of Computer Science FAST-National University of Computer and Emerging Sciences Islamabad Pakistan Department of Computer Science and Information Engineering Chang Gung University Taoyuan Taiwan Department of Mathematics Chaudhary Charan Singh University Meerut India School of Chemical Engineering and Physical Sciences Lovely Professional University Jalandhar India

The long-range wide area network (LoRaWAN) is a standard for the Internet of Things (IoT) because it has low cost, long range, not energy-intensive, and capable of supporting massive end devices (EDs). The adaptive data rate (ADR) adjusts parameters at both EDs and the network server (NS). This includes modifying the transmission spreading factor (SF) and transmit power (TP) to minimize packet errors and optimize transmission performance at the NS. The ADR managed by NS aims to provide reliable and energy-efficient resources (e.g., SF and TP) to EDs by monitoring the packets received from the EDs. However, since the channel condition changes rapidly in LoRaWAN due to mobility, the existing ADR algorithm is unsuitable and results in a significant amount of packet loss and retransmissions causing an increase in energy consumption. In this paper, we enhance the ADR by introducing Kalman filter-based ADR (KF-ADR) and moving median-based ADR (Median-ADR), which estimate the optimal SNR by considering the mobility later used to assign the SF and TP to EDs. The simulation results showed that the proposed techniques outperform the legacy ADRs in terms of convergence period, energy consumption, and packet success ratio. © 2024 John Wiley & Sons Ltd.

关键词： adaptive data rate Internet of Things Kalman filter LoRa LoRaWAN mobility resource allocation

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：