检索结果-内蒙古大学图书馆

32nd ACM International Conference on Multimedia, MM 2024

作者： Li, Zejun Wang, Ye Du, Mengfei Liu, Qingwen Wu, Binhao Zhang, Jiwen Zhou, Chengxing Fan, Zhihao Fu, Jie Chen, Jingjing Wei, Zhongyu Huang, Xuanjing School of Data Science Fudan University Shanghai China Academy for Engineering and Technology Fudan University Shanghai China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China Software College Northeastern University Liaoning Shenyang China Alibaba Group Zhejiang Hangzhou China Department of Computer Science and Engineering Hong Kong University of Science and Technology Hong Kong School of Computer Science Fudan University Shanghai China

ISBN: (纸本)9798400706868

Recent years have witnessed remarkable progress in the development of large vision-language models (LVLMs). Benefiting from the strong language backbones and efficient cross-modal alignment strategies, LVLMs exhibit surprising capabilities to perceive visual signals and perform visually grounded reasoning. However, the capabilities of LVLMs have not been comprehensively and quantitatively evaluated. Most existing multi-modal benchmarks require task-oriented input-output formats, posing great challenges to automatically assess the free-form text output of LVLMs. To effectively leverage the annotations available and reduce the manual efforts required for constructing new benchmarks, we propose to re-formulate existing benchmarks into unified LVLM-compatible formats. Through systematic data collection and reformulation, we present ReForm-Eval benchmark, offering substantial data for evaluating various capabilities of LVLMs. Through extensive experiments and analysis in ReForm-Eval, we demonstrate the comprehensiveness and reliability of ReForm-Eval in assessing various LVLMs. Our benchmark and evaluation framework is now available at https://***/FudanDISC/ReForm-Eval © 2024 ACM.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

FBI-Net: Frequency Band Integration Network for Infrared Small Target Segmentation

FBI-Net: Frequency Band Integration Network for Infrared Sma...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Biqiao Xin Qiang Li Qianchen Mao Jinbao Wang Bingshu Wang School of Software Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Small targets in infrared imagery exhibit challenging characteristics due to their minimal semantic information and the extremely imbalanced distribution between the targets and the background. In this paper, we propose a frequency band integration network to extract salient features of infrared small targets in both the spatial and frequency domains. To excavate the high-frequency features of the small targets, we propose a frequency decoupling-fusion module. To decrease the semantic loss that occurs in deep networks, we propose a semantic injection mechanism to assist in retaining critical information from shallow layers. Experimental results show that our proposed method reaches higher prediction accuracy and robustness in the infrared small target segmentation task compared with other state-of-the-art approaches.

关键词： Wavelet transforms Frequency-domain analysis Semantics Signal processing Feature extraction Excavation Robustness Real-time systems Complexity theory Speech processing

来源：评论

学校读者我要写书评

暂无评论

Multi-tenant, Decentralized Access Control for the Internet of Things

Multi-tenant, Decentralized Access Control for the Internet ...

引用

2023 IEEE International Conference on Internet of Things and Intelligence Systems, IoTaIS 2023

作者： Pittaras, Iakovos Polyzos, George C. School of Information Sciences and Technology Athens University of Economics and Business Mobile Multimedia Laboratory Department of Informatics Greece School of Data Science CUHK Shenzhen China Mobile Multimedia Laboratory AUEB Athens Greece

ISBN: (纸本)9798350319040

The Internet of Things (IoT) involves diverse devices exchanging data and impacting the real world through actuators, often unattended. IoT data and actuation are accessed by many and diverse stakeholders, emphasizing the need for security and privacy and in particular for effective, efficient, usable, and fine-grained access control solutions. Unfortunately, most of the conventional access control approaches have been proven inefficient or ineffective for the IoT. Novel access control mechanisms have been designed, specifically for the IoT, with some of them taking advantage of Distributed Ledger Technologies (DLTs). DLTs and smart contracts provide increased availability, automation, transparency, and decentralization. Here, we first review the related literature and then we develop IoT access control requirements and solutions. We argue that DLT-based access control systems can address the key requirements for the IoT and we validate this claim by designing a realistic access control solution for a smart city use case. © 2023 IEEE.

关键词： Authorization

来源：评论

学校读者我要写书评

暂无评论

Eliminating Control Plane Overload via Measurement Task Placement

Eliminating Control Plane Overload via Measurement Task Plac...

引用

作者： Chen, Xiang Liu, Hongyan Zhang, Dong Huang, Qun Zhou, Haifeng Wu, Chunming Yang, Qiang College of Computer Science and Technology Zhejiang University Hangzhou310007 China College of Computer Science and Big Data Fuzhou University Fuzhou350116 China School of Electronics Engineering and Computer Science Peking University Beijing100871 China College of Control Science and Engineering Zhejiang University Hangzhou310007 China College of Electrical Engineering Zhejiang University Hangzhou310007 China

Recent efforts in network measurement place measurement tasks on programmable switches to measure high-speed traffic. These tasks extract flow data, i.e., events, from packets and send events to the control plane. However, the tasks may generate massive events in a short time. In this context, the links transferring events to the control plane and the control plane servers that handle events may be overloaded, i.e., control plane overload. None of existing solutions can eliminate control plane overload. In this paper, we propose MTP, a framework that eliminates control plane overload via careful measurement task placement. Our key idea is to allocate enough resources for each task during task placement to avoid control plane overload at runtime. For each task, MTP estimates its maximum possible rate of sending events to the control plane. Then its optimization framework addresses the resource restrictions of both switches and the control plane. The experiments on Tofino switches indicate that MTP outperforms existing solutions with higher accuracy in several use cases. © 2022 IEEE.

关键词： Job analysis

来源：评论

学校读者我要写书评

暂无评论

Two distributed singleton formation avoidance strategies for noncooperative target fencing

Two distributed singleton formation avoidance strategies for...

引用

Youth Academic Annual Conference of Chinese Association of Automation (YAC)

作者： Cheng Liu Fan Zhang Xueyang Liao Zezhou Zhang School of Aeronautics and Astronautics Sun Yat-sen University Shenzhen China Institute of G&C Luoyang China School of Mathematics and Big Data Anhui University of Science and Technology Huainan China

ISBN: (数字)9798350379228

ISBN: (纸本)9798350390780

The cooperative fencing control problem has been extensively studied mainly in the context of multiple pursuers, also called agents, and one single evader usually called the target. The most popular scenario in the literature is, that the pursuers move in a circular formation to encircle and track the target. The requirement of the circular formation imposes a heavy burden on the distributed coordination among the pursuers. Fortunately, a novel cooperative fencing control framework proposed in [1] only drives the pursuers to form an arbitrary convex hull that could change over time. However, this cooperative fencing control framework also has a drawback in that, the collinear singleton formation could happen and result in ineffective fencing. In [1], a centralized singleton formation avoidance strategy requires that the target information is known to all pursuers. Besides, it fails in more complex settings, for example, the noncooperative target case. By means of a novel rotational term, this paper improves the singleton formation avoidance strategy in [1]. First, we trim the original rotational term and drive only two pursuers to break the singleton formation. Meanwhile, we use only distances between neighboring pursuers to impose additional restrictions on the collision avoidance function, which turns out to be fully distributed. Moreover, the target studied here is noncooperative under a bounded unknown velocity input. The novel strategies together with the nonsmooth cooperative fencing control algorithm are supported by rigorous theoretical analysis. Numerical simulations are conducted to demonstrate the effectiveness of our novel design.

关键词： Target tracking Automation Numerical simulation Vectors Task analysis Collision avoidance Convergence

来源：评论

学校读者我要写书评

暂无评论

A survey on lung CT datasets and research trends

引用

Research on Biomedical Engineering 2021年第2期37卷 403-418页

作者： Adiraju, Rama Vasantha Elias, Susan School of Electronics Engineering Vellore Institute of Technology Chennai India Centre for Advanced Data Science Vellore Institute of Technology Chennai India

Purpose: Lung cancer is the most dangerous of all forms of cancer and it has the highest occurrence rate, world over. Early detection of lung cancer is a difficult task. Medical images generated by computer tomography (CT) are being used extensively for lung cancer analysis and research. However, it is essential to have a well-organized image database in order to design a reliable computer-aided diagnosis (CAD) tool. Identifying the most appropriate dataset for the research is another big challenge. Literarture review: The objective of this paper is to present a review of literature related to lung CT datasets. The Cancer Imaging Archive (TCIA) consortium collates different types of cancer datasets and permits public access through an integrated search engine. This survey summarizes the research work done using lung CT datasets maintained by TCIA. The motivation to present this survey was to help the research community in selecting the right lung dataset and to provide a comprehensive summary of the research developments in the field. © 2021, Sociedade Brasileira de Engenharia Biomedica.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

An ADRC-Incorporated Stochastic Gradient Descent Algorithm for Latent Factor Analysis

arXiv

引用

arXiv 2024年

作者： Li, Jinli Yuan, Ye The School of Computer Science and Technology Chongqing University of Posts and Telecommunications Chongqing400065 China The Chongqing Key Laboratory of Big Data and Intelligent Computing Chongqing Engineering Research Center of Big Data Application for Smart Cities Chongqing Institute of Green and Intelligent Technology Chinese Academy of Sciences Chongqing400714 China The College of Computer and Information Science Southwest University Chongqing400715 China

High-dimensional and incomplete (HDI) matrix contains many complex interactions between numerous nodes. A stochastic gradient descent (SGD)-based latent factor analysis (LFA) model is remarkably effective in extracting valuable information from an HDI matrix. However, such a model commonly encounters the problem of slow convergence because a standard SGD algorithm only considers the current learning error to compute the stochastic gradient without considering the historical and future state of the learning error. To address this critical issue, this paper innovatively proposes an ADRC-incorporated SGD (ADS) algorithm by refining the instance learning error by considering the historical and future state by following the principle of an ADRC controller. With it, an ADS-based LFA model is further achieved for fast and accurate latent factor analysis on an HDI matrix. Empirical studies on two HDI datasets demonstrate that the proposed model outperforms the state-of-the-art LFA models in terms of computational efficiency and accuracy for predicting the missing data of an HDI matrix. Copyright © 2024, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Production and test of sPHENIX W/SciFiber electromagnetic calorimeter blocks in China

引用

Nuclear science and Techniques 2024年第8期35卷 167-176页

作者： Xiao‑Zhou Yu Xi‑Yang Wang Wei‑Hu Ma Shi‑Hong Fu Peng‑Fei Sun Jin‑Xing Song Wan‑Bing He Yang Shen Long Ma Jin‑Hui Chen Huan‑Zhong Huang Si‑Guang Wang Jing Zhou Xiao‑Mei Li Institute of Modern Physics Fudan UniversityShanghai 200433China Key Laboratory of Nuclear Physics and Ion‑Beam Application(MOE) Fudan UniversityShanghai 200433China Science and Technology on Nuclear Data Laboratory China Institute of Atomic EnergyBeijing 102413China Department of Physics and Astronomy University of CaliforniaLos AngelesCA 90095USA State Key Laboratory of Nuclear Physics and Technology School of PhysicsPeking UniversityBeijing 100871China

The sPHENIX experiment is a new generation of large acceptance detectors at the relativistic heavy ion collider at Brookhaven National Laboratory,with scientific goals focusing on probing the strongly interacting Quark–Gluon plasma with hard probes of jets,open heavy flavor particles,andγ*** EMCal detector,which covers the pseudo-rapidity region of|η|≤1.1,is an essential subsystem of *** this study,we focused on producing and testing EMCal blocks covering a pseudo-rapidity of|η|∈[0.8,1.1].These,in conjunction with the central pseudo-rapidity EMCal blocks,significantly enhance the sPHENIX physics capability of the jet andγparticle *** this paper,the detector module production and testing of sPHENIX W-powder/scintillating fiber(W/ScFi)electromagnetic calorimeter blocks are *** selection of the tungsten powder,mold fabrication,QA procedures,and cosmic ray test results are discussed.

关键词： sPHENIX Tungsten/scintillating fiber electromagnetic calorimeter Cosmic ray test

来源：评论

学校读者我要写书评

暂无评论

Lightweight Human Pose Estimation Based on Multi-Attention Mechanism

引用

Journal of Shanghai Jiaotong University (science) 2024年 1-12页

作者： Lin, Xiao Lu, Meichen Gao, Mufeng Li, Yan Institute of Artificial Intelligence on Education Research College of Information Mechanical and Electrical Engineering Shanghai Normal University Shanghai200234 China Shanghai Intelligent Education Big Data Engineering Technology Research Center Shanghai Normal University Shanghai200234 China Shanghai Online Education Research Base for Primary and Secondary Schools Shanghai200234 China School of Physical Education Shanghai Normal University Shanghai200234 China

Human pose estimation has received much attention from the research community because of its wide range of applications. However, current research for pose estimation is usually complex and computationally intensive, especially the feature loss problems in the feature fusion process. To address the above problems, we propose a lightweight human pose estimation network based on multi-attention mechanism (LMANet). In our method, network parameters can be significantly reduced by lightweighting the bottleneck blocks with depth-wise separable convolution on the high-resolution networks. After that, we also introduce a multi-attention mechanism to improve the model prediction accuracy, and the channel attention module is added in the initial stage of the network to enhance the local cross-channel information interaction. More importantly, we inject spatial cross-awareness module in the multi-scale feature fusion stage to reduce the spatial information loss during feature extraction. Extensive experiments on COCO2017 dataset and MPII dataset show that LMANet can guarantee a higher prediction accuracy with fewer network parameters and computational effort. Compared with the high-resolution network HRNet, the number of parameters and the computational complexity of the network are reduced by 67% and 73%, respectively. © 2023, Shanghai Jiao Tong University.

关键词： Complex networks

来源：评论

学校读者我要写书评

暂无评论

Source Code Summarization in the Era of Large Language Models

arXiv

引用

arXiv 2024年

作者： Sun, Weisong Miao, Yun Li, Yuekang Zhang, Hongyu Fang, Chunrong Liu, Yi Deng, Gelei Liu, Yang Chen, Zhenyu State Key Laboratory for Novel Software Technology Nanjing University Nanjing China College of Computing and Data Science Nanyang Technological University Singapore Singapore School of Computer Science and Engineering University of New South Wales Sidney Australia School of Big Data and Software Engineering Chongqing University Chongqing China

To support software developers in understanding and maintaining programs, various automatic (source) code summarization techniques have been proposed to generate a concise natural language summary (i.e., comment) for a given code snippet. Recently, the emergence of large language models (LLMs) has led to a great boost in the performance of code-related tasks. In this paper, we undertake a systematic and comprehensive study on code summarization in the era of LLMs, which covers multiple aspects involved in the workflow of LLM-based code summarization. Specifically, we begin by examining prevalent automated evaluation methods for assessing the quality of summaries generated by LLMs and find that the results of the GPT-4 evaluation method are most closely aligned with human evaluation. Then, we explore the effectiveness of five prompting techniques (zero-shot, few-shot, chain-of-thought, critique, and expert) in adapting LLMs to code summarization tasks. Contrary to expectations, advanced prompting techniques may not outperform simple zero-shot prompting. Next, we investigate the impact of LLMs’ model settings (including top_p and temperature parameters) on the quality of generated summaries. We find the impact of the two parameters on summary quality varies by the base LLM and programming language, but their impacts are similar. Moreover, we canvass LLMs’ abilities to summarize code snippets in distinct types of programming languages. The results reveal that LLMs perform suboptimally when summarizing code written in logic programming languages compared to other language types (e.g., procedural and object-oriented programming languages). Finally, we unexpectedly find that CodeLlama-Instruct with 7B parameters can outperform advanced GPT-4 in generating summaries describing code implementation details and asserting code properties. We hope that our findings can provide a comprehensive understanding of code summarization in the era of *** Codes 68-04 Copyright © 202

关键词： Quality control

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：