检索结果-内蒙古大学图书馆

S$^\text{3}$Attention: Improving Long Sequence Attention With Smoothed Skeleton Sketching

IEEE Journal of Selected Topics in Signal Processing 2024年第6期18卷 985-996页

作者： Xue Wang Tian Zhou Jianqing Zhu Jialin Liu Kun Yuan Tao Yao Wotao Yin Rong Jin HanQin Cai Alibaba Group Bellevue WA USA Computer Electrical and Mathematical Science and Engineering Division King Abdullah University of Science and Technology Thuwal Saudi Arabia Department of Statistics and Data Science University of Central Florida Orlando FL USA Center for Machine Learning Research Peking University Beijing China Antai College of Economics and Management Shanghai Jiao Tong University Shanghai China Meta Menlo Park CA USA Department of Statistics and Data Science and the Department of Computer Science University of Central Florida Orlando FL USA

Attention based models have achieved many remarkable breakthroughs in numerous applications. However, the quadratic complexity of Attention makes the vanilla Attention based models hard to apply to long sequence tasks. Various improved Attention structures are proposed to reduce the computation cost by inducing low rankness and approximating the whole sequence by sub-sequences. The most challenging part of those approaches is maintaining the proper balance between information preservation and computation reduction: the longer sub-sequences used, the better information is preserved, but at the price of introducing more noise and computational costs. In this paper, we propose a smoothed skeleton sketching based Attention structure, coined S $^{3}$ Attention, which significantly improves upon the previous attempts to negotiate this trade-off. S $^{3}$ Attention has two mechanisms to effectively minimize the impact of noise while keeping the linear complexity to the sequence length: a smoothing block to mix information over long sequences and a matrix sketching method that simultaneously selects columns and rows from the input matrix. We verify the effectiveness of S $^{3}$ Attention both theoretically and empirically. Extensive studies over Long Range Arena (LRA) datasets and six time-series forecasting show that S $^{3}$ Attention significantly outperforms both vanilla Attention and other state-of-the-art variants of Attention structures.

关键词： Computational modeling Complexity theory Transformers Task analysis Skeleton Kernel Noise

来源：评论

学校读者我要写书评

暂无评论

Implicit Relative Labeling-Importance Aware Multi-Label Metric Learning 39

Implicit Relative Labeling-Importance Aware Multi-Label Metr...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Mao, Jun-Xiang Rui, Yong Zhang, Min-Ling School of Computer Science and Engineering Southeast University Nanjing210096 China Ministry of Education China Information Technology and Data Management Department China Mobile Communications Group Zhejiang Co. Ltd. China Lenovo Research Lenovo Group Ltd. Beijing China

ISBN: (纸本)157735897X

Multi-label metric learning, as an extension of metric learning to multi-label scenarios, aims to learn better similarity metrics for objects with rich semantics. Existing multi-label metric learning approaches employ the common assumption of equal labeling-importance, i.e., all associated labels are considered relevant to the training instance, while there is no differentiation in the relative importance of their semantics. However, this common assumption does not reflect the fact that the importance of each relevant label is generally different, even though such importance information is not directly accessible from the training examples. In this paper, we claim that it is beneficial to leverage the implicit Relative Labeling-Importance (RLI) information to facilitate multi-label metric learning. Specifically, the manifold structure within the feature space is exploited by local linear reconstruction, and then the RLIs are recovered by transferring such structure to the label space. Subsequently, a discrimiative multi-label metric learning framework is introduced to align the predictive modeling outputs with the recovered RLIs, under which instances with similar RLI are implicitly pulled closer to each other, while those with dissimilar RLI are pushed further apart. Comprehensive experiments on benchmark multi-label datasets validate the superiority of our proposed approach in learning effective similarity metrics between multi-label examples. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词： Nameplates

来源：评论

学校读者我要写书评

暂无评论

A Dual-Level Cancelable Framework for Palmprint Verification and Hack-Proof data Storage

arXiv

引用

arXiv 2024年

作者： Yang, Ziyuan Kang, Ming Teoh, Andrew Beng Jin Gao, Chengrui Chen, Wen Zhang, Bob Zhang, Yi The College of Computer Science Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University Chengdu610065 China The School of Cyber Science and Engineering Sichuan University Chengdu610065 China The School of Electrical and Electronic Engineering College of Engineering Yonsei University Seoul Korea Republic of The College of Computer Science Sichuan University Chengdu610065 China The Pattern Analysis and Machine Intelligence Group Department of Computer and Information Science University of Macau Taipa China The School of Cyber Science and Engineering Key Laboratory of Data Protection and Intelligent Management Ministry of Education Sichuan University Chengdu610065 China

In recent years, palmprints have been widely used for individual verification. The rich privacy information in palmprint data necessitates its protection to ensure security and privacy without sacrificing system performance. Existing systems often use cancelable technologies to protect templates, but these technologies ignore the potential risk of data leakage. Upon breaching the system and gaining access to the stored database, a hacker could easily manipulate the stored templates, compromising the security of the verification system. To address this issue, we propose a dual-level cancelable palmprint verification framework in this paper. Specifically, the raw template is initially encrypted using a competition hashing network with a first-level token, facilitating the end-to-end generation of cancelable templates. Different from previous works, the protected template undergoes further encryption to differentiate the second-level protected template from the first-level one. The system specifically creates a negative database (NDB) with the second-level token for dual-level protection during the enrollment stage. Reversing the NDB is NP-hard and a fine-grained algorithm for NDB generation is introduced to manage the noise and specified bits. During the verification stage, we propose an NDB matching algorithm based on matrix operation to accelerate the matching process of previous NDB methods caused by dictionary-based matching rules. This approach circumvents the need to store templates identical to those utilized for verification, reducing the risk of potential data leakage. Extensive experiments conducted on public palmprint datasets have confirmed the effectiveness and generality of the proposed framework. Upon acceptance of the paper, the code will be accessible at https://***/Deep-Imaging-group/NPR. Copyright © 2024, The Authors. All rights reserved.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Power of Big data: A Comprehensive Analysis and Future Directions

Unleashing the Power of Big Data: A Comprehensive Analysis a...

引用

International Conference on Contemporary Computing and Informatics (IC3I)

作者： Annu Sharma Gaurav Kumar Mansoor Farooq Manish Kumar Gupta Saranya Raj Ashok Kumar Rai Department of Computer Science & Application RajaRajeshwari College of Engineering Bengaluru Karnataka India Department of Computer Science & Engineering Indian Institute of Science Education and Research Bhopal Bhopal Madhya Pradesh India Department of Management Studies University of Kashmir Jammu & Kashmir India Department of Information Technology & Computer Application Madan Mohan Malaviya University of Technology Gorakhpure UP India Department of Data Science & Engineering Dronacharya Group of Institutions Greater Noida Uttar Pradesh India Department of Computer Science & Engineering Madan Mohan Malaviya University of Technology Gorakhpure UP India

Big data (BD) has emerged as a transformative force, offering unprecedented opportunities for organizations to extract valuable insights and drive informed decision-making. This research paper presents a comprehensive analysis of the current state of BD, explores its potential applications across industries, and outlines future directions for maximizing its benefits. This paper examines the key components of BD, including data collection, storage, processing, and analytics. It investigates the technologies and methodologies that enable efficient handling of large volumes of structured and unstructured data. Additionally, it explores the impact of cloud computing, artificial intelligence (AI), and the Internet of Things (IoT) on the growth and utilization of BD. Overall, this research paper provides a comprehensive analysis of BD, its current applications, challenges, and future directions. It serves as a valuable resource for researchers, practitioners, and policymakers seeking to unlock the full power of BD and harness its benefits across diverse domains.

关键词：

来源：评论

学校读者我要写书评

暂无评论

6G and AI: Viewpoints, Processes, and Technologies

6G and AI: Viewpoints, Processes, and Technologies

引用

Communication, Computing and Energy Efficient Technologies (I3CEET), International Conference on

作者： S.A. Shoyusupov B. Lanitha Shanky Goyal Vishal Goyal Saif O. Husain Praveen Sharma Department of Physics and Chemistry Tashkent Institute of Irrigation and Agricultural Mechanization Engineers National Research University Tashkent Uzbekistan Department of Artificial Intelligence and Data Science Karpagam Academy of Higher Education Coimbatore Department of Computer Science Engineering Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri Mohali Punjab India Department of Electronics and Communication Engineering GLA University Mathura India Department Of Computers Techniques Engineering College Of Technical Engineering The Islamic University Najaf Iraq Department of Computer Science & Engineering IES Institute of Technology and Management IES University Bhopal M.P. India

ISBN: (数字)9798331541583

ISBN: (纸本)9798331541590

The rapid improvement of remote systems is being driven by the growing use of fake intelligence. The shift from "interdependent items" to "associated insights" is expected to be fundamentally altered by sixth-generation (6G) distant innovation. However, because of their vast analytics foundations and deep neural networks, state-of-the-art AI frameworks entirely rely on computer and interactions. As a result, excessive inactivity, excessive energy use, organizational obstruction, and protection leakage occur throughout the planning and deduction phases. Edge AI might be a game-changer for 6G, improving the practicality, efficacy, security, and validity of 6G systems in general, with its steady integration of sensing, communication, processing, and intelligence. It does this by coordinating modelling with duction and teaching skills at the organise edge. In this research, we will outline our methodology for robust and flexible uncontrolled neural network models and coordinated Bluetooth connections in edge AI contexts. A comprehensive end-to-end frame plan for supporting edge AI, service-driven use efficiency tactics, and contemporary concepts in remote organize building will all be safeguarded. In addition, uniformity, phases for software and hardware components, state-of-the-art AI applications, and real-world examples are presented to support industrialization and subsequently deployment.

关键词： 6G mobile communication Technological innovation Edge AI Software Telecommunication computing Sensors Resource management Reliability Artificial intelligence Protection

来源：评论

学校读者我要写书评

暂无评论

PROV-IO+: A Cross-Platform Provenance Framework for Scientific data on HPC Systems

arXiv

引用

arXiv 2023年

作者： Han, Runzhou Zheng, Mai Byna, Suren Tang, Houjun Dong, Bin Dai, Dong Chen, Yong Kim, Dongkyun Hassoun, Joseph Thorsley, David Wolf, Matthew Department of Electrical and Computer Engineering Iowa State University United States Department of Computer Science and Engineering The Ohio State University United States Scientific Data Management Group Lawrence Berkeley National Laboratory United States Computer Science Department University of North Carolina Charlotte United States Systems Architecture Lab Samsung United States Samsung Advanced Institute of Technology Samsung Korea Republic of

data provenance, or data lineage, describes the life cycle of data. In scientific workflows on HPC systems, scientists often seek diverse provenance (e.g., origins of data products, usage patterns of datasets). Unfortunately, existing provenance solutions cannot address the challenges due to their incompatible provenance models and/or system implementations. In this paper, we analyze four representative scientific workflows in collaboration with the domain scientists to identify concrete provenance needs. Based on the first-hand analysis, we propose a provenance framework called PROV-IO+, which includes an I/O-centric provenance model for describing scientific data and the associated I/O operations and environments precisely. Moreover, we build a prototype of PROV-IO+ to enable end-to-end provenance support on real HPC systems with little manual effort. The PROV-IO+ framework can support both containerized and non-containerized workflows on different HPC platforms with flexibility in selecting various classes of provenance. Our experiments with realistic workflows show that PROV-IO+ can address the provenance needs of the domain scientists effectively with reasonable performance (e.g., less than 3.5% tracking overhead for most experiments). Moreover, PROV-IO+ outperforms a state-of-the-art system (i.e., ProvLake) in our experiments. © 2023, CC BY-NC-SA.

关键词： Life cycle

来源：评论

学校读者我要写书评

暂无评论

SHLE: Devices Tracking and Depth Filtering for Stereo-based Height Limit Estimation

arXiv

引用

arXiv 2022年

作者： Fan, Zhaoxin Yang, Kaixing Zhang, Min Song, Zhenbo Liu, Hongyan He, Jun Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China

Recently, over-height vehicle strike frequently occurs, causing great economic cost and serious safety problems. Hence, an alert system which can accurately discover any possible height limiting devices in advance is necessary to be employed in modern large or medium sized cars, such as touring cars. Detecting and estimating the height limiting devices act as the key point of a successful height limit alert system. Though there are some works research height limit estimation, existing methods are either too computational expensive or not accurate enough. In this paper, we propose a novel stereo-based pipeline named SHLE for height limit estimation. Our SHLE pipeline consists of two stages. In stage 1, a novel devices detection and tracking scheme is introduced, which accurately locate the height limit devices in the left or right image. Then, in stage 2, the depth is temporally measured, extracted and filtered to calculate the height limit device. To benchmark the height limit estimation task, we build a large-scale dataset named "Disparity Height", where stereo images, pre-computed disparities and ground-truth height limit annotations are provided. We conducted extensive experiments on "Disparity Height" and the results show that SHLE achieves an average error below than 10cm though the car is 70m away from the devices. Our method also outperforms all compared baselines and achieves state-of-the-art performance. Code is available at https://***/Yang-Kaixing/SHLE. Copyright © 2022, The Authors. All rights reserved.

关键词： Pipelines

来源：评论

学校读者我要写书评

暂无评论

Deformable 3D/3D CT-to-digital-tomosynthesis image registration in image-guided bronchoscopy interventions

引用

computers in Biology and Medicine 2024年 171卷 108199-108199页

作者： Saad, Fatima Frysch, Robert Saalfeld, Sylvia Kellnberger, Stephan Schulz, Jessica Fahrig, Rebecca Bhadra, Krish Nürnberger, Andreas Rose, Georg Institute for Medical Engineering Otto-von-Guericke University Magdeburg Germany Forschungscampus STIMULATE Otto-von-Guericke University Magdeburg Germany Department of Simulation and Graphics Otto-von-Guericke University Magdeburg Germany Siemens Healthcare GmbH Forchheim Germany CHI Memorial Rees Skillern Cancer Institute Chattanooga United States Data and Knowledge Engineering Group Faculty of Computer Science Otto-von-Guericke University Magdeburg Germany

Traditional navigational bronchoscopy procedures rely on preprocedural computed tomography (CT) and intraoperative chest radiography and cone-beam CT (CBCT) to biopsy peripheral lung lesions. This navigational approach is challenging due to the projective nature of radiography, and the high radiation dose, long imaging time, and large footprints of CBCT. Digital tomosynthesis (DTS) is considered an attractive alternative combining the advantages of radiography and CBCT. Only the depth resolution cannot match a full CBCT image due to the limited angle acquisition. To address this issue, preoperative CT is a good auxiliary in guiding bronchoscopy interventions. Nevertheless, CT-to-body divergence caused by anatomic changes and respiratory motion, hinders the effective use of CT imaging. To mitigate CT-to-body divergence, we propose a novel deformable 3D/3D CT-to-DTS registration algorithm employing a multistage, multiresolution approach and using affine and elastic B-spline transformation models with bone and lung mask images. A multiresolution strategy with a Gaussian image pyramid and a multigrid strategy within the B-spline model are applied. The normalized correlation coefficient is included in the cost function for the affine model and a multimetric weighted cost function is used for the B-spline model, with weights determined heuristically. Tested on simulated and real patient bronchoscopy data, the algorithm yields promising results. Assessed qualitatively by visual inspection and quantitatively by computing the Dice coefficient (DC) and the average symmetric surface distance (ASSD), the algorithm achieves mean DC of 0.82±0.05 and 0.74±0.05, and mean ASSD of 0.65±0.29mm and 0.93±0.43mm for simulated and real data, respectively. This algorithm lays the groundwork for CT-aided intraoperative DTS imaging in image-guided bronchoscopy interventions with future studies focusing on automated metric weight setting. © 2024

关键词： Image registration

来源：评论

学校读者我要写书评

暂无评论

Object Level Depth Reconstruction for Category Level 6D Object Pose Estimation From Monocular RGB Image

arXiv

引用

arXiv 2022年

作者： Fan, Zhaoxin Song, Zhenbo Xu, Jian Wang, Zhicheng Wu, Kejian Liu, Hongyan He, Jun Key Laboratory of Data Engineering and Knowledge Engineering of MOE School of Information Renmin University of China Beijing100872 China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China Department of Management Science and Engineering Tsinghua University Beijing100084 China Nreal China

Recently, RGBD-based category-level 6D object pose estimation has achieved promising improvement in performance, however, the requirement of depth information prohibits broader applications. In order to relieve this problem, this paper proposes a novel approach named Object Level Depth reconstruction Network (OLD-Net) taking only RGB images as input for category-level 6D object pose estimation. We propose to directly predict object-level depth from a monocular RGB image by deforming the category-level shape prior into object-level depth and the canonical NOCS representation. Two novel modules named Normalized Global Position Hints (NGPH) and Shape-aware Decoupled Depth Reconstruction (SDDR) module are introduced to learn high fidelity object-level depth and delicate shape representations. At last, the 6D object pose is solved by aligning the predicted canonical representation with the back-projected object-level depth. Extensive experiments on the challenging CAMERA25 and REAL275 datasets indicate that our model, though simple, achieves state-of-the-art performance. Copyright © 2022, The Authors. All rights reserved.

关键词： Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Enhanced Performance and data Privacy in Lung Nodule Classification via Federated Deep Learning Approach 24

Enhanced Performance and Data Privacy in Lung Nodule Classif...

引用

2024 7th International Conference on Healthcare Service management, ICHSM 2024

作者： Nguyen, Duc-Khanh Li, Ai-Hsien Adam Lai, Yen-Jun Chiu, Yen-Ling Phan, Dinh-Van Chien, Ting-Ying Chan, Chien-Lung Department of Information Management Yuan Ze University Taoyuan Taiwan Department of Statistics and Informatics University of Economics The University of Danang Danang Viet Nam Division of Cardiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Radiology Far Eastern Memorial Hospital New Taipei Taiwan Graduate Institute of Medicine and Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan Taiwan Department of Medical Research Far Eastern Memorial Hospital New Taipei Taiwan Department of Computer Science and Engineering Yuan Ze University Taoyuan Taiwan ZDT Group- YZU Joint Research and Development Center for Big Data Taoyuan Taiwan Yuan Ze University Taoyuan Taiwan

ISBN: (纸本)9798400710162

This study explores the feasibility of deep learning for classifying nodule neoplasms, analyzing their performance on two openly available datasets, LUNGx SPIE, and LIDC-IDRI. These datasets offer valuable diversity in image quantity, quality, and malignancy annotation methodologies, posing a real-world challenge for effective model development. To handle the disparities in these diverse datasets, we aim to develop a robust classification model trained using federated learning. This decentralized approach allows model training across datasets without sharing patient data, preserving privacy and overcoming data fragmentation. Our experiments demonstrate that federated learning enables the development of a robust and superior deep learning model compared to individual models trained on limited data. This combination of deep learning, and federated learning holds immense promise for nodule neoplasm classification and can significantly improve patient care and outcomes. © 2024 Copyright held by the owner/author(s).

关键词： Federated learning

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：