检索结果-内蒙古大学图书馆

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

作者： Hongji Wang Chengdong Liang Shuai Wang Zhengyang Chen Binbin Zhang Xu Xiang Yanlei Deng Yanmin Qian CSE Dept MoE Key Lab of AI X-LANCE Lab Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China WeNet Open Source Community School of Marine Science and Technology Northwestern Polytechnical University Xi’an China NVIDIA Santa Clara USA Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Horizon Robotics Beijing China AISpeech Ltd Suzhou China

Speaker modeling is essential for many related tasks, such as speaker recognition and speaker diarization. The dominant modeling approach is fixed-dimensional vector representation, i.e., speaker embedding. This paper introduces a research and production oriented speaker embedding learning toolkit, Wespeaker. Wespeaker contains the implementation of scalable data management, state-of-the-art speaker embedding models, loss functions, and scoring back-ends, with highly competitive results achieved by structured recipes which were adopted in the winning systems in several speaker verification challenges. The application to other downstream tasks such as speaker diarization is also exhibited in the related recipe. Moreover, CPU- and GPU-compatible deployment codes are integrated for production-oriented development. The toolkit is publicly available at https://***/wenet-e2e/wespeaker.

关键词： Codes Production Signal processing data models Acoustics Speaker recognition Task analysis

来源：评论

学校读者我要写书评

暂无评论

Tail Quantile Estimation for Non-Preemptive Priority Queues

Tail Quantile Estimation for Non-Preemptive Priority Queues

引用

Simulation Winter Conference

作者： Jin Guang Guiyu Hong Xinyun Chen Xi Peng Li Chen Bo Bai Gong Zhang Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen Shenzhen Guangdong P. R. CHINA School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen Guangdong P. R. CHINA Theory Lab 2012 Labs Central Research Institute Huawei Technologies Co. Ltd. Hong Kong P. R. CHINA

ISBN: (纸本)9781665476621

Motivated by applications in computing and telecommunication systems, we investigate the problem of estimating $p$ -quantile of steady-state sojourn times in a single-server multi-class queueing system with non-preemptive priorities for $p$ close to 1. The main challenge in this problem lies in efficient sampling from the tail event. To address this issue, we develop a regenerative simulation algorithm with importance sampling. In addition, we establish a central limit theorem for the estimator to construct the confidence interval. Numerical experiments show that our algorithm outperforms benchmark simulation methods. Our result contributes to the literature on rare event simulation for queueing systems.

关键词： Monte Carlo methods Protocols Computational modeling Estimation Tail Benchmark testing Numerical models

来源：评论

学校读者我要写书评

暂无评论

Cross-City Matters: A Multimodal Remote Sensing Benchmark dataset for Cross-City Semantic Segmentation using High-Resolution Domain Adaptation Networks

arXiv

引用

arXiv 2023年

作者： Hong, Danfeng Zhang, Bing Li, Hao Li, Yuxuan Yao, Jing Li, Chenyu Werner, Martin Chanussot, Jocelyn Zipf, Alexander Zhu, Xiao Xiang Aerospace Information Research Institute Chinese Academy of Sciences Beijing100094 China College of Resources and Environment University of Chinese Academy of Sciences Beijing100049 China Big Geospatial Data Management Technical University of Munich Munich85521 Germany School of Mathematics Southeast University Nanjing210096 China Univ. Grenoble Alpes CNRS Grenoble INP GIPSA-Lab Grenoble38000 France GIScience Chair Institute of Geography Heidelberg University Heidelberg69120 Germany Data Science in Earth Observation Technical University of Munich Munich80333 Germany

Artificial intelligence (AI) approaches nowadays have gained remarkable success in single-modality-dominated remote sensing (RS) applications, especially with an emphasis on individual urban environments (e.g., single cities or regions). Yet these AI models tend to meet the performance bottleneck in the case studies across cities or regions, due to the lack of diverse RS information and cutting-edge solutions with high generalization ability. To this end, we build a new set of multimodal remote sensing benchmark datasets (including hyperspectral, multispectral, SAR) for the study purpose of the cross-city semantic segmentation task (called C2Seg dataset), which consists of two cross-city scenes, i.e., Berlin-Augsburg (in Germany) and Beijing-Wuhan (in China). Beyond the single city, we propose a high-resolution domain adaptation network, HighDAN for short, to promote the AI model’s generalization ability from the multi-city environments. HighDAN is capable of retaining the spatially topological structure of the studied urban scene well in a parallel high-to-low resolution fusion fashion but also closing the gap derived from enormous differences of RS image representations between different cities by means of adversarial learning. In addition, the Dice loss is considered in HighDAN to alleviate the class imbalance issue caused by factors across cities. Extensive experiments conducted on the C2Seg dataset show the superiority of our HighDAN in terms of segmentation performance and generalization ability, compared to state-of-the-art competitors. The C2Seg dataset and the semantic segmentation toolbox (involving the proposed HighDAN) will be available publicly at https://***/danfenghong. Copyright © 2023, The Authors. All rights reserved.

关键词： Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Coresets for near-convex functions 20

Coresets for near-convex functions

引用

Proceedings of the 34th International Conference on Neural Information Processing Systems

作者： Murad Tukan Alaa Maalouf Dan Feldman The Robotics and Big Data Lab Department of Computer Science University of Haifa Haifa Israel

ISBN: (纸本)9781713829546

Coreset is usually a small weighted subset of n input points in ℝd, that provably approximates their loss function for a given set of queries (models, classifiers, etc.). Coresets become increasingly common in machine learning since existing heuristics or inefficient algorithms may be improved by running them possibly many times on the small coreset that can be maintained for streaming distributed data. Coresets can be obtained by sensitivity (importance) sampling, where its size is proportional to the total sum of sensitivities. Unfortunately, computing the sensitivity of each point is problem dependent and may be harder to compute than the original optimization problem at hand. We suggest a generic framework for computing sensitivities (and thus coresets) for wide family of loss functions which we call near-convex functions. This is by suggesting the ƒ-SVD factorization that generalizes the SVD factorization of matrices to functions. Example applications include coresets that are either new or significantly improves previous results, such as SVM, Logistic regression, M-estimators, and ℓz-regression. Experimental results and open source are also provided.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Federated Learning for Privacy Preservation and Efficiency in Edge Computing

引用

IEEE Transactions on Services Computing 2025年第03期18卷 1739-1752页

作者： Zhou, Hao Dai, Hua Yang, Geng Xiang, Yang Nanjing University of Posts and Telecommunications School of Computer Science Jiangsu Security and Intelligent Processing Lab of Big Data Nanjing210023 China Swinburne University of Technology Department of Computer Science HawthornVIC3122 Australia

Federated Learning (FL) has emerged as a key enabler of privacy-preserving distributed model training in edge computing environments, crucial for service-oriented applications such as personalized healthcare, smart cities, and intelligent assistants. However, existing privacy-preserving FL methods are susceptible to multiple privacy leakage attacks (MPLA), where adversaries infer sensitive information through repeated gradient updates. This paper proposes a Robust and Communication-Efficient Federated Learning (RCFL) framework designed to enhance privacy protection and communication efficiency in edge-based service environments. RCFL integrates a global privacy-preserving mechanism with an innovative privacy encoding strategy that minimizes privacy risks over multiple data releases while significantly reducing communication overhead. The proposed framework's theoretical analysis demonstrates its ability to maintain differential privacy across numerous interactions, ensuring robust model convergence and efficiency. Experimental results using MNIST and CIFAR-10 datasets reveal that RCFL can lower the MPLA success rate from 88.56% to 42.57% compared to state-of-the-art methods, while reducing communication costs by over 90%. These findings underscore RCFL's potential to enhance security, efficiency, and scalability in service-oriented edge computing applications. © 2008-2012 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Global Collaboration to Enhance Information Technology & Quantitative Management: Preface for ITQM 2023

引用

Procedia Computer science 2023年 221卷 xv-xvii页

作者： Shi, Yong Filip, Florin G. He, Jing Li, Jianping Kou, Gang Tien, James Berg, Daniel Research Centre on Fictitious Economy and Data Science Chinese Academy of Sciences Beijing100190 China Key Lab of Big Data Mining and Knowledge Management Chinese Academy of Sciences Beijing100190 China School of Economics and Management University of Chinese Academy of Sciences Beijing100190 China Romanian Academy Calea Victoriei 125 Sector 1 Bucharest010071 Romania College of Information Science and Technology University of Nebraska at Omaha OmahaNE68182 United States University of Oxford United Kingdom School of Business Chengdu University Sichuan 610106 China College of Engineering University of Miami Coral GablesFL33124 United States

来源：评论

学校读者我要写书评

暂无评论

MYOPIA PREDICTION FOR ADOLESCENTS VIA TIME-AWARE DEEP LEARNING

arXiv

引用

arXiv 2022年

作者： Huang, Junjia Ma, Wei Li, Rong Zhao, Na Zhou, Tao Computational Education Lab Big Data Research Center University of Electronic Science and Technology of China Chengdu China Department of Ophthalmology of West China Hospital Sichuan University Chengdu China Eye See Inc Chengdu China National Pilot School of Software Yunnan University Kunming China

Background: Quantitative prediction of the adolescents’ spherical equivalent based on their variable-length historical vision records. Methods: From October 2019 to March 2022, we examined binocular uncorrected visual acuity, axial length, corneal curvature, and axial of 75,172 eyes from 37,586 adolescents aged 6-20 years in Chengdu, China. 80% samples consist of the training set and the remaining 20% form the testing set. Time-Aware Long Short-Term Memory was used to quantitatively predict the adolescents’ spherical equivalent within two and a half years. Result: The mean absolute prediction error on the testing set was 0.273 ± 0.257 for spherical equivalent, ranging from 0.189 ± 0.160 to 0.596 ± 0.473 if we consider different lengths of historical records and different prediction durations. Conclusions: Time-Aware Long Short-Term Memory was applied to captured the temporal features in irregularly sampled time series, which is more in line with the characteristics of real data and thus has higher applicability, and helps to identify the progression of myopia earlier. The overall error 0.273 is much smaller than the criterion for clinically acceptable prediction, say 0.75. Copyright © 2022, The Authors. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

MLS3RDUH: Deep unsupervised hashing via manifold based local semantic similarity structure reconstructing 29

MLS3RDUH: Deep unsupervised hashing via manifold based local...

引用

29th International Joint Conference on Artificial Intelligence, IJCAI 2020

作者： Tu, Rong-Cheng Mao, Xian-Ling Wei, Wei Department of Computer Science and Technology Beijing Institute of Technology China CETC Big Data Research Institute Co. Ltd. Guiyang55002 China Zhijiang Lab Hangzhou China School of Computer Science Huazhong University of Science and Technology China

ISBN: (纸本)9780999241165

Most of the unsupervised hashing methods usually map images into semantic similarity-preserving hash codes by constructing local semantic similarity structure as guiding information, i.e., treating each point similar to its k nearest neighbours. However, for an image, some of its k nearest neighbours may be dissimilar to it, i.e., they are noisy datapoints which will damage the retrieval performance. Thus, to tackle this problem, in this paper, we propose a novel deep unsupervised hashing method, called MLS3RDUH, which can reduce the noisy datapoints to further enhance retrieval performance. Specifically, the proposed method first defines a novel similarity matrix by utilising the intrinsic manifold structure in feature space and the cosine similarity of datapoints to reconstruct the local semantic similarity structure. Then a novel log-cosh hashing loss function is used to optimize the hashing network to generate compact hash codes by incorporating the defined similarity as guiding information. Extensive experiments on three public datasets show that the proposed method outperforms the state-of-the-art baselines. © 2020 Inst. Sci. inf., Univ. Defence in Belgrade. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Uncovering multi-order popularity and similarity mechanisms in link prediction by graphlet predictors

arXiv

引用

arXiv 2024年

作者： He, Yong-Jian Ran, Yijun Di, Zengru Zhou, Tao Xu, Xiao-Ke Department of Systems Science Faculty of Arts and Sciences Beijing Normal University Zhuhai519087 China International Academic Center of Complex Systems Beijing Normal University Zhuhai519087 China School of Systems Science Beijing Normal University Beijing100875 China Computational Communication Research Center Beijing Normal University Zhuhai519087 China Department of Systems Science Faculty of Artsand Sciences Beijing Normal University Zhuhai519087 China CompleX Lab University of Electronic Science and Technology of China Chengdu611731 China Big Data Research Center University of Electronic Science and Technology of China Chengdu611731 China

Link prediction has become a crucial problem in network science and has thus attracted increasing research interest. Popularity and similarity are two primary mechanisms in the link formation of real networks. However, the roles of these mechanisms in link prediction across various networks in domains remain poorly understood. Here, we use orbit degrees of graphlets to construct lower- and higher-order predictors and demonstrate that multi-order popularity and similarity indices can be efficiently represented in terms of orbit degrees. We further propose a supervised learning model that fuses multiple orbit-degree-based features and validate its enhanced performance. We observe that lower-order features, particularly lower-order similarity, serve as the primary role in the link prediction, while higher-order features tend to play a complementary role. Our research improves the accuracy and interpretability of link prediction and provides new perspectives and tools for analyzing complex networks. © 2024, CC BY.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Research on personalized learning path management based on blockchain technology 16

Research on personalized learning path management based on b...

引用

16th IEEE International Conference on Computer science and Education, ICCSE 2021

作者： Changhua, Zhao Chunqiao, Mi Huaihua University School of Computer Science and Engineering Hunan Huaihua418000 China Key Lab. of Wuling-Mt. Hlth. Big Data Intelligent Proc. and Applic. in Hunan Province Universities Hunan Huaihua418000 China Key Lab. of Intelligent Contr. Technol. for Wuling-Mountain Ecological Agriculture in Hunan Province Hunan Huaihua18000 China

ISBN: (纸本)9781665414685

Aiming at the problem that learners' personal information, courses and relevant certificates can not provide detailed information about learning depth and learning or teaching methods, this paper takes learners' learning information, learning record smart contract and Ethereum Blockchain related technology as the research object, aiming to use Ethereum Blockchain and smart contract to connect learners' learning records. On the one hand, it can use the block data stored in the Blockchain to easily verify the authenticity of the data and ensure the privacy and security of the data. On the other hand, it can provide personalized learning path for learners and be used to evaluate a person's educational achievement, employment suitability and intelligence evaluation. © 2021 IEEE.

关键词： Smart contract

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：