检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Xian, Xiaole He, Xilin Niu, Zenghao Zhang, Junliang Xie, Weicheng Song, Siyang Yu, Zitong Shen, Linlin Computer Vision Institute School of Computer Science & Software Engineering Shenzhen University China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University China Guangdong Key Laboratory of Intelligent Information Processing China University of Exeter United Kingdom Great Bay University China

For efficient and high-fidelity local facial attribute editing, most existing editing methods either require additional finetuning for different editing effects or tend to affect beyond the editing regions. Alternatively, inpainting methods can edit the target image region while preserving external areas. However, current inpainting methods still suffer from the generation misalignment with facial attributes description and the loss of facial skin details. To address these challenges, (i) a novel data utilization strategy is introduced to construct datasets consisting of attribute-text-image triples from a data-driven perspective, (ii) a Causality-Aware Condition Adapter is proposed to enhance the contextual causality modeling of specific details, which encodes the skin details from the original image while preventing conflicts between these cues and textual conditions. In addition, a Skin Transition Frequency Guidance technique is introduced for the local modeling of contextual causality via sampling guidance driven by low-frequency alignment. Extensive quantitative and qualitative experiments demonstrate the effectiveness of our method in boosting both fidelity and editability for localized attribute editing. The code is available at https://***/connorxian/CA-Edit. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Age of Information in Random Access Networks With Correlated Sources

Optimizing Age of Information in Random Access Networks With...

引用

IEEE International Conference on Information Communication and Signal Processing (ICICSP)

作者： Long Liang Siyuan Zhou Bin Tang Guoping Tan College of Information Science and Engineering Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China

ISBN: (数字)9798350355895

ISBN: (纸本)9798350355901

Random access is a wireless network access technique that can meet the transmission requirements of a massive number of Internet of Things terminals under limited resource constraints. To address the needs of delay-sensitive applications, it is essential to study random access strategies from the perspective of information timeliness. Existing research often assumes that the information transmitted by terminals is independent of each other, neglecting the correlation between information in the design process of random access strategies. However, in scenarios such as video surveillance and sensor monitoring, adjacent terminal transmissions exhibit spatial correlation. To overcome this limitation, this paper proposes a random access strategy based on information timeliness and information correlation. Specifically, we establish information correlation between information sources and analyze the coupling variation of Age of Information (AoI) in multipoint transmission scenarios, deriving an expression for the average network AoI. Next, by jointly optimizing the random access probabilities of various terminals, we minimize the average network AoI. To address the non-convex and nonlinear optimization problem, we design an optimization algorithm based on Sequential Quadratic Programming and propose an approach to obtain initial values for improved algorithm stability. Simulation results demonstrate that the proposed method significantly reduces the average network AoI compared to random strategies that do not consider correlation.

关键词： Correlation Wireless networks Simulation Signal processing algorithms Signal processing Reliability theory Information age Video surveillance Stability analysis Quadratic programming

来源：评论

学校读者我要写书评

暂无评论

Distilling Cross-Temporal Contexts for Continuous Sign Language Recognition

Distilling Cross-Temporal Contexts for Continuous Sign Langu...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Leming Guo Wanli Xue Qing Guo Bo Liu Kaihua Zhang Tiantian Yuan Shengyong Chen School of Computer Science and Engineering Tianjin University of Technology Centre for Frontier AI Research (CFAR) A*STAR Singapore Walmart Global Tech Sunnyvale CA USA School of Computer and Software Nanjing University of Information Science and Technology Technical College for the Deaf Tianjin University of Technology

Continuous sign language recognition (CSLR) aims to recognize glosses in a sign language video. State-of-the-art methods typically have two modules, a spatial perception module and a temporal aggregation module, which are jointly learned end-to-end. Existing results in [9, 20, 25, 36] have indicated that, as the frontal component of the over-all model, the spatial perception module used for spatial feature extraction tends to be insufficiently trained. In this paper, we first conduct empirical studies and show that a shallow temporal aggregation module allows more thor-ough training of the spatial perception module. However, a shallow temporal aggregation module cannot well capture both local and global temporal context information in sign language. To address this dilemma, we propose a cross-temporal context aggregation (CTCA) model. Specifically, we build a dual-path network that contains two branches for perceptions of local temporal context and global temporal context. We further design a cross-context knowledge distil-lation learning objective to aggregate the two types of con-text and the linguistic prior. The knowledge distillation en-ables the resultant one-branch temporal aggregation mod-ule to perceive local-global temporal and semantic context. This shallow temporal perception module structure facili-tates spatial perception module learning. Extensive exper-iments on challenging CSLR benchmarks demonstrate that our method outperforms all state-of-the-art methods.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Fed2PKD: Bridging Model Diversity in Federated Learning via Two-Pronged Knowledge Distillation

Fed2PKD: Bridging Model Diversity in Federated Learning via ...

引用

IEEE International Conference on Cloud Computing, CLOUD

作者： Zaipeng Xie Han Xu Xing Gao Junchen Jiang Ruiqian Han Key Laboratory of Water Big Data Technology of Ministry of Water Resources Hohai University Nanjing China College of Computer Science and Software Engineering Hohai University Nanjing China The Hong Kong University of Science and Technology (Guangzhou) Guangzhou China

ISBN: (数字)9798350368536

ISBN: (纸本)9798350368543

Heterogeneous federated learning (HFL) enables collaborative learning across clients with diverse model architectures and data distributions while preserving privacy. However, existing HFL approaches often struggle to effectively address the challenges posed by model diversity, leading to suboptimal performance and limited generalization ability. This paper pro-poses Fed2PKD, a novel HFL framework that tackles these challenges through a two-pronged knowledge distillation approach. Fed2PKD combines prototypical contrastive knowledge distillation to align client embeddings with global class prototypes and semi-supervised global knowledge distillation to capture global data characteristics. Experimental results on three benchmarks (MNIST, CIFAR10, and CIFAR100) demonstrate that Fed2PKD significantly outperforms existing state-of-the-art HFL methods, achieving average improvements of up to 30.53%, 13.89%, and 5.80 % in global model accuracy, respectively. Furthermore, Fed2PKD enables personalized models for each client, adapting to their specific data distributions and model architectures while benefiting from global knowledge sharing. Theoretical analysis provides convergence guarantees for Fed2PKD under realistic assumptions. Fed2PKD represents a significant step forward in HFL, unlocking the potential for privacy-preserving collaborative learning in real-world scenarios with model and data diversity.

关键词： Knowledge engineering Adaptation models Cloud computing Data privacy Federated learning Computational modeling Prototypes

来源：评论

学校读者我要写书评

暂无评论

Multi-batch Nuclear-norm Adversarial Network for Unsupervised Domain Adaptation

Multi-batch Nuclear-norm Adversarial Network for Unsupervise...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Pei Wang Yun Yang Zhenyu Yu School of Information Science and Engineering Yunnan University Kunming China National Pilot School of Software Yunnan University Kunming China Yunnan Key Laboratory of Software Engineering Yunnan University Kunming China Guangzhou University Guangzhou China CISiP Faculty of Computer Science and Information Technology Universiti Malaya Kuala Lumpur Malaysia

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Adversarial learning has achieved great success for unsupervised domain adaptation (UDA). Existing adversarial UDA methods leverage the predicted discriminative information with Nuclear-norm Wasserstein discrepancy for feature alignment. However, the limited memory space makes it very difficult to accurately calculate the Nuclear-norm, which hinders domain adaptation. To address this challenge, we propose a multi-batch Nuclear-norm adversarial network, termed as MBAN. Specifically, we build a dynamic queue to cache features, which encourages to generate a large and consistent output matrix, enabling accurate calculation of the Nuclear-norm. Then, the multi-batch Nuclear-norm discrepancy is proposed, which can effectively improve the transferability and discriminability of the learned features. Experimental results show that MBAN could achieve significant performance improvement, especially when the number of categories is quite large. Code is available at https://***/peiwang0518/Multi-BAN.

关键词： Codes Accuracy Adversarial machine learning Noise measurement

来源：评论

学校读者我要写书评

暂无评论

An Efficient Convolutional Multi-Scale Vision Transformer for Image Classification

An Efficient Convolutional Multi-Scale Vision Transformer fo...

引用

Image Processing, computer Vision and Machine Learning (ICICML), International Conference on

作者： Ji Zhang Zhihao Chen Yiyuan Ge Mingxin Yu School of Instrument Science and Opto-Electronics Engineering Beijing Information Science and Technology University Beijing China Computer School Beijing Information Science & Technology University Beijing China Department of Software Engineering Jilin University Changchun China

This paper introduces an innovative and efficient multi-scale Vision Transformer (ViT) for the task of image classification. The proposed model leverages the inherent power of transformer architecture and combines it with the concept of multi-scale processing generally used in convolutional neural networks (CNNs). The work aims to address the limitations of conventional ViTs which typically operate at a single scale, hence overlooking the hierarchical structure in visual data. The multi-scale ViT enhances classification performance by processing image features at different scales, effectively capturing both low-level and high-level semantic information. Extensive experimental results demonstrate the superior performance of the proposed model over standard ViTs and other state-of-the-art image classification methods, signifying the effectiveness of the multi-scale approach. This research opens new avenues for incorporating scale-variance in transformer-based models for improved performance in vision tasks.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Mining High Utility Itemset with Multiple Minimum Utility Thresholds Based on Utility Deviation

Mining High Utility Itemset with Multiple Minimum Utility Th...

引用

IEEE International Conference on Data Mining Workshops (ICDM Workshops)

作者： Naji Alhusaini Jing Li Philippe Fournier-Viger Ammar Hawbani Guilin Chen School of Computer and Information Engineering. Chuzhou University Chuzhou China School of Computer Since and Technology University of Since and Technology of China Hefei China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

High Utility Itemset Mining (HUIM) is the task of extracting actionable patterns considering the utility of items such as profits and quantities. An important issue with traditional HUIM methods is that they evaluate all items using a single threshold, which is inconsistent with reality due to differences in the nature and importance of items. Recently, algorithms were proposed to address this problem by assigning a minimum item utility threshold to each item. However, since the minimum item utility (MIU) is expressed as a percentage of the external utility, these methods still face two problems, called “itemset missing” and “itemset explosion”. To solve these problems, this paper introduces a novel notion of Utility Deviation (UD), which is calculated based on the standard deviation. The U D and actual utility are jointly used to calculate the MIU of items. By doing so, the problems of “itemset missing” and “itemset explosion” are alleviated. To implement and evaluate the U D notion, a novel algorithm is proposed, called HUI-MMU-UD. Experimental results demonstrate the effectiveness of the proposed notion for solving the problems of “itemset missing” and “itemset explosion”. Results also show that the proposed algorithm outperforms the previous HUI-MMU algorithm in many cases, in terms of runtime and memory usage.

关键词： Runtime Itemsets Conferences Explosions Data mining Task analysis Standards

来源：评论

学校读者我要写书评

暂无评论

A Graph Sequence Generator and Multi-head Self-attention Mechanism based Knowledge Graph Reasoning Architecture 26

A Graph Sequence Generator and Multi-head Self-attention Mec...

引用

26th International Conference on computer Supported Cooperative Work in Design, CSCWD 2023

作者： Wu, Yuejia Zhou, Jian-Tao College of Computer Science Inner Mongolia University Hohhot China National & Local Joint Engineering Research Center Intelligent Info. Proc. Technology for Mongolian Engineering Research Center of Ecological Big Data Ministry of Education Hohhot China Inner Mongolia Engineering Laboratory for Cloud Computing and Service Software Inner Mongolia Key Laboratory of Social Computing and Data Processing Hohhot China Inner Mongolia Key Laboratory of Discipline Inspection and Supervision Big Data Inner Mongolia Engineering Laboratory for Big Data Analysis Technology Hohhot China

ISBN: (纸本)9798350331684

Knowledge Graph (KG) is an essential research direction that involves storing and managing knowledge data, but its incompleteness and sparsity hinder its development in various applications. Knowledge Graph Reasoning (KGR) is an effective method to solve this limitation via reasoning missing knowledge based on existing knowledge. The graph Convolution Network (GCN) based method is one of the state-of-the-art approaches to this work. However, there are still some problems, such as the insufficient ability to perceive graph structure and the poor effect of learning data features which may limit the reasoning accuracy. This paper proposes a KGR architecture based on a graph sequence generator and multi-head self-attention mechanism, named GaM-KGR, to improve the above problems and enhance prediction accuracy. Specifically, the GaM-KGR first introduces the graph generation model into the field of KGR for graph representation learning to obtain the hidden features in the data so that enhancing the reasoning effect and then embeds the generated graph sequence into the multi-head self-attention mechanism for subsequent processing to improve the graph structure perception ability of the proposed architecture, so that it can process the graph structure data more appropriately. Extensive experimental results show that the GaM-KGR architecture can achieve the state-of-the-art prediction results of current GCN-based models. © 2023 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

QoS Perception for Cloud Databases: Necessity, Trends, and Challenges

QoS Perception for Cloud Databases: Necessity, Trends, and C...

引用

International Workshop on Quality of Service

作者： Weipeng Cao Xi Tao Yinghui Pan Ye Liu Zhong Ming Guangdong Laboratory of Artificial Intelligence and Digital Economy (Shenzhen) Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China

ISBN: (数字)9798350350128

ISBN: (纸本)9798350350135

The advantages of resource elasticity and proactive data backup in cloud databases have attracted a large number of users to consider deploying their IT systems in the cloud. Factors such as performance, reliability, security, and ease of use are the most important considerations for users when choosing to migrate to the cloud. This paper mainly discusses the necessity of Quality of Service (QoS) awareness for cloud applications in the current public cloud environment, as well as the technological trends and challenges associated with it.

关键词： Cloud computing Databases Quality of service Elasticity Market research Real-time systems Security

来源：评论

学校读者我要写书评

暂无评论

Stock Price Prediction Using LSTMSeq2Seq: A Deep Learning Approach with Advanced Feature engineering

Stock Price Prediction Using LSTMSeq2Seq: A Deep Learning Ap...

引用

International Conference on computer and Information technology (ICCIT)

作者： Md. Kalim Amzad Chy Abdul Kadar Muhammad Masum Mohammed Shamsul Alam Md. Abul Kalam Azad Md Zia Uddin Dept. of AI Innovation Liberate Labs Texas USA Dept. of Software Engineering Daffodil International University Dhaka Bangladesh Dept. of Computer Science and Engineering International Islamic University Chittagong Chittagong Bangladesh Dept. of Business and Technology Management Islamic University of Technology Gazipur Bangladesh Software and Service Innovation Department SINTEF Digital Oslo Norway

ISBN: (数字)9798331519094

ISBN: (纸本)9798331519100

This paper explores stock price prediction in the context of the Bangladesh stock market using advanced deep learning methodologies, specifically the LSTMSeq2Seq model. Traditional analytical techniques often fail to capture the complex, non-linear patterns inherent in financial data. To address this limitation, our research leverages the strengths of the LSTM-Seq2Seq architecture, which is tailored to the unique dynamics of the Bangladesh market. A robust feature engineering process is employed, utilizing 67 diverse features, including market trends, stock-specific indicators, fundamental and technical variables, and key macroeconomic factors such as gold prices and foreign exchange reserves. The dataset encompasses historical stock market data from 2012 to 2022, and extensive data preprocessing is performed to handle inconsistencies. Hyperparameter optimization is conducted using grid search to ensure model performance. The LSTMSeq2Seq model is evaluated based on key metrics such as MAE, MAPE, MSE, and the R 2 score, demonstrating superior predictive capabilities compared to traditional methods. This research not only advances the application of deep learning in financial forecasting but also provides valuable insights into stock price prediction in emerging markets, addressing ethical concerns to mitigate risks like market manipulation.

关键词： Deep learning Measurement Sentiment analysis Computational modeling Time series analysis Predictive models Macroeconomics Stock markets Forecasting Long short term memory

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：