检索结果-内蒙古大学图书馆

Fine-Grained Cross-Modal Fusion Based Refinement for Text-to-Image Synthesis

Chinese Journal of Electronics 2023年第6期32卷 1329-1340页

作者： SUN Haoran WANG Yang LIU Haipeng QIAN Biao Department of Computer Science and Information Engineering Hefei University of Technology Key Laboratory of Knowledge Engineering with Big Data Ministry of EducationHefei University of Technology

Text-to-image synthesis refers to generating visual-realistic and semantically consistent images from given textual descriptions. Previous approaches generate an initial low-resolution image and then refine it to be high-resolution. Despite the remarkable progress, these methods are limited in fully utilizing the given texts and could generate text-mismatched images, especially when the text description is complex. We propose a novel finegrained text-image fusion based generative adversarial networks(FF-GAN), which consists of two modules: Finegrained text-image fusion block(FF-Block) and global semantic refinement(GSR). The proposed FF-Block integrates an attention block and several convolution layers to effectively fuse the fine-grained word-context features into the corresponding visual features, in which the text information is fully used to refine the initial image with more details. And the GSR is proposed to improve the global semantic consistency between linguistic and visual features during the refinement process. Extensive experiments on CUB-200 and COCO datasets demonstrate the superiority of FF-GAN over other state-of-the-art approaches in generating images with semantic consistency to the given texts.

关键词： Visualization Fuses Convolution Semantics Linguistics Benchmark testing Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

GIRP: Energy-Efficient QoS-Oriented Microservice Resource Provisioning via Multi-Objective Multi-Task Reinforcement Learning

引用

IEEE Transactions on Mobile Computing 2025年第07期24卷 5793-5807页

作者： Yuan, Honggang Wang, Ting Fu, Min Shi, Yuanming East China Normal University MoE Engineering Research Center of Software/Hardware Co-design Technology and Application Shanghai Key Laboratory of Trustworthy Computing Shanghai200062 China National University of Singapore Department of Electrical and Computer Engineering 117583 Singapore ShanghaiTech University School of Information Science and Technology Shanghai201210 China

Microservice architecture has revolutionized web service development by facilitating loosely coupled and independently developable components distributed as containers or virtual machines. While existing studies emphasize end-to-end latency, this paper investigates energy-efficient quality-of-service (QoS)-oriented microservice provisioning, focusing on both QoS satisfaction and power consumption (PC) conservation. We propose the Green and Intelligent Resource Provision (GIRP) architecture, integrating a data-driven energy-latency-aware resource allocation and scheduling manager to balance latency and PC. To reconcile the trade-offs involved, a dual-objective optimization problem is formulated to minimize latency and energy use by selecting proper servers, allocating CPU cores, and determining service replicas. To address challenges with discrete variables, dual objectives, and implicit mappings, we leverage a model-free deep deterministic policy gradient-based reinforcement learning algorithm. Specifically, we develop a multi-task agent via the Multi-gate Mixture-of-Experts model to simultaneously make two separate actions regarding CPU core numbers and service replica numbers, followed by a single-task agent to determine service scheduling. Extensive experiments on the DeathStarBenchmark testbed validate GIRP's effectiveness, demonstrating approximately 52% resource savings and a 43% reduction in PC compared to leading methods like Sinan, Firm, and heuristic-based algorithms. These results highlight GIRP's capability to optimize microservice orchestration by balancing end-to-end latency and power efficiency. © 2025 IEEE. All rights reserved.

关键词： Quality of service

来源：评论

学校读者我要写书评

暂无评论

Fixed-point quantum continuous search algorithm with optimal query complexity

引用

science China(Physics,Mechanics & Astronomy) 2025年第6期Mechanics & Astronomy) .卷 84-95页

作者： Shan Jin Yuhan Huang Shaojun Wu Guanyu Zhou Chang-Ling Zou Luyan Sun Xiaoting Wang Institute of Fundamental and Frontier Sciences University of Electronic Science and Technology of China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Key Laboratory of Quantum Information CAS University of Science and Technology of China Hefei National Laboratory Center for Quantum Information Institute for Interdisciplinary Information Sciences Tsinghua University

Continuous search problems(CSPs), which involve finding solutions within a continuous domain, frequently arise in fields such as optimization, physics, and engineering. Unlike discrete search problems, CSPs require navigating an uncountably infinite space, presenting unique computational challenges. In this work, we propose a fixed-point quantum search algorithm that leverages continuous variables to address these challenges, achieving a quadratic speedup. Inspired by the discrete search results, we manage to establish a lower bound on the query complexity of arbitrary quantum search for CSPs, demonstrating the optimality of our approach. In addition, we demonstrate how to design the internal structure of the quantum search oracle for specific problems. Furthermore, we develop a general framework to apply this algorithm to a range of problem types, including optimization and eigenvalue problems involving continuous variables.

关键词： quantum search quantum algorithm quantum computation optimization spectral problems

来源：评论

学校读者我要写书评

暂无评论

PAIR: Protein-aptamer interaction prediction based on language models and contrastive learning framework

PAIR: Protein-aptamer interaction prediction based on langua...

引用

2024 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2024

作者： Zhang, Jun Yan, Zhiqiang Zeng, Hao Zhu, Zexuan Shenzhen University National Engineering Laboratory for Big Data System Computing Technology Shenzhen China Shenzhen University College of Computer Science and Software Engineering Shenzhen China

ISBN: (纸本)9798350386226

Aptamers are single-stranded DNA or RNA oligonucleotides that selectively bind to specific targets, making them valuable for drug design and diagnostic applications. Identifying the interactions between aptamers and target proteins is crucial for these applications. The systematic evolution of ligands by exponential enrichment process, traditionally used for this purpose, is challenging and time-consuming. The resulting aptamers often suffer from limitations in stability and diversity. Computational approaches have shown promise in aiding the discovery of high-performance aptamers, but existing methods are usually constrained by insufficient training data and limited generalizability. Recently, advancements in pre-training large language models have offered a new avenue to mitigate the dependency on large datasets. In this study, we propose a novel method to predict aptamer-protein interactions using large language models within a contrastive learning framework. Experimental results demonstrate that our method exhibits superior generalization and outperforms existing approaches. This method holds promise as a powerful tool for predicting aptamer-protein interactions. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

A Survey and Experimental Review on Data Distribution Strategies for Parallel Spatial Clustering Algorithms

引用

Journal of computer science & Technology 2024年第3期39卷 610-636页

作者： Jagat Sesh Challa Navneet Goyal Amogh Sharma Nikhil Sreekumar Sundar Balasubramaniam Poonam Goyal Advanced Data Analytics and Parallel Technologies Laboratory Birla Institute of Technology and Science Pilani 333031India Uber New York 11101U.S.A. Computer Science and Engineering Department University of MinnesotaMinneapolis 55455U.S.A.

The advent of Big Data has led to the rapid growth in the usage of parallel clustering algorithms that work over distributed computing frameworks such as MPI,MapReduce,and *** important step for any parallel clustering algorithm is the distribution of data amongst the cluster *** step governs the methodology and performance of the entire *** typically use random,or a spatial/geometric distribution strategy like kd-tree based partitioning and grid-based partitioning,as per the requirements of the ***,these strategies are generic and are not tailor-made for any specific parallel clustering *** this paper,we give a very comprehensive literature survey of MPI-based parallel clustering algorithms with special reference to the specific data distribution strategies they *** also propose three new data distribution strategies namely Parameterized Dimensional Split for parallel density-based clustering algorithms like DBSCAN and OPTICS,Cell-Based Dimensional Split for dGridSLINK,which is a grid-based hierarchical clustering algorithm that exhibits efficiency for disjoint spatial distribution,and Projection-Based Split,which is a generic distribution *** of these preserve spatial locality,achieve disjoint partitioning,and ensure good data load *** experimental analysis shows the benefits of using the proposed data distribution strategies for algorithms they are designed for,based on which we give appropriate recommendations for their usage.

关键词： parallel data mining data distribution parallel clustering spatial locality preservation

来源：评论

学校读者我要写书评

暂无评论

RGB-T object tracking with adaptive decision fusion 2

RGB-T object tracking with adaptive decision fusion

引用

2nd International Conference on Algorithms, Microchips, and Network Applications, AMNA 2023

作者： Bai, Yida Yang, Ming Department of Software Engineering College of Computer & Information Science Southwest University Chongqing400715 China Department of Computer Science College of Computer & Information Science Southwest University Chongqing400715 China

ISBN: (纸本)9781510664791

Visual object tracking is a traditional task in computer vision, which has developed with several decades. With the development of machine learning, correlation filter (CF) has been proposed with satisfying performance and very high framerate. Though the CF framework has numerous strengths in this task, the tracker is fragile to miss the target in several scenes, including extreme illumination, target occlusion and deformation. Recently, thermal modality, which detects the target’s temperature, is robust to the night scenes and can provide a precise target contour. In this paper, we propose a CF based tracker with decision fusion strategy for visible-thermal (RGB-T) tracking. First, we introduce multi-modal KCF trackers as our baseline. Then, we design a decision fusion method considering the Peak-to-Side Rate (PSR) of the score maps, thereby achieving an adaptive fusing those modalities and avoiding model’s heterogeneity. In the experiments, our tracker has validated on the public dataset, namely GTOT. Compared with two uni-modality trackers, the proposed tracker with real-time speed has shown superior results on both target localization and scale estimation. © 2023 SPIE.

关键词： Target tracking

来源：评论

学校读者我要写书评

暂无评论

Injections Attacks Efficient and Secure Techniques Based on Bidirectional Long Short Time Memory Model

引用

computers, Materials & Continua 2023年第9期76卷 3605-3622页

作者： Abdulgbar A.R.Farea Gehad Abdullah Amran Ebraheem Farea Amerah Alabrah Ahmed A.Abdulraheem Muhammad Mursil Mohammed A.A.Al-qaness School of Big Data&Software Engineering Chongqing UniversityChongqing401331China Department of Management Science Engineering Dalian University of TechnologyDalian116024China Software College Northeastern UniversityShenyang110169China Department of Information Systems College of Computer and Information ScienceKing Saud UniversityRiyadh11543Saudi Arabia Department of Management Science and Engineering South China University of TechnologyGuangzhou510641China Department of Computer Engineering and Mathematics University of Rovira i VirgiliTarragonaSpain College of Physics and Electronic Information Engineering Zhejiang Normal UniversityJinhua321004China

E-commerce,online ticketing,online banking,and other web-based applications that handle sensitive data,such as passwords,payment information,and financial information,are widely *** web developers may have varying levels of understanding when it comes to securing an online *** Query language SQL injection and cross-site scripting are the two vulnerabilities defined by the OpenWeb Application Security Project(OWASP)for its 2017 Top Ten List Cross Site Scripting(XSS).An attacker can exploit these two flaws and launch malicious web-based actions as a result of these *** published articles focused on these attacks’binary *** article described a novel deep-learning approach for detecting SQL injection and XSS *** datasets for SQL injection and XSS payloads are combined into a single *** dataset is labeledmanually into three labels,each representing a kind of *** work implements some pre-processing algorithms,including Porter stemming,one-hot encoding,and the word-embedding method to convert a word’s text into a *** model used bidirectional long short-term memory(BiLSTM)to extract features automatically,train,and test the payload *** payloads were classified into three types by BiLSTM:XSS,SQL injection attacks,and *** outcomes demonstrated excellent performance in classifying payloads into XSS attacks,injection attacks,and non-malicious ***’s high performance was demonstrated by its accuracy of 99.26%.

关键词： Web security SQL injection XSS deep learning RNN LSTM BiLSTM

来源：评论

学校读者我要写书评

暂无评论

Dysarthric Speech Recognition using Depthwise Separable Convolutions: Preliminary Study 12

Dysarthric Speech Recognition using Depthwise Separable Conv...

引用

12th International Conference on Speech Technology and Human-computer Dialogue, SpeD 2023

作者： Shahamiri, Seyed Reza Mandal, Krishnendu Sarkar, Sudeshna The University of Auckland Faulty of Engineering Department of Electrical Computer and Software Engineering Auckland New Zealand Indian Institute of Technology Computer Science & Engineering Department Kharagpur India

ISBN: (纸本)9798350327977

As a neurological disability that affects muscles involved in articulation, dysarthria is a speech impairment that leads to reduced speech intelligibility. In severe cases, these individuals could also be handicapped and unable to interact with digital devices. For such individuals, Automatic Speech Recognition (ASR) technologies could be life changing by enabling them to communicate with others as well as computing devices via voice commands. Nonetheless, ASR systems designed to recognize healthy speech have shown very poor performance to transcribe dysarthric speech, signaling the need to design ASR specifically tailored for dysarthria. Dysarthric Speech Recognition (DRS) research has progressed gradually because of the challenges the research community faces such as the scarcity of dysarthric speech that does not allow the researchers to design deeper acoustic models needed to better learn dysarthric speech variations. In this paper we report on our preliminary findings to improve our previous DSR called Speech Vision and study the effects of Separable Convolutional neurons to improve its acoustic model. Speech Vision is a novel Dysarthric Speech Recognition system that learns to recognize the shape of the words uttered by dysarthric speakers instead of recognizing phone sequences and then mapping them to words. Experiments conducted on the utterances provided by all UA-Speech dysarthric speakers indicate the proposed Depthwise separable architecture provided better word recognition accuracies compared to the original Speech Vision's architecture across all dysarthric speech intelligibility classes. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Parkinson’s Disease Detection from Resting State EEG Using Multi-head Graph Structure Learning with Gradient Weighted Graph Attention Explanations 7th

Parkinson’s Disease Detection from Resting State EEG Using...

引用

7th International Workshop on Machine Learning in Clinical Neuroimaging, MLCN 2024, Held in Conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Neves, Christopher Zeng, Yong Xiao, Yiming Department of Computer Science and Software Engineering Concordia University MontrealQC Canada Concordia Institute for Information Systems Engineering Concordia University MontrealQC Canada

ISBN: (纸本)9783031787607

Parkinson’s disease (PD) is a debilitating neurodegenerative disease that has severe impacts on an individual’s quality of life. Compared with structural and functional MRI-based biomarkers for the disease, electroencephalography (EEG) can provide more accessible alternatives for clinical insights. While deep learning (DL) techniques have provided excellent outcomes, many techniques fail to model spatial information and dynamic brain connectivity, and face challenges in robust feature learning, limited data sizes, and poor explainability. To address these issues, we proposed a novel graph neural network (GNN) technique for explainable PD detection using resting state EEG. Specifically, we employ structured global convolutions with contrastive learning to better model complex features with limited data, a novel multi-head graph structure learner to capture the non-Euclidean structure of EEG data, and a head-wise gradient-weighted graph attention explainer to offer neural connectivity insights. We developed and evaluated our method using the UC San Diego Parkinson’s disease EEG dataset, and achieved 69.40% detection accuracy in subject-wise leave-one-out cross-validation while generating intuitive explanations for the learnt graph topology. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Performance-Guaranteed Finite-Time Tracking of Strict-Feedback Systems with Unknown Control Directions: A Novel Switching Mechanism

引用

IEEE Transactions on Automatic Control 2025年第6期70卷 4061-4068页

作者： Mao, Bing Wu, Xiaoqun Fan, Ziye Lu, Jinhu Chen, Guanrong Shenzhen University College of Computer Science and Software Engineering Shenzhen518060 China Wuhan University School of Mathematics and Statistics Hubei430072 China Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Electrical Engineering Hong Kong Hong Kong

The problem of achieving performance-guaranteed finite-time exact tracking for uncertain strict-feedback nonlinear systems with unknown control directions is addressed. A novel logic switching mechanism with monitoring functions is designed to deal with unknown control directions. This approach is different from existing methods like the Nussbaum gain technique and smooth orientation functions, which are inapplicable to finite-time exact tracking. The main challenge lies in designing monitoring functions and determining switching rules, which is well resolved through three steps. Most significantly, in contrast to existing works that solely guarantee bounded tracking or asymptotic exact tracking, the new mechanism incorporates novel integral sliding mode techniques to achieve finite-time exact tracking with guaranteed performance. Finally, simulations are presented with comparison to demonstrate the effectiveness of the proposed methods. © 1963-2012 IEEE.

关键词： Feedback

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：