检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Liang, Keyu Liu, Zhongxin Liu, Chao Wan, Zhiyuan Lo, David Yang, Xiaohu The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China School of Big Data and Software Engineering Chongqing University Chongqing China School of Computing and Information Systems Singapore Management University Singapore Singapore

Code search is a crucial task in software engineering, aiming to retrieve code snippets that are semantically relevant to a natural language query. Recently, Pre-trained Language Models (PLMs) have shown remarkable success and are widely adopted for code search tasks. However, PLM-based methods often struggle in cross-domain scenarios. When applied to a new domain, they typically require extensive fine-tuning with substantial data. Even worse, the data scarcity problem in new domains often forces these methods to operate in a zero-shot setting, resulting in a significant decline in performance. RAPID, which generates synthetic data for model fine-tuning, is currently the only effective method for zero-shot cross-domain code search. Despite its effectiveness, RAPID demands substantial computational resources for fine-tuning and needs to maintain specialized models for each domain, underscoring the need for a zero-shot, fine-tuning-free approach for cross-domain code search. The key to tackling zero-shot cross-domain code search lies in bridging the gaps among domains. In this work, we propose to break the query-code matching process of code search into two simpler tasks: query-comment matching and code-code matching. We first conduct an empirical study to investigate the effectiveness of these two matching schemas in zero-shot cross-domain code search. Our findings highlight the strong complementarity among the three matching schemas, i.e., query-code, query-comment, and code-code matching. Based on the findings, we propose CodeBridge, a zero-shot, fine-tuning-free approach for cross-domain code search. Specifically, CodeBridge first employs zero-shot prompting to guide Large Language Models (LLMs) to generate a comment for each code snippet in the codebase and produce a code for each query. Subsequently, it encodes queries, code snippets, comments, and the generated code using PLMs and assesses similarities through three matching schemas: query-code, query-comment,

关键词： Search engines

来源：评论

学校读者我要写书评

暂无评论

ECA-RetinaNet: A Novel Self-Attention RetinaNet for Environmental Microorganism Image Object Detection

ECA-RetinaNet: A Novel Self-Attention RetinaNet for Environm...

引用

IEEE International Conference on Big Data

作者： Hechen Yang Jinzhu Yang Tao Jiang Xin Zhao Jinghua Zhang Peng Zhao Ao Chen Qianqing Nie Marcin Grzegorzek Chen Li Microscopic Image and Medical Image Analysis Group College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang Liaoning China School of Intelligent Medicine Chengdu University of Traditional Chinese Medicine Chengdu China International Joint Institute of Robotics and Intelligent Systems Chengdu University of Information Technology Chengdu China Institute of Medical Informatics University of Luebeck Luebeck Germany

The detection of environmental microorganisms is always a difficult task, e specially when the multi-scale environment is complex. For tiny objects in microscopic images, current detection methods face the challenge of accurate identification and localization. In contrast, we propose a convolutional neural network (ECA-RetinaNet) for microscopic object detection of which underlying dataset is a high-quality EMDS-7 dataset. The accuracy of ECA-RetinaNet is high, with a high mean Average Precision (mAP) value of 81.42% in the Environmental Microorganisms (EMS) detection task. Its accuracy has been higher than that of the two-stage object detection network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel distributed Informatics Platform to Support Machine Learning Discovery of Metabolic Biomarkers in Hypoxia Predisposition

Novel Distributed Informatics Platform to Support Machine Le...

引用

16th International Joint Conference on Biomedical Engineering systems and Technologies, BIOSTEC 2023

作者： Stell, Anthony Chauhan, Vedant Amador, Sandra Beuschlein, Felix Favier, Judith Gil, David Greenwood, Philip de Krijger, Ronald Kroiss, Matthias Ortuno, Samanta Patocs, Attila Walch, Axel School of Computing and Information Systems University of Melbourne Melbourne Australia Zurich Switzerland Universite Paris Cite PARCC INSERM Equipe Labellisee par la Ligue contre le Cancer Paris France Department of Computer Science Technology and Computation University of Alicante Alicante Spain Dept. of Pathology University Medical Center Utrecht and Princess Maxima Center for Pediatric Oncology Utrecht Netherlands University Hospital Munich Ludwig-Maximilians-Universitat Munchen Germany ELKH Hereditary Cancer Research Group Department of Laboratory Medicine Semmelweis University and Department of Molecular Genetics National Institute of Oncology Budapest Hungary Research Unit Analytical Pathology Helmholtz Zentmm Munchen Oberschleissheim Germany Department of Computer Science and Systems University of Murcia Murcia Spain Health and Biomedical Research Institute of Alicante Alicante Spain

To realise the scientific and clinical benefits of machine learning (ML) in a multi-centre research collaboration, a common issue is tire need to bring high-volnme data, complex analytical algorithms, and large-scale processing power, all together into one place. This paper describes tire detailed architecture of a novel platform that combines these features, in tire context of a proposed new clinical/bioinformatics project, Hypox-PD. Hypox-PD uses ML methods to identify new metabolic bionrarkers, through the analysis of high-volume data including mass spectrometry and imaging morphology of biobank tissue. The platform features three components: a content delivery network (CDN);a standardised orchestration application;and lrigh-specification processing power and storage. The central innovation of this platform is a distributed application that simultaneously manages the workflow between these components, provides a virtual mapping of the domain data dictionary, and presents the project data/metadata in a FAIR-compliant external interface. This paper presents the detailed design specifications of this platform, as well as initial test results in establishing the benchmark challenge of current direct transfer times without any specialised support. An initial costing of CDN usage is also presented, which indicates that significant performance improvement may be achievable at a reasonable cost to research budgets. © 2023 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Decoupled Doubly Contrastive Learning for Cross Domain Facial Action Unit Detection

arXiv

引用

arXiv 2025年

作者： Li, Yong Liu, Menglin Cui, Zhen Ding, Yi Zong, Yuan Zheng, Wenming Shan, Shiguang Guan, Cuntai School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Nanjing210096 China Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information Ministry of Education School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing210094 China School of Artificial Intelligence Beijing Normal University Beijing100875 China Key Laboratory of AI Safety Institute of Computing Technology Chinese Academy of Sciences Beijing100190 China University of Chinese Academy of Sciences Beijing100049 China School of Computer Science and Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore Key Laboratory of Child Development and Learning Science of Ministry of Education School of Biological Science and Medical Engineering Nanjing210096 China

Despite the impressive performance of current vision-based facial action unit (AU) detection approaches, they are heavily susceptible to the variations across different domains and the cross-domain AU detection methods are under-explored. In response to this challenge, we propose a decoupled doubly contrastive adaptation (D2CA) approach to learn a purified AU representation that is semantically aligned for the source and target domains. Specifically, we decompose latent representations into AU-relevant and AU-irrelevant components, with the objective of exclusively facilitating adaptation within the AU-relevant subspace. To achieve the feature decoupling, D2CA is trained to disentangle AU and domain factors by assessing the quality of synthesized faces in cross-domain scenarios when either AU or domain attributes are modified. To further strengthen feature decoupling, particularly in scenarios with limited AU data diversity, D2CA employs a doubly contrastive learning mechanism comprising image and feature-level contrastive learning to ensure the quality of synthesized faces and mitigate feature ambiguities. This new framework leads to an automatically learned, dedicated separation of AU-relevant and domain-relevant factors, and it enables intuitive, scale-specific control of the cross-domain facial image synthesis. Extensive experiments demonstrate the efficacy of D2CA in successfully decoupling AU and domain factors, yielding visually pleasing cross-domain synthesized facial images. Meanwhile, D2CA consistently outperforms state-of-the-art cross-domain AU detection approaches, achieving an average F1 score improvement of 6%-14% across various cross-domain scenarios. © 2025, CC BY-NC-SA.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

PrivGenDB: Efficient and privacy-preserving query executions over encrypted SNP-phenotype database

arXiv

引用

arXiv 2021年

作者： Jafarbeiki, Sara Sakzad, Amin Kermanshahi, Shabnam Kasra Gaire, Raj Steinfeld, Ron Lai, Shangqi Abraham, Gad The Faculty of Information Technology Monash University Melbourne Australia CSIRO Data 61 Australia The School of Computing Technologies RMIT University Melbourne Australia The Systems Genomics Laboratory Baker Institute Melbourne Australia

Searchable symmetric encryption (SSE) has been used to protect the confidentiality of genomic data while providing substring search and range queries on a sequence of genomic data, but it has not been studied for protecting single nucleotide polymorphism (SNP)-phenotype data. In this article, we propose a novel model, PrivGenDB, for securely storing and efficiently conducting different queries on genomic data outsourced to an honest-but-curious cloud server. To instantiate PrivGenDB, we use SSE to ensure confidentiality while conducting different types of queries on encrypted genomic data, phenotype and other information of individuals to help analysts/clinicians in their analysis/care. To the best of our knowledge, PrivGenDB construction is the first SSE-based approach ensuring the confidentiality of shared SNP-phenotype data through encryption while making the computation/query process efficient and scalable for biomedical research and care. Furthermore, it supports a variety of query types on genomic data, including count queries, Boolean queries, and k0-out-of-k match queries. Finally, the PrivGenDB model handles the dataset containing both genotype and phenotype, and it also supports storing and managing other metadata like gender and ethnicity privately. Computer evaluations on a dataset with 5, 000 records and 1, 000 SNPs demonstrate that a count/Boolean query and a k0-out-of-k match query over 40 SNPs take approximately 4.3s and 86.4µs, respectively, outperforming the existing schemes. Copyright © 2021, The Authors. All rights reserved.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

An Auto-Parallel Method for Deep Learning Models Based on Genetic Algorithm

An Auto-Parallel Method for Deep Learning Models Based on Ge...

引用

International Conference on Parallel and distributed systems (ICPADS)

作者： Yan Zeng ChengChuang Huang YiJie Ni ChunBao Zhou JiLin Zhang Jue Wang MingYao Zhou MeiTing Xue YunQuan Zhang School of Computer Science and Technology Hangzhou Dianzi University Hangzhou China Key Laboratory for Modeling and Simulation of Complex Systems Ministry of Education Hangzhou China Data Security Governance Zhejiang Engineering Research Center Hangzhou China School of ITMO Joint Institute Hangzhou Dianzi University Hangzhou China Institute of Computer Network Information Center of the Chinese Academy of Sciences Beijing China HuaWei State Key Laboratory of Computer Architecture Institute of Computing Technology of the Chinese Academy of Sciences Beijing China

As the size of datasets and neural network models increases, automatic parallelization methods for models have become a research hotspot in recent years. The existing auto-parallel methods based on machine learning or graph algorithms still have issues with search efficiency and applicability. This paper proposes an automatic parallel method based on a dual-population genetic algorithm, TGA, which transforms model partitioning and placement into an integer linear programming problem and constructs a cost model to evaluate the solution. The solution space is built using the neural network’s dataflow graph and device cluster’s topology, and the dual-population genetic algorithm is used to search for the optimal model parallel strategy. Experiments with various models show that the proposed method can improve single-step execution time by up to 42% compared to the Baechi method and up to 37.7% compared to the Hierarchical method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Strategy for Advancing Research and Impact in New computing Paradigms

arXiv

引用

arXiv 2021年

作者： Buyya, Rajkumar Gill, Sukhpal Singh Srirama, Satish Narayana Bahsoon, Rami Murugesan, San Laboratory School of Computing and Information Systems The University of Melbourne Australia School of Electronic Engineering and Computer Science Queen Mary University of London United Kingdom School of Computer and Information Sciences University of Hyderabad India Mobile & Cloud Lab Institute of Computer Science University of Tartu Estonia School of Computer Science University of Birmingham Birmingham United Kingdom BRITE Professional Services Australia

In the domain of information technology, new paradigms, technologies, development approaches, and application scenarios continue to emerge rapidly presenting new opportunities for researchers to pursue. Emerging paradigms are often considered to be high risk for academic research due to the immaturity of research foundation and ambiguity in fundamentals supporting the paradigm. A pragmatic and holistic strategy would be needed to systematically steer continuous development and evaluation of research in the area and to accelerate impact and adoption. Drawing on our own a decade-long experience in establishing strong and impactful research in cloud computing, we document and reflect on our strategy for advancing research and building a strong community in what was believed to be a high risk emerging/new computing research area for researchers to embark on. The strategy consists of nine key elements which include creation of a roadmap, development of simulators and supporting tools, and creation of application demonstrators that confirm feasibility and effectiveness of applications of the new research findings. We discuss how development of simulators can be cost-effective in accelerating design of real systems and outline strategic role played by different types of publications or conference organization, and development and delivery of educational programs that form part of the research strategy. We illustrate effectiveness of the recommended strategy with our cloud computing research work, which is globally recognized for its impact. Copyright © 2021, The Authors. All rights reserved.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

DMNER: Biomedical Named Entity Recognition by Detection and Matching

DMNER: Biomedical Named Entity Recognition by Detection and ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Junyi Bian Rongze Jiang Weiqi Zhai Tianyang Huang Xiaodi Huang Hong Zhou Shanfeng Zhu School of Computer Science Fudan University Shanghai China Institute of Science and Technology for Brain-Inspired Intelligence Fudan University Shanghai China School of Computing Mathematics and Engineering Charles Sturt University New South Wales Australia Atypon Systems LLC UK Key Laboratory of Computational Neuroscience and Brain-Inspired Intelligence Institute of Science and Technology for Brain-Inspired Intelligence and MOE Frontiers Center for Brain Science Shanghai Key Lab of Intelligent Information Processing Zhangjiang Fudan International Innovation Center Fudan University Shanghai China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Biomedical Named Entity Recognition (NER) is a crucial task in extracting information from biomedical texts. However, the diversity of professional terminology, semantic complexity, and the widespread presence of synonyms pose significant challenges. Traditional methods that rely on sequence labeling training datasets often struggle to handle these complexities. To address this, we introduce a novel framework for BioNER, termed DMNER, which leverages external knowledge and operates in two steps: entity boundary detection and entity category identification through matching. The core of DMNER is its second step, which determines the entity category by retrieving similar entities and their categories from a knowledge dictionary using semantic similarity matching. Our experiments on 10 biomedical datasets demonstrate that DMNER outperforms baselines across these tasks, proving its effectiveness and adaptability. DMNER is versatile and can be applied to various NER tasks, including supervised NER, distantly supervised NER, and NER on multiple datasets with disjoint label sets. The DMNER code is publicly available 1 .

关键词： Training Dictionaries Codes Semantics Named entity recognition Complexity theory Labeling Data mining Bioinformatics

来源：评论

学校读者我要写书评

暂无评论

Comprehensive evaluation of cloud services based on fuzzy grey method

Comprehensive evaluation of cloud services based on fuzzy gr...

引用

作者： Li, Wenjuan Cao, Jian Qian, Shiyou Qianjiang College Hangzhou Normal University Hangzhou310036 China Computer Science and Technology Shanghai Jiao Tong University Shanghai200240 China Laboratory School of Computing and Information Systems University of Melbourne MelbourneVIC3010 Australia

cloud-based applications have become more and more popular. However, it remains a big challenge to comprehensive evaluate the reliability and performance of cloud providers and services due to the reason that cloud is extremely dynamic and uncertain, resources distributed, virtualised, and freedom of entry and exit. The grey theory is adapted to handle the problems of blurring and uncertainty. Therefore, based on the grey relational analysis and grey comprehensive evaluation method, this paper proposes a novel trust comprehensive evaluation method for cloud services, also a comprehensive user satisfaction evaluation method for the better selection of suitable providers. In addition, it discuss in detail the construction and calculation of the evaluation model by case study. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Web services

来源：评论

学校读者我要写书评

暂无评论

Application of Computer Vision Techniques to Identify Spray Primary Breakup Structures in High-Speed Flow

Application of Computer Vision Techniques to Identify Spray ...

引用

computing (ICOCO), IEEE International Conference on

作者： Refat Khan Pathan Wei Lun Lim Sian Lun Lau Chiung Ching Ho Luis Bravo Rahul Babu Koneru Prashant Khare Dept. of Computing and Information Systems School of Engineering and Technology Sunway University Bandar Sunway Malaysia Dept. of Engineering School of Engineering and Technology Sunway University Bandar Sunway Malaysia Sunway DataXSight Research Cluster Sunway University Bandar Sunway Malaysia DEVCOM Army Research Laboratory Army Research Directorate MD Department of Aerospace Engineering University of Cincinnati Cincinnati Ohio Department of Aerospace Engineering University of Maryland College Park Maryland USA

Accurate analysis of the spray formation process is of utmost importance because it governs the fuel injector performance in air-breathing engines. Historically, optical diagnostic measurements in this region have been limited, hindering progress in understanding the underpinning physics. Due to the rapid growth in computer power, first principle simulations of the primary breakup process are now available, providing access to the full spatiotemporal fields. This data is essential to investigate the physical instability modes. However, it typically relies on subjective criteria to identify the emerging structures in the spray formation process. Since computer vision tools are known to help automate such classification tasks, this work focuses on developing a framework that can be applied to help identify critical regions during the breakup process. The emerging spray structures identified and tracked include the well-known lobes, ligaments, and droplets that arise during the fuel injection process. Analysis shows that our approach yields promising results providing helpful statistics of the fundamental breakup dynamics for engineering analysis.

关键词：

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：