检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Li, Weihong Liu, Xiaoqiong Fan, Heng Zhang, Libo Hangzhou Institute for Advanced Study University of Chinese Academy of Sciences Hangzhou310024 China Dept. of Computer Science and Engineering University of North Texas DentonTX76207 United States Institute of Software Chinese Academy of Science Beijing100190 China

Recent advancements in visual object tracking have markedly improved the capabilities of unmanned aerial vehicle (UAV) tracking, which is a critical component in real-world robotics applications. While the integration of hierarchical lightweight networks has become a prevalent strategy for enhancing efficiency in UAV tracking, it often results in a significant drop in network capacity, which further exacerbates challenges in UAV scenarios, such as frequent occlusions and extreme changes in viewing angles. To address these issues, we introduce a novel family of UAV trackers, termed CGTrack, which combines explicit and implicit techniques to expand network capacity within a coarse-to-fine framework. Specifically, we first introduce a Hierarchical Feature Cascade (HFC) module that leverages the spirit of feature reuse to increase network capacity by integrating the deep semantic cues with the rich spatial information, incurring minimal computational costs while enhancing feature representation. Based on this, we design a novel Lightweight Gated Center Head (LGCH) that utilizes gating mechanisms to decouple target-oriented coordinates from previously expanded features, which contain dense local discriminative information. Extensive experiments on three challenging UAV tracking benchmarks demonstrate that CGTrack achieves state-of-the-art performance while running fast. Code will be available at https://***/NightwatchFox11/CGTrack. Copyright © 2025, The Authors. All rights reserved.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

Predicting Students’ Academic Performance Through Supervised Machine Learning

Predicting Students’ Academic Performance Through Supervise...

引用

International Conference on Information Science and Communication Technology (ICISCT)

作者： Engr. Sana Bhutto Isma Farah Siddiqui Qasim Ali Arain Maleeha Anwar Department of Software Eengineering Mehran University Of Engineering And Technology Jamshoro Pakistan Dept. of Computer Science University of Karachi Karachi Pakistan

ISBN: (数字)9781728168999

ISBN: (纸本)9781728169002

There are many supervised and unsupervised types of machine learning approaches that are used to extract hidden information and relationship between data, which will eventually, helps decision-makers in the future to take proper interventions. The variety of powerful algorithms used in different areas of daily life that includes our educational system as well. This paper introduces students' academic performance prediction model that uses supervised type of machine learning algorithms like support vector machine and logistic regression. The results supported by various experiments using different technologies are compared and it is showed that sequential minimal optimization algorithm outperforms by achieving improved accuracy as compared to logistic regression. And the knowledge found through this research can help educational institutes to predict the future behavior of students so that they can categorize their performance into good or bad. The objective is not just to predict future performance of students but also provide the best technique for finding the most impactful features to work on like teacher's performance, student's motivation that will eventually decrease the student's dropout ratio.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Semantic Similarity Techniques for Medical Text

Comparative Analysis of Semantic Similarity Techniques for M...

引用

International Conference on Information Networking

作者： Fakhare Alam Muhammad Afzal Khalid Mahmood Malik Dept. of Computer Science & Engineering Oakland University Rochester United States Department of Software Sejong University Seou South Korea

ISBN: (数字)9781728141992

ISBN: (纸本)9781728142005

In medical domain, physicians frequently consult information and knowledge sources for learning relevant piece of information for their clinical decisions. The sources are either internal such as electronic medical records databases or external sources such as biomedical literature. The key challenge for medical information extraction systems is finding required information, considering the explicit and implicit clinical context, with high precision and recall. Previously, many approaches were presented to exploit different aspects of information in the user query and medical text for obtaining semantic similarity at a concept, sentence, and document level, however, there doesn't exist a comparative analysis of different semantic similarity approaches for biomedical domain. This paper aims to compare different techniques used for finding semantic similarity by performing empirical analysis. We have implemented various modern semantic similarity techniques including ontological based matching and contextual word embedding.

关键词： Semantics Ontologies Correlation Google Biomedical measurement Databases Knowledge based systems

来源：评论

学校读者我要写书评

暂无评论

Network2Vec: Learning node representation based on space mapping in networks 19

Network2Vec: Learning node representation based on space map...

引用

19th IEEE International Conference on Data Mining Workshops, ICDMW 2019

作者： Huang, Zhenhua Wang, Zhenyu Zhang, Rui Zhao, Yangyang Xie, Xiaohui Mehrotra, Sharad School of Software Engineering South China University of Technology China Dept. of Computer Science University of California IrvineCA United States

ISBN: (纸本)9781728146034

Complex networks represented as node adjacency matrices constrains the application of machine learning and parallel algorithms. To address this limitation, network embedding (i.e., graph representation) has been intensively studied to learn a fixed-length vector for each node in an embedding space, where the node properties in the original graph are preserved. Existing methods mainly focus on learning embedding vectors to preserve nodes proximity, i.e., nodes next to each other in the graph space should also be closed in the embedding space, but do not enforce algebraic statistical properties to be shared between the embedding space and graph space. In this work, we propose a lightweight model, entitled Network2Vec, to learn network embedding on the base of semantic distance mapping between the graph space and embedding space. The model builds a bridge between the two spaces leveraging the property of group homomorphism. Experiments on different learning tasks, including node classification, link prediction, and community visualization, demonstrate the effectiveness and efficiency of the new embedding method, which improves the state-of-the-art model by 19% in node classification and 7% in link prediction tasks at most. In addition, our method is significantly faster, consuming only a fraction of the time used by some famous methods. © 2019 IEEE.

关键词： Network embeddings

来源：评论

学校读者我要写书评

暂无评论

Challenges and Opportunities in Open Data Collaboration – a focus group study

Challenges and Opportunities in Open Data Collaboration – a...

引用

Euromicro Conference on software engineering and Advanced Applications (SEAA)

作者： Per Runeson Thomas Olsson Dept. of Computer Science Lund University Lund Sweden Software and Systems Engineering Lab RISE Research Institutes of Sweden Lund Sweden

ISBN: (数字)9781728195322

ISBN: (纸本)9781728195339

Data-driven software is becoming prevalent, especially with the advent of machine learning and artificial intelligence. With data-driven systems come both challenges - to keep collecting and maintaining high quality data - and opportunities - open innovation by sharing data with others. We propose Open Data Collaboration (ODC) to describe pecuniary and non-pecuniary sharing of open data, similar to Open Source software (OSS) and in contrast to Open Government Data (OGD), where public authorities share data. To understand challenges and opportunities with ODC, we organized five focus groups with in total 27 practitioners from 22 companies, public organizations, and research institutes. In the discussions, we observed a general interest in the subject, both from private companies and public authorities. We also noticed similarities in attitudes to open innovation practices, i.e. initial resistance which gradually turned into interest. While several of the participants were experienced in open source software, no had shared data openly. Based on the findings, we identify challenges which we set out to continue addressing in future research.

关键词： Organizations Technological innovation Ecosystems Conferences software Collaboration Government

来源：评论

学校读者我要写书评

暂无评论

Augmented shortcuts for vision transformers 21

Augmented shortcuts for vision transformers

引用

Proceedings of the 35th International Conference on Neural Information Processing Systems

作者： Yehui Tang Kai Han Chang Xu An Xiao Yiping Deng Chao Xu Yunhe Wang Key Lab of Machine Perception (MOE) Dept. of Machine Intelligence Peking University and Huawei Noah's Ark Lab Huawei Noah's Ark Lab School of Computer Science Faculty of Engineering University of Sydney Central Software Institution Huawei Technologies Key Lab of Machine Perception (MOE) Dept. of Machine Intelligence Peking University

ISBN: (纸本)9781713845393

Transformer models have achieved great progress on computer vision tasks recently. The rapid development of vision transformers is mainly contributed by their high representation ability for extracting informative features from input images. However, the mainstream transformer models are designed with deep architectures, and the feature diversity will be continuously reduced as the dept. increases, i.e., feature collapse. In this paper, we theoretically analyze the feature collapse phenomenon and study the relationship between shortcuts and feature diversity in these transformer models. Then, we present an augmented shortcut scheme, which inserts additional paths with learnable parameters in parallel on the original shortcuts. To save the computational costs, we further explore an efficient approach that uses the block-circulant projection to implement augmented shortcuts. Extensive experiments conducted on benchmark datasets demonstrate the effectiveness of the proposed method, which brings about 1% accuracy increase of the state-of-the-art visual transformers without obviously increasing their parameters and FLOPs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Translate and Summarize Complaints of Patient to Electronic Health Record by BiLSTM-CNN Attention model 12

Translate and Summarize Complaints of Patient to Electronic ...

引用

12th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2019

作者： Song, Haowei Li, Gangmin Hou, Size Qu, Yuan Ying Liang, Hai-Ning Bai, Xuming Xi'an Jiaotong-Liverpool University Dept. Computer Science and Software Engineering Suzhou Jiangsu China Second Affiliated Hospital of Soochow University Dept. Interventional Radiology Suzhou Jiangsu China

ISBN: (纸本)9781728148526

Auto-generation of Electronic Health Record (EHR) is a difficult problem in intelligent medical diagnose and health care. This paper proposes a BiLSTM-CNN attention model which directly reads patients' complaints and generates EHRs. The BiLSTM-CNN attention model is a combination of BiLSTM and CNN model with attention. The attention is achieved through the Encode-Decode model. With the coded input text the BiLSTM-CNN model is trained and used to generate EHRs. The model is validated against reference EHRs which shows satisfactory result. The ROUGE is also used as the evaluation metrics to compare with other baseline models. A brief discussion about the limitations, weakness and the future work of the proposed mode are given. © 2019 IEEE.

关键词： Decoding

来源：评论

学校读者我要写书评

暂无评论

Modified indexing algorithm based on priority queue in metric space for MVP tree 4

Modified indexing algorithm based on priority queue in metri...

引用

4th International Conference on Future Networks and Distributed Systems, ICFNDS 2020

作者： Fomin, Vladimir Aleksandrov, Igor Gallyamov, Denis Kirichek, Ruslan Dept. of Information Systems Herzen State Pedagogical University of Russia Saint Petersburg Russia Dept. of Software Engineering and Computer Science Bonch-Bruevich Saint Petersburg State University of Telecommunications Saint Petersburg Russia Bonch-Bruevich Saint Petersburg State University of Telecommunications Saint Petersburg Russia V. A. Trapeznikov Institute of Control Sciences of Russian Academy of Sciences Moscow Russia

ISBN: (纸本)9781450388863

The Internet of Things (IoT) algorithms process huge amounts of heterogeneous data in real-time. One of the most computationally intensive tasks using cloud technologies is the task of clustering and classifying data. The authors propose to develop an approach to data classification within the "Query by Similarity"paradigm, which uses the technology of data indexing based on Metric Access Methods (MAM). To improve the performance of data indexing, this paper proposes a similar nearest neighbor search method combining a multiple vantage point tree (MVP) and improved algorithms for processing the priority queue of nodes. The following two algorithms for processing the priority queue of nodes were developed: 1) algorithm for all kinds of points-queries, which makes it possible to take into account parent nodes of all higher levels;2) algorithm for grouped based on clustering of points-queries by reusing previously obtained search results. Experimental results confirm the effectiveness of the proposed approaches and algorithms. © 2020 ACM.

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Psychometrics in behavioral software engineering: A methodological introduction with guidelines

arXiv

引用

arXiv 2020年

作者： Graziotin, Daniel Lenberg, Per Feldt, Robert Wagner, Stefan University of Stuttgart Institute of Software Engineering Universitätsstraße 38 Stuttgart70569 Germany Chalmers and the University of Gothenburg Dept. of Computer Science and Engineering GothenbugSE-412 96 Sweden The University of Gothenburg Dept. of Computer Science and Engineering GothenbugSE-412 96 Sweden

A meaningful and deep understanding of the human aspects of software engineering (SE) requires psychological constructs to be considered. Psychology theory can facilitate the systematic and sound development as well as the adoption of instruments (e.g., psychological tests, questionnaires) to assess these constructs. In particular, to ensure high quality, the psychometric properties of instruments need evaluation. In this paper, we provide an introduction to psychometric theory for the evaluation of measurement instruments for SE researchers. We present guidelines that enable using existing instruments and developing new ones adequately. We conducted a comprehensive review of the psychology literature framed by the Standards for Educational and Psychological Testing. We detail activities used when operationalizing new psychological constructs, such as item pooling, item review, pilot testing, item analysis, factor analysis, statistical property of items, reliability, validity, and fairness in testing and test bias. We provide an openly available example of a psychometric evaluation based on our guideline. We hope to encourage a culture change in SE research towards the adoption of established methods from psychology. To improve the quality of behavioral research in SE, studies focusing on introducing, validating, and then using psychometric instruments need to be more common. Copyright © 2020, The Authors. All rights reserved.

关键词： Behavioral research

来源：评论

学校读者我要写书评

暂无评论

引用

2019 ACM Turing Celebration Conference - China, ACM TURC 2019

作者： Li, Xiuhua Wang, Xiaofei Sheng, Zhengguo Hu, Chunqiang Leung, Victor C.M. School of Big Data and Software Engineering Chongqing University Chongqing China School of Computer Science and Technology Tianjin University Tianjin China Dept. of Engineering and Design University of Sussex Falmer Brighton United Kingdom Dept. Electrical and Computer Engineering University of British Columbia Vancouver Canada

ISBN: (纸本)9781450371582

Content requests from mobile users are explosively increasing due to the growing popularity of mobile social activities. However, current mobile network infrastructure cannot effectively support the generated massive mobile data traffic while maintaining consistent and acceptable network performances. To deal with such a serious challenge, caching popular content at the edges of mobile networks has been recognized as a promising solution. In this paper, we introduce the content caching technique in Fog-Cloud based radio access networks for offering joint Fog-enabled and Cloud-enabled data services. Then we propose a collaborative hierarchical Fog-Cloud caching framework based on predicting content popularity with the Auto Regressive model. Our objective is to explore the maximum capacity of the considered network infrastructure by effectively offloading network traffic. Trace-driven evaluations demonstrate the effectiveness of our proposed caching mechanism in terms of traffic offload. © 2019 Association for Computing Machinery.

关键词： Fog

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：