检索结果-内蒙古大学图书馆

您好，读者！请登录

内蒙古大学图书馆

首页
概况
党建
资源
服务
科研支持
- 论文收录引用证明
- 科技查新
知识产权
档案馆
帮助

咨询与建议

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

您的常用邮箱：*

您的手机号码：*

问题描述：

当前已输入0个字，您还可以输入200个字

全部搜索
期刊论文
图书
学位论文
标准
纸本馆藏
外文资源发现
数据库导航
超星发现

高级检索

时间限定

出版年份：

文献类型

图书期刊文献学位论文多媒体

馆藏选择

电子馆藏纸本馆藏

核心期刊

全部期刊 SCI 收录期刊 SSCI 收录期刊 EI 收录期刊 CSCD 收录期刊 CSSCI 收录期刊

语言

中文英文

文献类型

期刊文献图书学位论文标准纸本馆藏

帮助

文字说明：

T=题名（书名、题名），A=作者（责任者），K=主题词，P=出版物名称，PU=出版社名称，O=机构（作者单位、学位授予单位、专利申请人），L=中图分类号，C=学科分类号，U=全部字段，Y=年（出版发行年、学位年度、标准发布年）

检索规则说明：

AND代表“并且”；OR代表“或者”；NOT代表“不包含”；(注意必须大写,运算符两边需空一格)

检索范例：

范例一：(K=图书馆学 OR K=情报学) AND A=范并思 AND Y=1982-2016
范例二：P=计算机应用与软件 AND (U=C++ OR U=Basic) NOT K=Visual AND Y=2011-2016

分类表

所选分类

>> <<

限定检索结果

文献类型

282,603 篇 会议
17,623 册 图书

馆藏范围

299,995 篇 电子文献
263 种 纸本馆藏

日期分布

学科分类号

281,828 篇 工学
- 277,751 篇 计算机科学与技术...
- 67,717 篇 软件工程
- 14,895 篇 信息与通信工程
- 8,439 篇 电气工程
- 8,089 篇 控制科学与工程
- 4,688 篇 生物医学工程（可授...
- 974 篇 生物工程
- 827 篇 光学工程
- 606 篇 机械工程
- 568 篇 仪器科学与技术
- 494 篇 测绘科学与技术
- 492 篇 交通运输工程
35,837 篇 理学
- 28,677 篇 数学
- 5,532 篇 生物学
- 1,683 篇 物理学
- 1,126 篇 统计学（可授理学、...
- 517 篇 系统科学
- 482 篇 化学
30,399 篇 医学
- 22,124 篇 临床医学
- 9,245 篇 特种医学
- 3,035 篇 基础医学(可授医学...
- 1,217 篇 医学技术（可授医学...
10,775 篇 管理学
- 6,492 篇 管理科学与工程(可...
- 3,323 篇 图书情报与档案管...
- 1,770 篇 工商管理
- 743 篇 公共管理
4,314 篇 教育学
- 4,041 篇 教育学
2,337 篇 法学
- 1,997 篇 社会学
1,680 篇 文学
- 1,179 篇 新闻传播学
- 526 篇 外国语言文学
467 篇 艺术学
372 篇 经济学
149 篇 农学
98 篇 历史学
65 篇 哲学
24 篇 军事学

主题

10,830 篇 artificial intel...
4,631 篇 computer communi...
3,945 篇 deep learning
3,861 篇 information syst...
3,741 篇 computers
3,637 篇 software enginee...
3,332 篇 machine learning
3,243 篇 algorithm analys...
3,223 篇 semantics
2,288 篇 information stor...
2,190 篇 pattern recognit...
1,834 篇 neural networks
1,820 篇 user interfaces ...
1,820 篇 image processing...
1,805 篇 database managem...
1,794 篇 logics and meani...
1,777 篇 mathematical log...
1,770 篇 cryptography
1,757 篇 software enginee...
1,707 篇 data mining and ...

机构

651 篇 univ chinese aca...
541 篇 carnegie mellon ...
403 篇 univ chinese aca...
359 篇 univ calif berke...
353 篇 shanghai jiao to...
318 篇 stanford univ st...
307 篇 chinese acad sci...
288 篇 shanghai jiao to...
285 篇 inria
248 篇 tech univ munich...
241 篇 tech univ darmst...
225 篇 swiss fed inst t...
212 篇 univ waterloo wa...
207 篇 nanjing univ sta...
203 篇 tsinghua univ pe...
199 篇 ist austria klos...
198 篇 natl univ singap...
186 篇 mit cambridge ma...
185 篇 univ maryland co...
183 篇 chinese acad sci...

作者

212 篇 shen dinggang
104 篇 navab nassir
98 篇 zhang lei
94 篇 wang wei
92 篇 susilo willy
85 篇 liu yang
83 篇 rueckert daniel
81 篇 wang lei
81 篇 wang xin
76 篇 auer soeren
66 篇 golland polina
64 篇 weske mathias
61 篇 zhang yong
54 篇 liu wei
52 篇 zhang li
51 篇 zhou jie
49 篇 jiang xiaoyi
47 篇 zhang tao
47 篇 zhang yu
47 篇 ishai yuval

语言

298,284 篇 英文
1,937 篇 中文
1 篇 加泰罗尼亚文
1 篇 法文

检索条件"丛书名=Lecture notes in computer science,"

共 300226 条记录，以下是4691-4700 订阅

全选清除本页清除全部题录导出标记到"检索档案"

详细简洁

排序：

Under-Sampling Strategies for Better Transformer-Based Classifications Models 15th

Under-Sampling Strategies for Better Transformer-Based Class...

引用

15th International Conference of the Cross-Language-Evaluation-Forum-Association (CLEF)

作者： Sawinski, Marcin Wecel, Krzysztof Ksiezniak, Ewelina Poznan Univ Econ & Business PL-61875 Poznan Poland

ISBN: (纸本)9783031717352;9783031717369

This paper presents findings from the Check-That! Lab Task 1B-English submission at CLEF 2023. The research developed a method for evaluating the check-worthiness of short English texts. The first iteration focused on identifying optimal model architectures and adaptation techniques, while the second iteration involved curating the dataset for improved results. The study included fine-tuning several GPT and BERT models, applying zero-shot, few-shot, and Chain-of-Thought prompting strategies, and utilizing dataset sampling techniques informed by quality and training dynamics metrics. Team achieved first place in the competition by fine-tuning the OpenAI GPT-3 curie model. Findings suggest that fine-tuned BERT models can perform comparably to GPT models, but dataset curation was pivotal in obtaining superior results across various model architectures.

关键词： check-worthiness GPT BERT DeBERTa dataset curation class imbalance under-sampling model training

来源：评论

学校读者我要写书评

暂无评论

Minimizing the Cost of Leveraging Influencers in Social Networks: IP and CP Approaches 1

引用

21st International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR)

作者： Pereira, Felipe de C. de Rezende, Pedro J. Yunes, Tallys Univ Campinas Unicamp Inst Comp Campinas SP Brazil Univ Miami Miami Herbert Business Sch Coral Gables FL 33124 USA

ISBN: (数字)9783031605994

ISBN: (纸本)9783031606014;9783031605994

In this paper, we introduce and study mathematical programming formulations for the Least Cost Directed Perfect Awareness Problem (LDPAP), an NP-hard optimization problem that arises in the context of influence marketing. In the LDPAP, we seek to identify influential members of a given social network that can disseminate a piece of information and trigger its propagation throughout the network. The objective is to minimize the cost of recruiting the initial spreaders while ensuring that the information reaches everyone. This problem has been previously modeled as two different integer programming formulations that were tested on a collection of 300 small synthetic instances. In this work, we propose two new integer programming models and three constraint programming formulations for the LDPAP. We also present preprocessing techniques capable of significantly reducing the sizes of these models. To investigate and compare the efficiency and effectiveness of our approaches, we perform a series of experiments using the existing small instances and a new publicly available benchmark of 14 large instances. Our findings yield new optimal solutions to 185 small instances that were previously unsolved, tripling the total number of instances with known optima. Regarding both small and large instances, our contributions include a comprehensive analysis of the experimental results and an evaluation of the performance of each formulation in distinct scenarios, further advancing our understanding of the LDPAP toward the design of exact approaches for the problem.

关键词： Least Cost Directed Perfect Awareness Problem Influence Marketing Social Networks Integer Programming Constraint Programming

来源：评论

学校读者我要写书评

暂无评论

LISAScore: Exploring Linear Sum Assignment on BERTScore 29th

LISAScore: Exploring Linear Sum Assignment on BERTScore

引用

29th International Conference on Applications of Natural Language to Information Systems (NLDB)

作者： Mander, Stephen Phillips, Jesse Univ Lancaster Sch Comp & Commun Lancaster England

ISBN: (纸本)9783031702419;9783031702426

Metrics play a crucial role in evaluating the performance of machine learning models. In the context of Natural Language Processing (NLP) tasks, such as text summarization and machine translation, Natural Language Generation (NLG) metrics such as Bleu and Rouge have been widely used. However, these metrics are based on n-gram matching and do not capture the semantic similarity between the generated and reference texts. To address this, BERTScore has emerged as a popular evaluation metric that uses a pre-trained Large Language Model (LLM) to measure semantic similarity between two sentences. Unlike n-grambased metrics, BERTScore uses the contextual and semantic embeddings of words, allowing flexible semantic evaluation. We outline a number of hypotheticals in which the dependence of BERTScore on token embedding cosine similarity may be exploited. The comparative distribution of BERTScores on a set of reference - prediction pairs mean that results often scale differently with training to traditional metrics, which requires more expertise when interpreting results. In this paper, we demonstrate an improvement to BERTScore, using accelerated Linear Sum Assignment approximations that reduce the mean score while maintaining accuracy. Linear Sum Assignment allows BERTScore to be more easily understood in the context of other NLG metrics, by changing the distribution of the metric.

关键词： NLG Metrics BERTScore Linear Sum Assignment

来源：评论

学校读者我要写书评

暂无评论

Shared Nearest Neighbor Calibration for Few-Shot Classification 6th

Shared Nearest Neighbor Calibration for Few-Shot Classificat...

引用

6th Chinese Conference on Pattern Recognition and computer Vision (PRCV)

作者： Qi, Rundong Ning, Sa Jiang, Yong Zhang, Yuwei Yang, Wenyu Southwest Univ Sci & Technol Sch Comp Sci & Technol Mianyang 621010 Sichuan Peoples R China

ISBN: (纸本)9789819984619;9789819984626

Few-shot classification aims to classify query samples using very few labeled examples. Most existing methods follow the Prototypical Network to classify query samples by matching them to the nearest centroid. However, scarce labeled examples tend to bias the centroids, which leads to query samples matching the wrong centroids. In this paper, we address the mismatching problem of centroids and query samples by optimizing the matching strategy. The idea is to combine the Shared Nearest Neighbor similarity with cosine similarity proportionally to calibrate the matching results of the latter. Furthermore, we also improve a bias-diminishing approach to increase the number of shared nearest neighbors between query samples and the centroid of their class. We validate the effectiveness of our method with extensive experiments on three few-shot classification datasets: miniImageNet, tieredImageNet, and CUB-200-2011 (CUB). Moreover, our method has achieved competitive performance across different settings and datasets.

关键词： Few-shot classification metric learning transductive

来源：评论

学校读者我要写书评

暂无评论

Modularizing Directed Greybox Fuzzing for Binaries over Multiple CPU Architectures 21st

Modularizing Directed Greybox Fuzzing for Binaries over Mult...

引用

21st Conference on Detection of Intrusions and Malware and Vulnerability Assessment (DIMVA)

作者： Benahmed, Sofiane Qasem, Abdullah Lounis, Anis Debbabi, Mourad Concordia Univ 1515 Ste Catherine St W Montreal PQ Canada

ISBN: (纸本)9783031641701;9783031641718

Directed Greybox Fuzzing has proven effective in vulnerability detection areas such as bug reproduction and patch testing. However, existing directed fuzzers are often difficult to customize, lack modularity and have limited binary support. This constrains their usability on complex software or when the source code is unavailable;a challenge encountered when fuzzing embedded systems. This article addresses these limitations by introducing the Directed Fuzzing Toolkit (DRIFT) as a platform for directed fuzzing within the modular framework LibAFL. DRIFT modularizes techniques from the state-of-the-art directed fuzzer AFLGo and adapts them for binary applications thereby augmenting LibAFL's highly customizable fuzzers with directed fuzzing capabilities. Additionally, by leveraging Ghidra's analysis, DRIFT achieves architecture agnostic static analysis, opening doors for DGF to tackle previously challenging scenarios. Our evaluation of DRIFT shows a 90% correlation in static analysis metrics over binary compared to its source-code counterpart. Fuzzing performance was also notable despite operating over emulation. In benchmarks, DRIFT's performance exceeds the original fuzzer with up to doubled bug discovery rates and 9-40x faster exploitation times of target bugs. These results are attributed to the toolkit's modular design and its integration with LibAFL. Additionally, DRIFT includes a profiling platform for DGF metrics and is incorporated with the Magma benchmark. Together, these features position DRIFT as a practical advancement in directed fuzzing within LibAFL.

关键词： Fuzzing Vulnerability Discovery Dynamic Analysis LibAFL Greybox Fuzzing Multiple CPU Architectures

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Techniques for Skeleton-Based Action Recognition: A Survey 24th

Deep Learning Techniques for Skeleton-Based Action Recogniti...

引用

24th International Conference on Computational science and Its Applications (ICCSA)

作者： Pham, Dinh-Tan Vietnam Natl Univ Int Sch Hanoi Vietnam

ISBN: (纸本)9783031646072;9783031646089

Interpreting human behavior from entirely performed actions is called human action recognition (HAR). HAR applications rapidly expand into robotics, CCTV surveillance, self-driving vehicles, gaming, and video retrieval. Among different data modalities, skeleton data offers compact representation and computational efficiency. In recent years, much work has gone into developing a robust and accurate deep-learning framework for skeleton-based HAR. The paper reviews state-of-the-art methods for skeleton-based HAR. The survey also summarizes evaluation results on a large-scale benchmark dataset. Trends in action recognition research are discussed.

关键词： action recognition skeleton data deep learning

来源：评论

学校读者我要写书评

暂无评论

CWordTM: Towards a Topic Modeling Toolkit from Low-Code to Pro-Code 29th

CWordTM: Towards a Topic Modeling Toolkit from Low-Code to P...

引用

29th International Conference on Applications of Natural Language to Information Systems (NLDB)

作者： Cheng, Wing-Fat Johnny Hong Kong Inst Informat Technol HKIIT Kowloon Hong Kong Peoples R China

ISBN: (纸本)9783031702419;9783031702426

Topic modeling is a widely used technique in Natural Language Processing (NLP) for extracting and uncovering latent thematic patterns in a collection of documents. However, working with topic modeling algorithms requires technical skills that may hinder the novices. This demo paper presents CWordTM (CWordTM stands for ChineseWord TopicModeling, where "Word" refers to the Word, i.e., the Holy Bible / Scripture.), an open-source Python toolkit designed to simplify the topic modeling process and some other NLP tasks. Although the toolkit offers the Holy Bible as a sample corpus, it works on other possible text data.

关键词： topic modeling BERTopic LDA NMF NLP Holy Bible pre-packaging low-code pro-code CWordTM

来源：评论

学校读者我要写书评

暂无评论

A Summary of the Workshop on Designing for Map-Based Interfaces and Interactions 19th

A Summary of the Workshop on Designing for Map-Based Interfa...

引用

19th International-Federation-for-Information-Processing-Technical-Committee-13 (IFIP TC13) International Conference on Human-computer Interaction (INTERACT)

作者： Masoodian, Masood Luz, Saturnino Aalto Univ Sch Arts Design & Architecture Espoo Finland Univ Edinburgh Usher Inst Edinburgh Scotland

ISBN: (纸本)9783031616976;9783031616983

Over the past few centuries maps have continued to play many different roles as tools used for guiding and coordinating all kinds of human activities. In modern times, maps are also used as the basis for a range of interactive tools, applications and visualizations. Despite this, there are not many venues for coordinating map-related research, design, and professional practices. Therefore, this workshop aimed to bring together researchers, designers and practitioners interested in maps and map-like visualizations as the underlying physical, theoretical, or metaphorical framework for designing interfaces and interactions. This workshop created a common ground and a collaborative space for sharing design, research, and practical expertise to aid its participants with creating novel future map-based designs across a number of fields, including visualization, visual design, interaction design, user interface design, and cartography. In this paper, we summarise the contributions made to this workshop by its participants, and provide a brief overview of its activities and outcomes.

关键词： Map visualizations map-like visualizations visualizations visual design user interface design interaction design cartography

来源：评论

学校读者我要写书评

暂无评论

A New Method "ProjectionP" for Table Structure Recognition 23rd

A New Method "ProjectionP" for Table Structure Recognition

引用

23rd International Conference on computer Information Systems and Industrial Management (CISIM)

作者： Marczak, Pawel Omieljanowicz, Miroslaw Broniewskiego 5-75 PL-15748 Bialystok Poland Bialystok Tech Univ Wiejska 45A PL-15385 Bialystok Poland

ISBN: (纸本)9783031711145;9783031711152

This paper introduces computer vision techniques to address the challenge of analyzing tabular data in digital documents. It details the research and experiments conducted by the authors aimed at automating the invoice registration process within the accounting system of a particular private company. Based on the results obtained, the authors assert that in certain contexts, pattern recognition processing techniques can continue to be effectively utilized for this problem, providing commercial benefits while circumventing some of the limitations inherent in newer, high-performance deep learning approaches. The article shows an overview of the latest advancements in the field and presents the authors' proposed table structure recognition (TSR) algorithm, which is based on the typical profile-projection approach. It also features comparison of the developed TSR algorithm with selected methods described in the literature, undertaking a verification of its efficacy using a dataset of reals documents derived from the accounting department of a private company.

关键词： Image processing Table structure recognition Pattern recognition OCR

来源：评论

学校读者我要写书评

暂无评论

Group Perception Based Self-adaptive Fusion Tracking 40th

Group Perception Based Self-adaptive Fusion Tracking

引用

40th computer Graphics International Conference (CGI)

作者： Xing, Yiyang Wang, Shuai Zhang, Yang Zhao, Shuangye Wu, Yubin Shen, Jiahao Sheng, Hao Beihang Univ Sch Comp Sci & Engn State Key Lab Virtual Real Technol & Syst Beijing 100191 Peoples R China Beihang Univ Zhongfa Aviat Inst Hangzhou 311115 Peoples R China Beijing Univ Chem Technol Coll Informat Sci & Technol Beijing 100029 Peoples R China

ISBN: (纸本)9783031500787;9783031500770

Multi-object tracking (MOT) is an important and representative task in the field of computer vision, while tracking-by-detection is the most mainstream paradigm for MOT, so that target detection quality, feature representation ability, and association algorithm greatly affect tracking performance. On the one hand, multiple pedestrians moving together in the same group maintain similar motion pattern, so that they can indicate each other's moving state. We extract groups from detections and maintain the group relationship of trajectories in tracking. We propose a state transition mechanism to smooth detection bias, recover missing detection and confront false detection. We also build a two-level group-detection association algorithm, which improves the accuracy of association. On the other hand, different areas of the tracking scene have diverse and varying impact on the detections' appearance feature, which weakens the appearance feature's representation ability. We propose a self-adaptive feature fusion strategy based on the tracking scene and the group structure, which can help us to get fusion feature with stronger representative ability to use in the trajectory-detection association to improve tracking performance. To summary, in this paper, we propose a novel Group Perception based Self-adaptive Fusion Tracking (GST) framework, including Group concept and Group Exploration Net, Group Perception based State Transition Mechanism, and Self-adaptive Feature Fusion Strategy. Experiments on the MOT17 dataset demonstrate the effectiveness of our method. The method achieves competitive results compared to the state-of-the-art methods.

关键词： Multi-object tracking (MOT) Group perception Self-adaptive Feature fusion

来源：评论

学校读者我要写书评

暂无评论

没有更多数据了...

全选清除本页清除全部题录导出标记到“检索档案”

共500页 << < 466 467 468 469 470 471 472 473 474 475 > >>

检索报告对象比较合并检索0

隐藏清空

合并搜索

回到顶部

执行限定条件

内容：

评分：

请选择保存的检索档案：

请选择收藏分类：

订阅名称：

通借通还

温馨提示：

图书名称：

借书校区：

取书校区：

手机号码：

邮箱地址：

一卡通帐号：

电话和邮箱必须正确填写，我们会与您联系确认。

联系人：

所在院系：

联系邮箱：

联系电话：

内蒙古自治区呼和浩特市赛罕区大学西街235号邮编: 010021

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：