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

1,747 篇 会议
75 册 图书
45 篇 期刊文献

馆藏范围

1,867 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,271 篇 工学
- 1,022 篇 计算机科学与技术...
- 621 篇 软件工程
- 213 篇 光学工程
- 205 篇 电气工程
- 198 篇 信息与通信工程
- 139 篇 生物医学工程（可授...
- 137 篇 生物工程
- 122 篇 控制科学与工程
- 51 篇 机械工程
- 48 篇 电子科学与技术（可...
- 40 篇 化学工程与技术
- 36 篇 仪器科学与技术
- 22 篇 安全科学与工程
- 19 篇 建筑学
- 19 篇 土木工程
- 17 篇 动力工程及工程热...
- 15 篇 材料科学与工程（可...
692 篇 理学
- 350 篇 数学
- 277 篇 物理学
- 191 篇 生物学
- 108 篇 统计学（可授理学、...
- 44 篇 化学
- 30 篇 系统科学
176 篇 管理学
- 113 篇 图书情报与档案管...
- 74 篇 管理科学与工程(可...
- 21 篇 工商管理
118 篇 医学
- 91 篇 临床医学
- 56 篇 基础医学(可授医学...
- 26 篇 药学(可授医学、理...
27 篇 法学
- 26 篇 社会学
17 篇 农学
12 篇 教育学
7 篇 经济学
7 篇 军事学
5 篇 艺术学
4 篇 文学

主题

425 篇 pattern recognit...
191 篇 pattern recognit...
68 篇 artificial intel...
64 篇 feature extracti...
48 篇 neural networks
42 篇 pattern matching
35 篇 face recognition
35 篇 data mining
33 篇 local binary pat...
33 篇 computer imaging...
30 篇 bioinformatics
27 篇 support vector m...
25 篇 image analysis
24 篇 image processing
24 篇 character recogn...
23 篇 image segmentati...
22 篇 deep learning
22 篇 machine learning
22 篇 image recognitio...
21 篇 pattern classifi...

机构

18 篇 national laborat...
8 篇 chinese acad sci...
6 篇 tsinghua univers...
5 篇 indian statistic...
5 篇 pattern recognit...
5 篇 university of ch...
4 篇 department of co...
4 篇 rehabil inst chi...
4 篇 school of comput...
4 篇 concordia univ c...
4 篇 shanghai jiao to...
4 篇 university of so...
3 篇 centre for patte...
3 篇 univ chinese aca...
3 篇 institute of ima...
3 篇 southwest jiaoto...
3 篇 pattern recognit...
3 篇 chinese acad sci...
3 篇 school of comput...
3 篇 institute for pa...

作者

16 篇 suen ching y.
11 篇 xu bo
8 篇 caelli terry
8 篇 tan tieniu
8 篇 yang jie
7 篇 levi j. hargrove
6 篇 hargrove levi j.
6 篇 zhao jun
6 篇 jain anil k.
6 篇 sun zhenan
6 篇 suen cy
6 篇 ney hermann
6 篇 kropatsch walter...
6 篇 huang taiyi
5 篇 zhou jie
5 篇 de-shuang huang
5 篇 liu cheng-lin
5 篇 zong chengqing
5 篇 oommen b.j.
5 篇 ablameyko s.

语言

1,845 篇 英文
18 篇 其他
5 篇 中文

检索条件"任意字段=6th IAPR International Conference on Pattern Recognition in Bioinformatics"

共 1867 条记录，以下是21-30 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：

Deep Multi-order Context-Aware Kernel Network for Multi-label Classification 27th

Deep Multi-order Context-Aware Kernel Network for Multi-lab...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Jiu, Mingyuan Zhu, Hailong Sahbi, Hichem School of Computer and Artificial Intelligence Zhengzhou University Zhengzhou China Engineering Research Center of Intelligent Swarm Systems Ministry of Education Zhengzhou University Zhengzhou China National Supercomputing Center in Zhengzhou Zhengzhou China Sorbonne University CNRS LIP6 Paris75005 France

ISBN: (纸本)9783031781216

Multi-label classification is a challenging task in pattern recognition. Many deep learning methods have been proposed and largely enhanced classification performance. However, most of the existing sophisticated methods ignore context in the models’ learning process. Since context may provide additional cues to the learned models, it may significantly boost classification performances. In this work, we make full use of context information (namely geometrical structure of images) in order to learn better context-aware similarities (a.k.a. kernels) between images. We reformulate context-aware kernel design as a feed-forward network that outputs explicit kernel mapping features. Our obtained context-aware kernel network further leverages multiple orders of patch neighbors within different distances, resulting into a more discriminating Deep Multi-order Context-aware Kernel Network (DMCKN) for multi-label classification. We evaluate the proposed method on the challenging Corel5K and NUS-WIDE benchmarks, and empirical results show that our method obtains competitive performances against the related state-of-the-art, and both quantitative and qualitative performances corroborate its effectiveness and superiority for multi-label image classification. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Religious Sentiment Analysis and Detection on Social Media 6th

Religious Sentiment Analysis and Detection on Social Media

引用

6th international conference on Computational Intelligence in pattern recognition, CIPR 2024

作者： Riskhan, Basheer Hossain, Md Shakil Ashfaq, Farzeen Albukhary International University Kedah Malaysia School of Computer Science SCS Taylors University Subang Jaya Malaysia

ISBN: (纸本)9789819780891

this research addresses the rising concern of religious hate speech on Facebook, employing a comprehensive methodology to create a dataset by annotating statements from diverse religious backgrounds. After preprocessing steps like noise removal and tokenization, various linguistic features, including character N-grams, TF-IDF-weighted N-grams, and text quality indicators, were utilized. Multiple supervised learning algorithms, such as logistic regression, linear SVC, random forest, Naive Bayes, decision tree, and a GRU-based neural network model, were examined for optimal performance. Evaluation metrics like accuracy, precision, recall, and F1 score were employed. the study illuminates the prevalence and characteristics of religiously motivated hate speech on social media, emphasizing the importance of algorithm selection based on desired performance metrics. this research offers a valuable tool for academics and platform management to effectively identify and mitigate the impact of religious hate speech on digital platforms, supporting ongoing efforts to combat online discrimination. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Extending 6D Object Pose Estimators for Stereo Vision 4th

Extending 6D Object Pose Estimators for Stereo Vision

引用

4th international conference on pattern recognition and Artificial Intelligence, ICPRAI 2024

作者： Pöllabauer, thomas Emrich, Jan Knauthe, Volker Kuijper, Arjan Fraunhofer Institute for Computer Graphics Research IGD Darmstadt Fraunhoferstraße 5 Darmstadt Germany Technical University Darmstadt Karolinenplatz 5 Darmstadt Germany

Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task. However, recent methods60;for directly regressing poses from RGB images using dense features60;have achieved state-of... 详细信息

ISBN: (纸本)9789819787043

Estimating the 6D pose of objects accurately, quickly, and robustly remains a difficult task. However, recent methods for directly regressing poses from RGB images using dense features have achieved state-of-the-art results. Stereo vision, which provides an additional perspective on the object, can help reduce pose ambiguity and occlusion. Moreover, stereo can directly infer the distance of an object, while mono-vision requires internalized knowledge of the object’s size. To extend the state-of-the-art in 6D object pose estimation to stereo, we created a BOP compatible stereo version of the YCB-V dataset called YCB-V DS and extended multiple state-of-the-art pose estimator algorithms to be applicable to stereo. Our method outperforms state-of-the-art 6D pose estimation algorithms by utilizing stereo vision and can easily be adopted for other dense feature-based algorithms. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Stereo vision

来源：评论

学校读者我要写书评

暂无评论

Virtual DSA for Learning Contrast Agent Dynamics in Projection Space 4th

Virtual DSA for Learning Contrast Agent Dynamics in Project...

引用

4th international Workshop on Imaging and Treatment Challenges, SWITCH 2024, and 6th international Challenge on Ischemic Stroke Lesion Segmentation Challenge, ISLES 2024, Held in Conjunction with Medical Image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Maul, Noah Birkhold, Annette thies, Mareike Vysotskaya, Nastassia Wagner, Fabian Pfaff, Laura Kowarschik, Markus Maier, Andreas Pattern Recognition Lab Friedrich-Alexander Universitaet Erlangen Germany Siemens Healthineers AG Forchheim Germany

ISBN: (纸本)9783031811005

Digital Subtraction Angiography (DSA) is a well-established imaging modality supporting treatment and diagnosis of vascular pathologies. Various clinical DSA acquisition protocols exist that provide qualitative blood flow information for vascular diseases. Velocity quantification algorithms primarily rely on tracking a contrast agent (CA) bolus through the vasculature. However, the true CA velocity is fast compared to the frame rate of angiographic images. therefore, high blood velocities pose a challenge for these methods, as the bolus may flow through long vessel segments between two subsequent DSA frames. this problem can be mitigated by increasing the temporal resolution, or equivalently, the projection image frame rate. We propose a simulation-informed neural network approach to synthetically double the projection frame rate without additional patient dose. We evaluate the quality of the synthesized projection images and show the impact on bolus tracking algorithms. Synthesized projection images can be predicted with a mean absolute percentage error of 2.5±0.8 % in the inflow phase. Further, the synthesized projections qualitatively capture bolus dynamics more accurately compared to linear interpolation. Conceptually, our method allows extension to predicting multiple intermediate projection frames, which can be a valuable tool toward accurate quantitative vascular flow estimation. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Memorable Vibration pattern Design Based on Writing pattern 14th

Memorable Vibration Pattern Design Based on Writing Pattern

引用

14th international conference on Human Haptic Sensing and Touch Enabled Computer Applications, EuroHaptics 2024

作者： Wong, Zi Ying Yoo, Yongjae Kim, Sang-Youn Interaction Lab Future Convergence Engineering Korea University of Technology and Education Cheonan-si Korea Republic of Department of Applied Artificial Intelligence Hanyang University Ansan-si Korea Republic of

ISBN: (纸本)9783031700576

In this paper, we presented memorable vibration patterns representing digit 0 to 9, which were designed based on writing patterns. Based on the collection of 50 participants’ handwriting pattern of 10 digits we gathered, we designed two different types of vibration patterns to generate the digits: vibrotactile flows and discrete vibrotactile simulations. In the user study, we evaluated identifiability and learnability of the patterns we generated. First, participants successfully identified 69.4% of vibrotactile flow patterns and 77.5% with discrete vibrotactile simulations in their first session of 30 trials without training. the average recognition rate in their last session 30 trials increased to 83.6% for vibrotactile flows and 91.1% for discrete vibrotactile simulations after two sessions (60 trials), shows the ease of learning the vibration pattern. We also observed a lasting learning effect of both types of vibrotactile patterns in a delayed recall test was conducted 72–96 h after the first user study – 90.0% success rate for vibrotactile flows and 91.4% for discrete vibrations. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Digits Memorable Vibration pattern Writing pattern

来源：评论

学校读者我要写书评

暂无评论

Plant Stress Classification with Deep Learning Models Using STFT-Based 2D Representation of 6-Channel 500 kHz Plant Sound 4th

Plant Stress Classification with Deep Learning Models Using ...

引用

4th international conference on pattern recognition and Artificial Intelligence, ICPRAI 2024

作者： Baek, Eu-Tteum Yoon, Hye-Seong AI&Bigdata Honam University Gwangju Korea Republic of

ISBN: (纸本)9789819787043

Plant stress is a physiological response triggered by various environmental factors, such as extreme weather conditions, diseases, or mechanical disturbances. Monitoring and classifying plant stress are crucial for assessing the overall health of vegetation and implementing timely interventions to ensure sustainable agricultural practices. However, estimating the magnitude of stress proves challenging due to a lack of comprehensive datasets and limited technological capabilities. therefore, in this study, we present a plant classification method leveraging a 2D representation based on Short-Time Fourier Transform of 6-channel 500 kHz sounds, recorded in scenarios such as tree cutting, drought, and other common environmental conditions. the experimental results demonstrate that our proposed method effectively predicts stress factors;however, due to a lack of a comprehensive dataset and limitations in data quality, the accuracy is slightly lower. these endeavors are expected to offer significant assistance in the analysis and judgment of plant stress. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： deep learning plant stress STFT

来源：评论

学校读者我要写书评

暂无评论

6-DOF Motion Blur Synthesis and Performance Evaluation of Object Detection 27th

6-DOF Motion Blur Synthesis and Performance Evaluation of Ob...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Yang, Hanjin Li, Feng Zhang, Lei School of Computer Science and Technology Donghua University Shanghai201600 China National Innovation Center of Advanced Dyeing and Finishing Technology Shandong Tai’an271000 China

ISBN: (纸本)9783031784439

the current state-of-the-art deep learning vision networks commonly employs synthetic approaches for data augmentation when confronted with scenes requiring motion blur. However, existing blur synthesis methods often fall short in accurately simulating motion blur as observed in real-world scenarios, consequently hindering the generalization capability of trained deep visual networks to real-world applications, a phenomenon known as domain shift effects [1]. To address this problem, we propose a novel non-uniform motion blur synthesis method for data augmentation. First, we randomly generate the camera’s motion trajectory using a more general six-degree-of-freedom (6-DOF) camera motion model, and then map this trajectory to pixel-level blur kernels. To efficiently perform spatially varying convolution, we employ non-negative matrix factorization (NMF) to decompose those blur kernels into a set of kernel basis and their corresponding mixing coefficients. this enables parallel execution of spatial variation convolutions, thereby significantly improving the efficiency of blur synthesis. Our experiments demonstrate consistently superior results of the proposed method on publicly available real datasets RealBlur, as well as synthetic datasets GoPro and REDS. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Non-negative matrix factorization

来源：评论

学校读者我要写书评

暂无评论

Efficient Detection of Fake Twitter Profiles on Social Media through Hybrid Deep Learning Model 6th

Efficient Detection of Fake Twitter Profiles on Social Media...

引用

6th international conference on Computational Intelligence in pattern recognition, CIPR 2024

作者： Bibi, Haleema Ashraf, Humaira Jhanjhi, N.Z. Department of Computer Science and Information Technology International Islamic University Islamabad Pakistan School of Computer Science SCS Taylor’s University Subang Jaya Malaysia

ISBN: (纸本)9789819780891

Social media is an interactive and reliable tool used for communication among people around the world. It provides a facility for people to make accounts of it and to share their personal ideas, photos, interests, and other expressions. through social media, people can easily interact with each other. Everyone is in contact with their loved ones. In social media mostly used applications are Facebook, Instagram, WhatsApp, Twitter, LinkedIn, and YouTube. Due to the ever-increasing popularity of social media, it has become an ideal platform for the creation of fake accounts by spammers for undesirable activities. Spammers make fake accounts on social media to create panic among people. In this research, we aimed to detect fake profiles in one of the most used content-sharing applications Twitter. We have used the MIB Twitter dataset. Based on user-based attributes we have implemented deep learning techniques LSTM and GRU, and we proposed a hybrid LSTM-GRU. through experimental results, we gain better accuracies and small losses with deep learning techniques than machine learning algorithms for efficient detection of fake Twitter profiles. © the Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Tweets

来源：评论

学校读者我要写书评

暂无评论

Moiré pattern Detection: Stability and Efficiency with Evaluated Loss Function 27th

Moiré Pattern Detection: Stability and Efficiency with Eval...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Li, Zhuocheng Shen, Xizhu Luan, Simin Guo, Shuwei Boukhers, Zeyd Sui, Wei Wang, Yuyi Yang, Cong Soochow University Suzhou China Fraunhofer Institute for Applied Information Technology Sankt Augustin Germany University Hospital of Cologne Cologne Germany CRRC Zhuzhou Institute Co. Ltd. Hunan Zhuzhou412001 China

ISBN: (纸本)9783031784439

Detecting moiré patterns in digital images is essential as it offers insights for assessing image integrity and undertaking demoiréing processes. MoireDet is a simple and efficient moiré pattern detection neural network designed explicitly for moiré edge map estimation [23]. However, the random feature mapping of the Performer significantly affects the prediction for continuous video frames. this paper introduces MoireDet+ based on existing work, which introduces Vision Transformer into moiré-related tasks. MoireDet+ utilizes a mixed-encoder as a backbone, integrating both high- and low-level vision encoders in an FPN-like method, along with a spatial encoder to extract the complex spatial features of moiré patterns. Furthermore, we produce a rapid approximation-based evaluation method to aid loss function design in image restoration and similar tasks. MoireDet+ reaches a state-of-the-art level on mainstream datasets, reducing time costs by 18% compared to MoireDet and other baselines with comparable performance levels. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Restoration

来源：评论

学校读者我要写书评

暂无评论

Enhancing Bengali Text-to-Speech Synthesis through Transformer-Driven Text Normalization 27th

Enhancing Bengali Text-to-Speech Synthesis Through Transform...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Ghosh, Krishnendu Patra, Munmun Dey, Eshita Indian Institute of Information Technology Dharwad Karnataka Dharwad India Techno International New Town West Bengal Kolkata India

this paper presents a transformer-driven approach60;for non-standard word (NSW) normalization in Bengali text-to-speech synthesis (TTS) systems. Our text normalization (TN) approach60;is realized over three modu... 详细信息

ISBN: (纸本)9783031784941

this paper presents a transformer-driven approach for non-standard word (NSW) normalization in Bengali text-to-speech synthesis (TTS) systems. Our text normalization (TN) approach is realized over three modules: pre-processing, NSW classification, and token-to-word expansion. the pre-processing module tokenizes the input sentences into words. the non-standard words are classified based on their format and other discriminative features in the next module. Apart from our proposed transformer-based approach, the present study explored four baseline TN approaches: rule-based, Conditional Random Field (CRF)-based, Long Short-Term Memory (LSTM)-based, and biLSTM-based. Based on the predicted types of the NSWs, standard words (SWs) are generated through token-to-word expansion using hand-crafted expansion rules. the performance of these five TN approaches is assessed on a corpus of around 6,000 NSWs, consisting of 6 initial and 14 final NSW types. the performances of these approaches are assessed using measures representing (i) direct accuracy and (ii) enhancements in text-to-speech synthesis systems. Based on direct accuracy, our proposed approach predicted correct NSW types for about 92% of cases. this performance is around 2% better than the performance of a rule-based approach. On the other hand, application-based measures guarantee that the generated utterances (i) sound natural and (ii) improve the quality of speech synthesis systems. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Speech enhancement

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187页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：