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

1,599 篇 会议
82 册 图书
82 篇 期刊文献

馆藏范围

1,763 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,198 篇 工学
- 917 篇 计算机科学与技术...
- 569 篇 软件工程
- 255 篇 信息与通信工程
- 248 篇 电气工程
- 143 篇 控制科学与工程
- 134 篇 生物医学工程（可授...
- 115 篇 生物工程
- 95 篇 光学工程
- 62 篇 机械工程
- 53 篇 化学工程与技术
- 52 篇 电子科学与技术（可...
- 48 篇 仪器科学与技术
- 35 篇 材料科学与工程（可...
- 29 篇 土木工程
- 27 篇 交通运输工程
- 24 篇 建筑学
- 22 篇 安全科学与工程
580 篇 理学
- 299 篇 数学
- 215 篇 物理学
- 157 篇 生物学
- 97 篇 统计学（可授理学、...
- 54 篇 化学
- 39 篇 系统科学
189 篇 管理学
- 114 篇 图书情报与档案管...
- 85 篇 管理科学与工程(可...
- 25 篇 工商管理
123 篇 医学
- 93 篇 临床医学
- 56 篇 基础医学(可授医学...
- 29 篇 药学(可授医学、理...
24 篇 法学
- 20 篇 社会学
13 篇 农学
9 篇 文学
8 篇 艺术学
7 篇 教育学
5 篇 经济学
1 篇 军事学

主题

493 篇 pattern recognit...
78 篇 feature extracti...
73 篇 artificial intel...
48 篇 face recognition
42 篇 neural networks
41 篇 pattern matching
38 篇 pattern recognit...
38 篇 computer imaging...
37 篇 support vector m...
37 篇 local binary pat...
33 篇 bioinformatics
29 篇 data mining
27 篇 training
26 篇 image processing
25 篇 accuracy
22 篇 information syst...
20 篇 machine learning
20 篇 image processing...
19 篇 pattern classifi...
19 篇 databases

机构

9 篇 national laborat...
7 篇 univ windsor sch...
6 篇 institute of ima...
5 篇 institute of ima...
4 篇 indian statistic...
4 篇 national laborat...
4 篇 institute for pa...
4 篇 univ patras sch ...
4 篇 tsinghua univ
4 篇 daffodil interna...
3 篇 natl. lab. of pa...
3 篇 university of el...
3 篇 departamento de ...
3 篇 university of mi...
3 篇 pattern recognit...
3 篇 school of comput...
3 篇 south china norm...
3 篇 universidad esta...
3 篇 tongji universit...
3 篇 guangxi key labo...

作者

10 篇 ngom alioune
7 篇 rueda luis
6 篇 ma songde
6 篇 kropatsch walter...
5 篇 jie yang
5 篇 wang wei
5 篇 de ridder dick
4 篇 li yifeng
4 篇 de-shuang huang
4 篇 donald c. wunsch
4 篇 martínez-hinarej...
4 篇 hornegger joachi...
4 篇 daniel s. levine
4 篇 hancock edwin r.
4 篇 duin robert p. w...
4 篇 anon
4 篇 jain anil k.
4 篇 kang-hyun jo
4 篇 kamel mohamed s.
4 篇 costaridou l.

语言

1,740 篇 英文
16 篇 中文
11 篇 其他
1 篇 西班牙文
1 篇 荷兰文

检索条件"任意字段=4th International Conference Pattern Recognition in Bioinformatics"

共 1763 条记录，以下是11-20 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：

Texture Spectral Decorrelation Criteria 27th

Texture Spectral Decorrelation Criteria

引用

27th international conference on pattern recognition, ICPR 2024

作者： Haindl, Michal Havlíček, Michal Institute of Information Theory and Automation Czech Academy of Sciences Pod Vodarenskou vezi 4 Prague182 08 Czech Republic

ISBN: (纸本)9783031781711

We introduce texture spectral criteria, which allow us to predict whether simplified spectrally factorized random field-based texture models, a set of two-dimensional models, can faithfully replicate texture spectra compared to their fully spectrally correlated 3D counterparts. these probabilistic models incorporate essential two- or three-dimensional building factors for modeling the seven-dimensional Bidirectional Texture Function (BTF), the most advanced representation in real-world material visual properties modeling. While these models seamlessly approximate original measured massive data and extend them to arbitrary sizes or simulate unmeasured textures, evaluating typically involves time-consuming synthesis and psycho-physical evaluation. the proposed criteria provide an alternative approach, enabling us to bypass the spectral quality evaluation step. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： 3D modeling

来源：评论

学校读者我要写书评

暂无评论

CLIP-AGIQA: Boosting the Performance of AI-Generated Image Quality Assessment with CLIP 27th

CLIP-AGIQA: Boosting the Performance of AI-Generated Image...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Tang, Zhenchen Wang, Zichuan Peng, Bo Dong, Jing New Laboratory of Pattern Recognition Institute of Automation Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031781247

With the rapid development of generative technologies, AI-Generated Images (AIGIs) have been widely applied in various aspects of daily life. However, due to the immaturity of the technology, the quality of the generated images varies, so it is important to develop quality assessment techniques for the generated images. Although some models have been proposed to assess the quality of generated images, they are inadequate when faced with the ever-increasing and diverse categories of generated images. Consequently, the development of more advanced and effective models for evaluating the quality of generated images is urgently needed. Recent research has explored the significant potential of the visual language model CLIP in image quality assessment, finding that it performs well in evaluating the quality of natural images. However, its application to generated images has not been thoroughly investigated. In this paper, we build on this idea and further explore the potential of CLIP in evaluating the quality of generated images. We design CLIP-AGIQA, a CLIP-based regression model for quality assessment of generated images, leveraging rich visual and textual knowledge encapsulated in CLIP. Particularly, we implement multi-category learnable prompts to fully utilize the textual knowledge in CLIP for quality assessment. Extensive experiments on several generated image quality assessment benchmarks, including AGIQA-3K and AIGCIQA2023, demonstrate that CLIP-AGIQA outperforms existing IQA models, achieving excellent results in evaluating the quality of generated images. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

pattern recognition in Apple Orchards During Dormancy and Bud Development 4th

Pattern Recognition in Apple Orchards During Dormancy and ...

引用

4th international conference on Smart Multimedia, ICSM 2024

作者： Sehgal, Bhavya Gandhi, Ritik Cheng, Irene Department of Computing Science University of Alberta EdmontonABT6G 2R3 Canada

ISBN: (纸本)9783031824746

Effective management of apple orchards during dormancy and bud development stages is crucial for optimizing fruit production and tree health. Automation using computer vision and deep learning techniques offers a promising solution for tree segmentation and labeling in complex outdoor environments. However, existing methods face challenges in accurately segmenting trees with bare branches and adapting to changing perspectives. this paper presents innovative solutions for bare tree segmentation and labeling, combining depth sensing and advanced image processing with deep learning approaches. the proposed methods address the limitations of current techniques, offering improved accuracy and robustness. We also introduce a novel tree labeling algorithm that utilizes spatial information and YOLOv4 for accurate tree identification and labeling across video frames. Experimental results demonstrate the effectiveness of our approach in handling complex outdoor conditions and bare tree segmentation. Our research contributes to advancing automated orchard management and precise monitoring during dormancy and bud development stages, enhancing fruit quality and overall orchard productivity. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Document Image Shadow Removal via Frequency Information-Oriented Network 27th

Document Image Shadow Removal via Frequency Information-Ori...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Yang, Fan Zhou, Xinyue Jiang, Nanfeng Wang, Da-Han Zhang, Xu-Yao Li, Guantin Man, Wang Wu, Yun School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing China

ISBN: (纸本)9783031781186

Removing shadows from document images can significantly improve the Quality of Experience (QoE) and boost the performance of the downstream document analysis and recognition tasks. However, existing methods still have limited generalization ability on complex document images and are prone to disrupt the image details. To address this issue, we consider the different shadow types that impact the image content on different frequency sub-bands. this motivates us to exploit frequency-domain information and further design a Frequency Information-oriented Deshadow Network (FID-Net). the proposed FID-Net mainly uses two elaborated modules, named Frequency Feature Extractor (FFE) and a Frequency Feature Refinement (FFR). FFE can generate low/high-frequency features through adaptively decomposing spectra of the shadow image. After that, FFR further refines both frequency features with mutual information operations. With the proposed key designs, extensive experimental results on the commonly used benchmarks demonstrate that the proposed method can learn discriminative shadows and achieve favorable performance against state-of-the-art approaches. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

pattern recognition applications and methods: 4th international conference, ICPRAM 2015 Lisbon, Portugal, January 10–12, 2015 revised selected papers 4th

Pattern recognition applications and methods: 4th internatio...

引用

4th international conference on pattern recognition Applications and Methods, ICPRAM 2015

作者： Fred, Ana De Marsico, Maria Figueiredo, Mário Instituto de Telecomunicações Instituto Superior Técnico University of Lisbon Lisbon Portugal Sapienza Università di Roma Rome Italy

来源：评论

学校读者我要写书评

暂无评论

Understanding the Influence of Extremely High-Degree Nodes on Graph Anomaly Detection 27th

Understanding the Influence of Extremely High-Degree Nodes...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Sun, Xun Xiao, Xi Wang, Zhaoguo Hu, Guangwu Jiang, Xuhui Zhang, Bin Li, Hao Shenzhen International Graduate School Tsinghua University Shenzhen China Ministry of Education Chengdu China Shenzhen China Shenzhen Institute of Information Technology Shenzhen China Institute of Computing Technology CAS Beijing China Peng Cheng Laboratory Shenzhen China National Key Laboratory of Advanced Communication Network Shijiazhuang China

ISBN: (纸本)9783031781827

Graph Anomaly Detection (GAD) has attracted considerable attention for its potential in detecting anomalies. However, an overlooked issue in prior research is the presence of extremely high-degree node, which can introduce noise into GAD, escalate computational costs, and intensify the problem of over-smoothing. To tackle this issue, this paper first presents a novel graph anomaly dataset, NFTGraph, characterized by a notable presence of extremely high-degree nodes. A series of experiments on this dataset sheds light on the influence of such nodes on GAD. Moreover, we introduce a novel model, the Super Node-Aware Graph Neural Network (SNGNN), designed to mitigate the noise emanating from extremely high-degree nodes. Experimental results demonstrate that SNGNN outperforms extant models, achieving an average improvement of over 2% in the Area Under the ROC Curve (AUROC), and effectively reducing noise. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

OCR4HSV: A Multi-task Learning Approach for Handwritten Signature Verification 27th

OCR4HSV: A Multi-task Learning Approach for Handwritten Sig...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Lin, Chao-Qun Wang, Da-Han Su, Yan-Fei Ge, De-Wu Zhang, Xu-Yao School of Computer and Information Engineering Xiamen University of Technology Xiamen361024 China Fujian Key Laboratory of Pattern Recognition and Image Understanding Xiamen361024 China Xiamen KEYTOP Communication Technology Co. Xiamen361024 China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation of Chinese Academy of Sciences Beijing100190 China

ISBN: (纸本)9783031781186

Handwritten signature verification (HSV) models are notably recognized for their ability to discern whether a signature is forged in an offline document. Recently, HSV technology has made significant development. However, these methods have primarily focused on the shape features of the text image and overlooked the textual feature information inherent in the text itself, which makes the HSV model overfit. In this paper, we propose a novel network model named OCR4HSV to solve the above shortcomings. the proposed OCR4HSV first attempts to combine OCR and HSV to learn textual features in a multi-task learning manner. the model employs a dual-parameter approach, combining shared parameters and independent parameters. Specifically, Within the shared parameters, the Laplace attention module (LAM) is incorporated for edge information extraction. For independent parameters, CN-Mamba is utilized for sequence feature extraction in OCR, and the multi-scale global fusion block (MGFB) is designed to enhance the distinction between reference and test sample pairs. Leveraging OCR-related information and these architectural enhancements can fully mine the inherent textual feature information and significantly mitigate overfitting in the HSV task, thereby boosting verification accuracy. Our model has achieved state-of-the-art performance on the ChiSig and HanSig datasets. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

2by2: Weakly-Supervised Learning for Global Action Segmentation 27th

2by2: Weakly-Supervised Learning for Global Action Segmenta...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Bueno-Benito, Elena Dimiccoli, Mariella Institut de Robòtica i Informàtica Industrial CSIC-UPC Llorens i Artigas 4-6 Barcelona08028 Spain

ISBN: (纸本)9783031781247

this paper presents a simple yet effective approach for the poorly investigated task of global action segmentation, aiming at grouping frames capturing the same action across videos of different activities. Unlike the case of videos depicting all the same activity, the temporal order of actions is not roughly shared among all videos, making the task even more challenging. We propose to use activity labels to learn, in a weakly-supervised fashion, action representations suitable for global action segmentation. For this purpose, we introduce a triadic learning approach for video pairs, to ensure intra-video action discrimination, as well as inter-video and inter-activity action association. For the backbone architecture, we use a Siamese network based on sparse transformers that takes as input video pairs and determine whether they belong to the same activity. the proposed approach is validated on two challenging benchmark datasets: Breakfast and YouTube Instructions, outperforming state-of-the-art methods. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Oracle Bone Inscription Image Retrieval Based on Improved ResNet Network 27th

Oracle Bone Inscription Image Retrieval Based on Improved Re...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Ding, Jun Wang, Jiaoyan Aysa, Alimjan Xu, Xuebin Ubul, Kurban School of Computer Science and Technology Xinjiang University Ürümqi830046 China Xinjiang Multilingual Information Technology Key Laboratory Xinjiang University Ürümqi830046 China Joint International Research Laboratory of Silk Road Multilingual Cognitive Computing Xinjiang University Urumqi830046 China

ISBN: (纸本)9783031783043

Research on oracle bone inscription image retrieval is important for applications in academic and cultural heritage areas. the current oracle bone dataset faces problems such as the low similarity between the same category, the high similarity between the different categories, and imbalanced sample distribution. In addition, due to the complex background of oracle bone images, existing network models have certain limitations in extracting image features. To address these challenges, this study first adopts a Siamese network-based image retrieval method to learn feature representations of similar and dissimilar images. Subsequently, the existing dataset was partitioned, providing a practical and usable retrieval dataset for the oracle bone image retrieval field. Finally, an improved network model based on ResNet is proposed and integrated into the Siamese network framework. the model achieves the highest retrieval MP and MAP values of 83.26% and 90.68%, respectively, which is better than the current research. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Label-Expanded Feature Debiasing for Single Domain Generalization 27th

Label-Expanded Feature Debiasing for Single Domain Generali...

引用

27th international conference on pattern recognition, ICPR 2024

作者： Yang, Jie Jing, Liwei Xu, Yuanzhuo Wu, Shaowu Drew, Steve Niu, Xiaoguang School of Computer Science Wuhan University Wuhan430072 China University of Calgary CalgaryT2N 1N4 Canada

ISBN: (纸本)9783031781278

In single domain generalization, the model is trained on a single source domain and requires being generalized to multiple unseen target domains. However, the presence of domain discrepancies poses a significant threat to this goal. A straightforward solution is to extract class-specific features that are robust to domain discrepancies. Existing methods typically learn class-specific features with the assistance of domain-specific features by enlarging the gap between them. Nevertheless, the absence of domain supervision limits the extraction of domain-specific features, leading to potential misidentification of class-specific features. To address this issue, we propose Label-expanded Feature Debiasing (LeFD), a novel method that learns class-specific features in a more robust manner. Technically, LeFD introduces domain supervision and explicitly extracts integrated domain and class features through label expansion. Subsequently, a rationale alignment module is employed to eliminate domain information from the integrated domain and class features, thereby obtaining class-specific features. Extensive experimental results on multiple benchmark datasets indicate the superiority of the proposed LeFD compared to other state-of-the-art methods. © the Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Domain supervision Feature debiasing Label expansion

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177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：