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

1,439 篇 会议
43 篇 期刊文献
42 册 图书

馆藏范围

1,524 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,208 篇 工学
- 1,039 篇 计算机科学与技术...
- 602 篇 软件工程
- 283 篇 电气工程
- 251 篇 信息与通信工程
- 208 篇 生物工程
- 162 篇 光学工程
- 145 篇 生物医学工程（可授...
- 131 篇 控制科学与工程
- 61 篇 电子科学与技术（可...
- 53 篇 机械工程
- 41 篇 化学工程与技术
- 32 篇 材料科学与工程（可...
- 29 篇 仪器科学与技术
- 25 篇 安全科学与工程
496 篇 理学
- 233 篇 数学
- 227 篇 生物学
- 184 篇 物理学
- 80 篇 统计学（可授理学、...
- 39 篇 化学
- 34 篇 系统科学
215 篇 医学
- 199 篇 临床医学
- 85 篇 基础医学(可授医学...
- 61 篇 药学(可授医学、理...
- 29 篇 公共卫生与预防医...
208 篇 管理学
- 140 篇 图书情报与档案管...
- 83 篇 管理科学与工程(可...
- 34 篇 工商管理
43 篇 农学
- 43 篇 作物学
30 篇 法学
- 27 篇 社会学
18 篇 教育学
- 18 篇 教育学
13 篇 经济学
3 篇 军事学
1 篇 艺术学

主题

140 篇 machine learning
122 篇 deep learning
116 篇 image processing
107 篇 pattern recognit...
70 篇 feature extracti...
63 篇 convolutional ne...
57 篇 image segmentati...
46 篇 face recognition
45 篇 computer vision
41 篇 artificial intel...
39 篇 support vector m...
36 篇 image recognitio...
34 篇 image classifica...
31 篇 neural networks
25 篇 training
24 篇 object detection
24 篇 accuracy
22 篇 machine learning...
22 篇 object recogniti...
21 篇 image enhancemen...

机构

6 篇 institute of ima...
5 篇 centre for inter...
5 篇 chitkara univers...
5 篇 univ south dakot...
4 篇 indian statistic...
4 篇 university of ca...
4 篇 national researc...
4 篇 boston universit...
3 篇 dept. of compute...
3 篇 shanghai jiao to...
3 篇 peter the great ...
3 篇 natl. lab. of pa...
3 篇 technische unive...
3 篇 graphic era deem...
3 篇 bangalore
3 篇 department of co...
2 篇 university of sc...
2 篇 université laval...
2 篇 department of cs...
2 篇 italian inst tec...

作者

6 篇 santosh k. c.
5 篇 yang jie
4 篇 gennaro claudio
4 篇 ma songde
4 篇 falchi fabrizio
4 篇 stan sclaroff
4 篇 cheng h.d.
4 篇 cosimo distante
3 篇 wendling laurent
3 篇 frontoni emanuel...
3 篇 guimaraes silvio...
3 篇 battiato sebasti...
3 篇 giovanni m. fari...
3 篇 anon
3 篇 santosh k.c.
3 篇 hegadi ravindra ...
3 篇 marco leo
3 篇 ozawa shinji
3 篇 hossain syed akh...
3 篇 maier-hein klaus

语言

1,483 篇 英文
40 篇 中文
34 篇 其他
2 篇 土耳其文

检索条件"任意字段=1st International Conference on Image Processing Machine Learning and Pattern Recognition"

共 1524 条记录，以下是481-490 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：

Hangul Fonts Dataset: A Hierarchical and Compositional Dataset for Investigating Learned Representations 21st

Hangul Fonts Dataset: A Hierarchical and Compositional Datas...

引用

21st international conference on image Analysis and processing (ICIAP)

作者： Livezey, Jesse A. Hwang, Ahyeon Yeung, Jacob Bouchard, Kristofer E. Lawrence Berkeley Natl Lab Biol Sci & Engn Div Berkeley CA 94720 USA Univ Calif Berkeley Redwood Ctr Theoret Neurosci Berkeley CA 94720 USA Univ Calif Irvine Math Computat & Syst Biol Irvine CA USA Univ Calif Berkeley Helen Wills Neurosci Inst Berkeley CA 94720 USA Lawrence Berkeley Natl Lab Computat Res Div Berkeley CA USA

ISBN: (纸本)9783031064333;9783031064326

Hierarchy and compositionality are common latent properties in many natural and scientific image datasets. Determining when a deep network's hidden activations represent hierarchy and compositionality is important both for understanding deep representation learning and for applying deep networks in domains where interpretability is crucial. However, current benchmark machine learning datasets either have little hierarchical or compositional structure, or the structure is not known. This gap impedes precise analysis of a network's representations and thus hinders development of new methods that can learn such properties. To address this gap, we developed a new benchmark dataset with known hierarchical and compositional structure. The Hangul Fonts Dataset (HFD) is comprised of 35 fonts from the Korean writing system (Hangul), each with 11,172 blocks (syllables) composed from the product of initial, medial, and final glyphs. All blocks can be grouped into a few geometric types which induces a hierarchy across blocks. In addition, each block is composed of individual glyphs with rotations, translations, scalings, and naturalistic style variation across fonts. We find that both shallow and deep unsupervised methods show only modest evidence of hierarchy and compositionality in their representations of the HFD compared to supervised deep networks. Thus, HFD enables the identification of shortcomings in existing methods, a critical first step toward developing new machine learning algorithms to extract hierarchical and compositional structure in the context of naturalistic variability.

关键词： Representation learning Hierarchy Compositionality

来源：评论

学校读者我要写书评

暂无评论

1st international conference on Cyber Warfare, Security and Space Research, SpacSec 2021

1st International Conference on Cyber Warfare, Security and ...

引用

1st international conference on Cyber Warfare, Security and Space Research, SpacSec 2021

ISBN: (纸本)9783031157837

The proceedings contain 25 papers. The special focus in this conference is on Cyber Warfare, Security and Space Research. The topics include: Privacy Preserving and Secured Clustering of Distributed Data Using Self Organizing Map;implementation of Intrusion Detection Systems in Distributed Architecture;Practical Phase Shift Model for RIS-Assisted D2D Communication Systems;recent Trend of Transform Domain image steganography Technique for Secret Sharing;design of a High Efficiency Access Control and Authentication Analysis Model for Cloud Deployments Using pattern Analysis;A study on Cyber Security in Various Critical IT Infrastructure Organizational Sectors: Challenges and Solutions;Short-Delay Multipath Errors in NavIC Signals for stationary Receivers;point Clouds Object Classification Using Part-Based Capsule Network;study of Various Attacks Over images Transferred Optically Through Communication Channel;Brain Tumor Classification via UNET Architecture of CNN Technique;Satellite image Classification Using ANN;power Quality Disturbance Classification Using Transformer Network;on-Orbit, Non-destructive Surface Surveillance and Inspection with Convolution Neural Network;ramadan Group Transform Fundamental Properties and Some its Dualities;enhancing Security Mechanism in Smart Phones Using Crowdsourcing;INTELLIBOT - Intelligent Voice Assisted Chatbot with Sentiment Analysis, COVID Dashboard and Offensive Text Detection;analysis of Various Supervised machine learning Algorithms for Intrusion Detection;enhanced Security Mechanism for Cryptographic File Systems Using Trusted Computing;critical Analysis of IoT Ecosystem to Understand Security Threats and Challenges;hyper-parameters study for Breast Cancer Datasets: Enhancing image Security and Accuracy for Prediction Class;An Efficient image Encryption Technique Using Logistic Map and 2D-TCLM;learning Co-occurrence Embeddings for Sentence Classification;Preventing Fault Attacks on S-Boxes of AES-Like Block Ciphers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Composite Awareness-Based Knowledge Distillation for Medical Anomaly Detection 1st

Composite Awareness-Based Knowledge Distillation for Medical...

引用

1st international conference on pattern Analysis and machine Intelligence, ICPAMI 2024

作者： Dong, Shiwen Ding, Xiaowei Department of Electronic Engineering Shanghai Jiao Tong University Shanghai China

ISBN: (纸本)9789819633487

In the field of medical image analysis, supervised deep learning methods have become mainstream but still face significant challenges. Firstly, they require substantial annotated data, which is costly and time-consuming to obtain. Secondly, there is a class imbalance issue, especially with rare diseases that have limited images and diverse lesion types, making accurate modeling difficult. To address these issues, we propose an anomaly detection model based on knowledge distillation. Our approach leverages the differences in intermediate layer features between a pre-trained teacher network and a student network trained on normal images through knowledge distillation to detect anomalies. We incorporate a composite awareness module to learn both local regional and global spatial information effectively. Experiments conducted on three medical datasets prove our approach performs competitive anomaly detection results compared to existing methods for medical images. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Medical image processing

来源：评论

学校读者我要写书评

暂无评论

Longitudinal Segmentation of MS Lesions via Temporal Difference Weighting

Longitudinal Segmentation of MS Lesions via Temporal Diffe...

引用

Workshop on Longitudinal Disease Tracking and Modeling with Medical images and Data, LDTM 2024, 5th international Workshop on Multiscale Multimodal Medical Imaging, MMMI 2024, 1st Workshop on machine learning for Multimodal/-sensor Healthcare Data, ML4MHD2024 and Workshop on Multimodal learning and Fusion Across Scales for Clinical Decision Support, ML-CDS 2024 held in conjunction with the 27th international conference on Medical image Computing and Computer Assisted Intervention, MICCAI 2024

作者： Rokuss, Maximilian R. Kirchhoff, Yannick Roy, Saikat Kovacs, Balint Ulrich, Constantin Wald, Tassilo Zenk, Maximilian Denner, stefan Isensee, Fabian Vollmuth, Philipp Kleesiek, Jens Maier-Hein, Klaus Division of Medical Image Computing Heidelberg Germany Faculty of Mathematics and Computer Science Heidelberg University Heidelberg Germany HIDSS4Health - Helmholtz Information and Data Science School for Health Karlsruhe Heidelberg Germany Medical Faculty Heidelberg Heidelberg University Heidelberg Germany Helmholtz Imaging German Cancer Research Center Heidelberg Germany Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany Division for Computational Neuroimaging Department of Neuroradiology Heidelberg University Hospital Heidelberg Germany University Hospital Essen Essen Germany University Hospital Essen West German Cancer Center Essen Essen Germany Pattern Analysis and Learning Group Department of Radiation Oncology Heidelberg University Hospital Heidelberg Germany

ISBN: (纸本)9783031845246

Accurate segmentation of Multiple Sclerosis (MS) lesions in longitudinal MRI scans is crucial for monitoring disease progression and treatment efficacy. Although changes across time are taken into account when assessing images in clinical practice, most existing deep learning methods treat scans from different timepoints separately. Among studies utilizing longitudinal images, a simple channel-wise concatenation is the primary albeit suboptimal method employed to integrate timepoints. We introduce a novel approach that explicitly incorporates temporal differences between baseline and follow-up scans through a unique architectural inductive bias called Difference Weighting Block. It merges features from two timepoints, emphasizing changes between scans. We achieve superior scores in lesion segmentation (Dice Score, Hausdorff distance) as well as lesion detection (lesion-level F1 score) as compared to state-of-the-art longitudinal and single timepoint models across two datasets. Our code is made publicly available at: ***/MIC-DKFZ/Longitudinal-Difference-Weighting. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： image segmentation

来源：评论

学校读者我要写书评

暂无评论

Skin Cancer Detection Using CNN and Ensemble learning

Skin Cancer Detection Using CNN and Ensemble Learning

引用

Advances in Signal processing, Power, Communication, and Computing (ASPCC), IEEE international conference on

作者： Ruturaj Samantaray Karishma Afrin Bichitrananda Behera Kirtimayee Bag TCS BaNCS TATA Consultancy Services Limited Bangalore India Dept. of Computer Science and Engineering C. V. Raman Global University Bhubaneswar India

ISBN: (数字)9798350355093

ISBN: (纸本)9798350355109

The global prevalence of skin cancer has seen a concerning increase over recent decades, now accounting for one in every three cancer cases worldwide. The unchecked growth of aberrant cells in the skin can lead to skin cancer, a potentially fatal illness. There are different types of skin cancer, namely, DF (Dermatofibroma), AKIEC (Actinic Keratoses and Intraepithelial Carcinoma), Mel (Melanoma), BCC (Basal Cell Carcinoma), VASC (Vascular Lesions), BKL (Benign Keratosislike Lesions), and NV (Melanocytic Nevi). Skin cancer can spread to nearby tissues in our body if it is not caught early. Presently, diagnosing skin cancer is a time-consuming and financially burdensome process for both patients and healthcare systems. Moreover, diagnosing skin cancer heavily relies on human cell detection. Skin cancers can be dangerous if they are not treated before they have a chance to spread. However, existing technology lacks the ability to detect skin cancer accurately. Traditional machine learning algorithms display limitations when classifying different classes of skin cancer. In this research, we have proposed skin cancer detection with classification using CNN and ensemble learning. CNN, known as the Convolutional Neural Network, represents a specialized architecture within deep learning algorithms primarily tailored for image recognition and feature extraction. It comprises convolutional, pooling, and fully connected layers in its mathematical structure. In this work, CNN (Convolutional Neural Network) is employed for image feature extraction, followed by utilizing three distinct classifier algorithms, namely, SVM (Support Vector machine), KNN (K-Nearest Neighbour), and DT (Decision Tree), integrated through an ensemble approach utilizing a voting system. Despite utilizing multiple classifiers, the model exhibits impressive performance, achieving a classification accuracy of 98%. Notably, our research leverages the HAM10000 dataset for this study.

关键词： Support vector machines machine learning algorithms Signal processing algorithms Nearest neighbor methods Feature extraction Classification algorithms Convolutional neural networks Ensemble learning Lesions Skin cancer

来源：评论

学校读者我要写书评

暂无评论

recognition of Active Deception Jamming for LFM Radar Based on Hyperdimensional Computing 3

Recognition of Active Deception Jamming for LFM Radar Based ...

引用

2022 3rd international conference on Electrical, Electronic Information and Communication Engineering, EEICE 2022

作者： Dong, Hao Wang, Yan Hu, Wen Key Laboratory of Radar Imaging and Microwave Photonics Ministry of Education Nanjing University of Aeronautics and Astronautics Nanjing China Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang China

Active deception jamming is one of the common means to jam radar signals. How to effectively recognize active deception jamming is a challenge of modern radar technology. To address the accuracy and real-time of radar active jamming recognition in practical applications, we propose a fast recognition method of radar active deception jamming based on hyperdimensional computing. First, to address the high feature dimensions, we use the sparse representation of time-frequency diagrams as the input, which time-frequency diagrams are constructed by the jamming plus echo signals in multiple consecutive pulse periods. Second, to achieve a high accuracy and real time of recognition, we employ the hyperdimensional computing to map the input to hyperdimensional space for training and recognition. Last, in the recognition stage, the Hamming distance is adopted to measure the similarity of samples. We validate our method on nine types of radar active deception jamming. The experimental results show that compared with the existing mainstream machine learning-based methods, the proposed method greatly shortens the training time on the premise of maintaining a high recognition accuracy. © Published under licence by IOP Publishing Ltd.

关键词： Hamming distance

来源：评论

学校读者我要写书评

暂无评论

A New Facial image Deviation Estimation and image Selection Algorithm (Fide-Isa) for Facial image recognition Systems: The Mathematical Models 1

A New Facial Image Deviation Estimation and Image Selection ...

引用

1st international conference on Multidisciplinary Engineering and Applied Science, ICMEAS 2021

作者： Siyaka, Hassan Opotu Owolabi, Olumide Bisallah, I. Hashim University of Abuja Department of Computer Science Nigeria

ISBN: (纸本)9781665434935

Deep learning models have been successful and shown to perform better in terms of accuracy and efficiency for facial recognition applications. However, they require huge amount of data samples that were well annotated to be successful. Their data requirements have led to some complications which include increased processing demands of the systems where such systems were to be deployed. Reducing the training sample sizes of deep learning models is still an open problem. This paper proposes the reduction of the number of samples required by the convolutional neutral network used in training a facial recognition system using a new Facial image Deviation Estimation and image Selection Algorithm (FIDE-ISA). The algorithm was used to select appropriate facial image training samples incrementally based on their facial deviation. This will reduce the need for huge dataset in training deep learning models. Preliminary results indicated a 100% accuracy for models trained with 54 images (at least 3 images per individual) and above. © 2021 IEEE.

关键词： Estimation

来源：评论

学校读者我要写书评

暂无评论

recognition of Graphological Wartegg Hand-Drawings 20th

Recognition of Graphological Wartegg Hand-Drawings

引用

20th international conference of the international-Graphonomics-Society (IGS)

作者： Xu, Yunqi Suen, Ching Y. Concordia Univ Ctr Pattern Recognit & Machine Intelligence CENPA Gina Cody Sch Engn & Comp Sci Montreal PQ H3G 1M8 Canada

ISBN: (纸本)9783031197444;9783031197451

Wartegg Test is a drawing completion task designed to reflect the personal characteristics of the testers. A complete Wartegg Test has eight 4 cm x 4 cm boxes with a printed hint in each of them. The tester will be required to use pencil to draw eight pictures in the boxes after they saw these printed hints. In recent years the trend of utilizing high-speed hardware and deep learning based model for object detection makes it possible to recognize hand-drawn objects from images. However, recognizing them is not an easy task, like other hand-drawn images, the Wartegg images are abstract and diverse. Also, Wartegg Test images are multi-object images, the number of objects in one image, their distribution and size are all unpredictable. These factors make the recognition task on Wartegg Test images more difficult. In this paper, we present a complete framework including PCC (Pearson's Correlation Coefficient) to extract lines and curves, SLIC for the selection of feature key points, DBSCAN for object cluster, and finally YoloV3-SPP model for detecting shapes and objects. Our system produced an accuracy of 87.9% for one object detection and 75% for multi-object detection which surpass the previous results by a wide margin.

关键词： Wartegg test image processing Object detection

来源：评论

学校读者我要写书评

暂无评论

Towards Reconstruction of 3D Shapes in a Realistic Environment 21st

Towards Reconstruction of 3D Shapes in a Realistic Environme...

引用

21st international conference on image Analysis and processing (ICIAP)

作者： Zohaib, Mohammad Taiana, Matteo Del Bue, Alessio Italian Inst Technol Pattern Anal & Comp Vis PAVIS Genoa Italy Univ Genoa Dept Marine Elect Elect & Telecommun Engn Genoa Italy

ISBN: (纸本)9783031064302;9783031064296

This paper presents an end-to-end approach for single-view 3D object reconstruction in a realistic environment. Most of the existing reconstruction approaches are trained on synthetic data and they fail when evaluated on real images. On the other hand, some of the methods require pre-processing in order to separate an object from the background. In contrast, the proposed approach learns to compute stable features for an object by reducing the influence of image background. This is achieved by feeding two images simultaneously to the model;synthetic with white background and its realistic variant with a natural background. The encoder extracts the common features from both images and hence separates features of the object from features of the background. The extracted features allow the model to predict an accurate 3D object surface from a real image. The approach is evaluated for both real images of the Pix3D dataset and realistic images rendered from the ShapeNet dataset. The results are compared with state-of-the-art approaches in order to highlight the significance of the proposed approach. Our approach achieves an increase in reconstruction accuracy of approximately 6.1% points in F-1 score with respect to Mesh R-CNN on the Pix3D dataset.

关键词： 3D reconstruction Single-view image Realistic background

来源：评论

学校读者我要写书评

暂无评论

Description of image Using Deep learning

Description of Image Using Deep Learning

引用

Intelligent Computing and Research Trends (ICRT), international conference on

作者： Praveen Kumar Tripathi Sanjeev Kumar Shukla Ved Prakash Farah Shan Ratnesh Kumar Shukla CSE Department SIET Prayagraj UP India Computer Application Axis Business School Kanpur UP India CSED KNIT Sultanpur India CSE Department Maharana Pratap Engineering College Kanpur UP India

Computer vision and natural language processing (NLP) are used in artificial intelligence (AI) to automatically create the description of contents of an image. A regenerative neuronal model is developed for this purpose. It depends on machine translation and computer vision. This model is designed to produce natural sentences that finally explain about the image. Convolution neural networks (CNN) and recurrent neural networks (RNN) make up this model. The CNN is used to extract picture features, and the RNN is used to generate sentences. The model has been trained to produce descriptions that almost exactly describe the given input image. Various datasets are used to test the model's precision, smoothness, and linguistic proficiency after learning from image descriptions. These tests demonstrate that the model frequently describes an input image accurately.

关键词：

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153页 << < 45 46 47 48 49 50 51 52 53 54 > >>

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：