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

78,699 篇 会议
791 篇 期刊文献
326 册 图书
2 篇 学位论文

馆藏范围

79,818 篇 电子文献
1 种 纸本馆藏

日期分布

学科分类号

49,796 篇 工学
- 29,044 篇 计算机科学与技术...
- 23,040 篇 电气工程
- 16,838 篇 软件工程
- 16,506 篇 信息与通信工程
- 5,194 篇 电子科学与技术（可...
- 4,826 篇 光学工程
- 4,536 篇 控制科学与工程
- 3,432 篇 生物医学工程（可授...
- 3,097 篇 机械工程
- 2,843 篇 仪器科学与技术
- 2,051 篇 生物工程
- 699 篇 化学工程与技术
- 558 篇 材料科学与工程（可...
- 521 篇 动力工程及工程热...
- 511 篇 航空宇航科学与技...
- 510 篇 交通运输工程
- 499 篇 安全科学与工程
- 494 篇 网络空间安全
19,891 篇 理学
- 12,187 篇 物理学
- 7,864 篇 数学
- 2,310 篇 生物学
- 2,211 篇 统计学（可授理学、...
- 1,567 篇 系统科学
- 899 篇 化学
10,909 篇 医学
- 10,426 篇 临床医学
- 1,072 篇 基础医学(可授医学...
- 1,057 篇 特种医学
- 694 篇 药学(可授医学、理...
3,247 篇 管理学
- 2,018 篇 管理科学与工程(可...
- 1,356 篇 图书情报与档案管...
391 篇 农学
350 篇 法学
286 篇 军事学
177 篇 经济学
118 篇 教育学
117 篇 文学
67 篇 艺术学

主题

7,223 篇 image processing
6,650 篇 signal processin...
5,258 篇 image coding
5,022 篇 image segmentati...
4,064 篇 image reconstruc...
3,853 篇 signal processin...
3,198 篇 feature extracti...
2,242 篇 image analysis
1,996 篇 digital signal p...
1,708 篇 robustness
1,691 篇 image edge detec...
1,680 篇 cameras
1,647 篇 training
1,628 篇 deep learning
1,588 篇 speech processin...
1,462 篇 pixel
1,422 篇 image resolution
1,382 篇 image enhancemen...
1,332 篇 image color anal...
1,187 篇 visualization

机构

53 篇 university of sc...
49 篇 univ chinese aca...
41 篇 department of si...
40 篇 institute for in...
40 篇 shanghai jiao to...
39 篇 tsinghua univers...
38 篇 school of electr...
38 篇 shanghai jiao to...
36 篇 national institu...
36 篇 school of comput...
34 篇 princeton univ d...
34 篇 beijing inst tec...
33 篇 ibm thomas j. wa...
33 篇 shenzhen interna...
30 篇 institute of inf...
30 篇 beijing key labo...
28 篇 zhejiang univers...
27 篇 nanyang technol ...
27 篇 centre for multi...
27 篇 astar inst infoc...

作者

51 篇 zhang lei
46 篇 wiegand thomas
40 篇 yang bin
33 篇 jie yang
32 篇 jing zhang
32 篇 kaup andre
31 篇 m. vetterli
29 篇 vetterli martin
29 篇 m. gabbouj
28 篇 li li
27 篇 guangtao zhai
27 篇 li xin
27 篇 wang jing
26 篇 karam lina j.
25 篇 jian wang
24 篇 zhang tao
24 篇 m.j.t. smith
24 篇 li yang
24 篇 jun wang
23 篇 kuo c. -c. jay

语言

77,938 篇 英文
1,073 篇 其他
503 篇 土耳其文
289 篇 中文
9 篇 俄文
5 篇 西班牙文
2 篇 法文
1 篇 葡萄牙文

检索条件"任意字段=IEEE International Conference on Signal and Image Processing Applications"

共 79818 条记录，以下是4661-4670 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：

NOISE SUPPRESSION FOR IMPROVED FEW-SHOT LEARNING 47

NOISE SUPPRESSION FOR IMPROVED FEW-SHOT LEARNING

引用

47th ieee international conference on Acoustics, Speech and signal processing (ICASSP)

作者： Chen, Zhikui Ji, Tiandong Zhang, Suhua Zhong, Fangming Dalian Univ Technol Sch Software Technol Dalian 116620 Liaoning Peoples R China

ISBN: (纸本)9781665405409

Few-shot learning (FSL) aims to generalize from few labeled samples. Recently, metric-based methods have achieved surprising classification performance on many FSL benchmarks. However, those methods ignore the impact of noise, making the few-shot learning still tricky. In this work, we identify that noise suppression is important to improve the performance of FSL algorithms. Hence, we proposed a novel attention-based contrastive learning model with discrete cosine transform input (ACL-DCT), which can suppress the noise in input images, image labels, and learned features, respectively. ACL-IX:T takes the transformed frequency domain representations by IX:T as input and removes the high-frequency part to suppress the input noise. Besides, an attention-based alignment of the feature maps and a supervised contrastive loss are used to mitigate the feature and label noise. We evaluate our ACL-DCT by comparing previous methods on two widely used datasets for few-shot classification (i.e., miniimageNet and CUB). The results indicate that our proposed method outperforms the state-of-the-art methods.

关键词： Few-shot learning image classification noise suppression contrastive learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing Computational Complexity: Real-Time Speech Enhancement Using an Efficient Convolutional Recurrent Dense Neural Network 13

Optimizing Computational Complexity: Real-Time Speech Enhanc...

引用

13th international Symposium on image and signal processing and Analysis, ISPA 2023

作者： Rajabi, Amir Krini, Mohammed Aschaffenburg University of Applied Sciences Signal Processing Laboratory Aschaffenburg Germany

ISBN: (纸本)9798350315363

Real-time communication through cell phones and telephones often involves challenging acoustic environments where the original speech signal is contaminated by environmental noise, known as the cocktail party problem. Audio source separation can be an effective solution for isolating the voice in a noisy environment, by suppressing undesired noise without distorting speech components, which can improve speech quality and intelligibility. Deep Neural Network (DNN) models, despite their excellent performance in speech enhancement, require a substantial computational effort during the inference process. This characteristic makes them less than ideal for addressing this specific problem. The high computational complexity of deep models can further impede regression latency, which is crucial for real-time applications that require minimized complexity. Considering these assumptions in this paper, a novel neural network for speech enhancement is presented, which incorporates phase information into the loss function. The proposed method utilizes a convolutional Recurrent Dense (CRD) network, which not only achieves notable computational efficiency but also demonstrates superior performance compared to other existing networks. Experimental results are provided to highlight the advantages and distinctions of the CRD network when compared with alternative state of the art approaches. © 2023 ieee.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Analysis of Gall Bladder & Kidney Stone Using Spectroscopic Technique: A Review 4

Analysis of Gall Bladder & Kidney Stone Using Spectroscopic ...

引用

4th international conference on signal processing and Communication, ICSPC 2023

作者： Kumar, Abhyanand Phagna, Lokesh Rawat, Sagar Gupta, Neha Manav Rachna International Institute of Research Manav Rachna International Institute of Research & Studies Faculty of Computer Applications Faridabad India

ISBN: (纸本)9798350300772

Gallstones and kidney stones are two types of stone diseases that are very afflictive and often fatal. Biological studies in this field have primarily aimed to discover what causes gallstones formation in the urinary tract and gallbladder. Many ideas have been put forward to explain how stones form and how they grow, but the entire pathogenesis cycle is still being debated. A combination makes stones of different things, but much attention is paid to finding what elements and molecules are in them. In this review article, we talk about spectroscopic techniques and show how they can be used to study the diseases of stones. To better understand the subject, we also went over the basics of how stones form inside the body and how complicated they can be. © 2023 ieee.

关键词： Biological organs

来源：评论

学校读者我要写书评

暂无评论

Observer-based discrete Gabor transform

Observer-based discrete Gabor transform

引用

ieee international Instrumentation and Measurement Technology conference (I2MTC)

作者： Orszag, Bence Sujbert, Laszlo Budapest Univ Technol & Econ Dept Measurement & Informat Syst Magyar Tudosok Krt 2 H-1521 Budapest Hungary

ISBN: (纸本)9781665483605

Time-frequency representations are frequently used in signal processing applications. This paper presents a framework for recursive implementation of biorthogonal nonstationary discrete Gabor transforms. These transforms can achieve a non-uniform frequency resolution unlike the well known Fourier transform. Typically they are realized with finite impulse response filters. This paper shows an observer-based recursive implementation of these transforms based on Hostetter's approach. In addition it reviews the construction of generalized Gabor frames and the conditions of their invertibility in detail. The design of the observer's parameters are discussed and multiple examples are given to illustrate the properties and capabilities of both the design process and the observer.

关键词： signal processing Gabor transform observer frames

来源：评论

学校读者我要写书评

暂无评论

Advancements and applications of Convolutional Neural Network 13

Advancements and Applications of Convolutional Neural Networ...

引用

13th international conference of Information and Communication Technology, ICTech 2024

作者： Li, Jialiang Zhu, Yicheng Sussex College of Artificial Intelligence Zhejiang Gongshang University Hangzhou China Faculty of Communication and Information Engineering Shanghai University Shanghai China

ISBN: (纸本)9798350376258

—This article presents an exhaustive exploration of convolutional vectors, a cornerstone concept in deep learning. Initially, it introduces the fundamental principles of convolutional vectors, and then delves into the essential operations that bolster their effectiveness in a broad application scope. The piece begins by examining the basic operations integral to convolutional vectors: convolution, pooling, and flattening. It elucidates how these processes enable convolutional vectors to distill meaningful features from raw data, thereby rendering them exceptionally apt for tasks like image recognition and natural language processing. Following this foundational discussion, the focus shifts to the diverse applications of convolutional vectors across various domains. The article showcases their utility in image classification, object detection, speech recognition, and recommendation systems, among other areas. Through examples and case studies, it illustrates the proficiency of convolutional vectors in addressing real-world challenges. Furthermore, the article ventures into the future trajectory and emerging trends in the realm of convolutional vectors. It highlights ongoing research aimed at enhancing their efficiency and scalability, and discusses their integration with other cutting-edge technologies, such as attention mechanisms and transfer learning. Moreover, the potential implications of convolutional vectors in nascent fields like robotics and autonomous systems are contemplated. ©2024 ieee.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Brain Computer Interfaces for Enhancing Motor imagery Classification Using EEG signal

Brain Computer Interfaces for Enhancing Motor Imagery Classi...

引用

2024 international conference on Brain Computer Interface and Healthcare Technologies, iCon-BCIHT 2024

作者： Lalawat, Rajveer Singh Bajaj, Varun Padhy, Prabin Kumar PDPM-IIITDM Department of ECE Jabalpur India MANIT Bhopal Department of ECE Bhopal India

ISBN: (纸本)9798331540067

The aim of signal processing with transformation techniques, is to precisely identify frequencies and extract minute signal variations. Previous studies have employed various time-frequency distributions (TFD) to extract features from electroen-cephalogram (EEG) signals, and nevertheless, there is still space for improvement. This article introduces a sophisticated method for the classification of motor imagery (MI) EEG signals. The objective of this investigation is to generate TFD plots by utilizing pre-proceed data with continuous wavelet transform (CWT). These plots are designed to assist in the identification of the features of each MI EEG class. Subsequently, these plots are applied to the classification of ResNet-20, ResNet-SO, and Long Short- Term Memory (LSTM) models. The LSTM outperforms the ResN et models, as evidenced by experiments. Our results indicate that this method enhances the efficacy of the brain-computer interface (BCI) for MI tasks and provides substantial advantages for biomedical applications. © 2024 ieee.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

ENHANCING PROTOTYPICAL FEW-SHOT LEARNING BY LEVERAGING THE LOCAL-LEVEL STRATEGY 47

ENHANCING PROTOTYPICAL FEW-SHOT LEARNING BY LEVERAGING THE L...

引用

47th ieee international conference on Acoustics, Speech and signal processing (ICASSP)

作者： Huang, Junying Chen, Fan Wang, Keze Lin, Liang Zhang, Dongyu Sun Yat Sen Univ Guangzhou Peoples R China

ISBN: (纸本)9781665405409

Aiming at recognizing the samples from novel categories with few reference samples, few-shot learning (FSL) is a challenging problem. We found that the existing works often build their few-shot model based on the image-level feature by mixing all local-level features, which leads to the discriminative location bias and information loss in local details. To tackle the problem, this paper returns the perspective to the local-level feature and proposes a series of local-level strategies. Specifically, we present (a) a local-agnostic training strategy to avoid the discriminative location bias between the base and novel categories, (b) a novel local-level similarity measure to capture the accurate comparison between local-level features, and (c) a local-level knowledge transfer that can synthesize different knowledge transfers from the base category according to different location features. Extensive experiments justify that our proposed local-level strategies can significantly boost the performance and achieve 2.8%-7.2% improvements over the baseline across different benchmark datasets, which also achieves the state-of-the-art accuracy.

关键词： Few-shot Learning image Classification Local-level Feature Knowledge Transfer Neural Network

来源：评论

学校读者我要写书评

暂无评论

A Clearer image: Improving Object Detection in Real Rainy Conditions with Two-Stage processing

A Clearer Image: Improving Object Detection in Real Rainy Co...

引用

2023 ieee international conference on Multimedia and Expo Workshops, ICMEW 2023

作者： Yang, Mingxuan Han, Xiyu Ping, Xianyao Li, Zipeng Xiao, Jing School of Computer Science and Artificial Intelligence Wuhan University of Technology China School of Computer Science Wuhan University China

ISBN: (纸本)9798350313154

Object detection is one of the most important and challenging branches of computer vision, which has been widely applied in social life, such as intelligent security, autonomous driving, and so on. However, the performance of object detection could degrade rapidly under challenging weather scenarios including rainy conditions. Despite existing technologies having made impressive advancements, they are almost under synthetic rainy-clean pairs, which have a huge domain gap between synthetic and real rain. In this work, we propose an unsupervised deraining method under real rain and utilize a non-local contrastive learning for better decoupling the rain layer from the clean image. Furthermore, we introduce a semi-supervised detector during detection module to reduce the inconsistency of pseudo labels for better facilitating contrastive learning. Extensive experiments with different deraining and object detection methods demonstrate that our two-stage method obtains competitive performance in complex weather scenarios. © 2023 ieee.

关键词： Rain

来源：评论

学校读者我要写书评

暂无评论

image Fusion with CT and MRI images for Improving the Quality of Diagnostics 8th

Image Fusion with CT and MRI Images for Improving the Qualit...

引用

8th international conference on Computers, Management and Mathematical Sciences, ICCM 2022

作者： Supriya, Bopparaju Keerthi, Jajula Om Sri Rachel, Peeka Ushasvi Manjari, Usha Shaik, Subhani Department of Information Technology Sreenidhi Institute of Science & Technology Telangana Hyderabad India

ISBN: (纸本)9783031511660

To create a single image with the most information possible, two photographs of same model are combined through the process of image fusion. Many image-processing applications, including satellite imaging, remote sensing, and picture fusion, are crucial. The study of fusing images has developed to support the development of the above applications, and it has since expanded to include research on medical imaging. The merger of magnetic resonance (MR) and computerized tomography (CT) images is accomplished by using a curvelet-based method, which is presented in this chapter. The goal of merging an MR image and a CT image of the same organ is to create a unique image that contains the most diagnostically useful information on that organ. Wavelet transform has been suggested in some attempts to fuse MR and CT images. Given the number of items and curved forms in medical photos and after fusion, the curvelet transform is expected to perform better than the wavelet transform. According to the simulation results, the curvelet transform outperforms the wavelet transform when merging MR and CT images, in terms of visual quality and peak signal-to-noise ratio (PSNR). © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： image fusion

来源：评论

学校读者我要写书评

暂无评论

CLASS ACTIVATION MAP REFINEMENT VIA SEMANTIC AFFINITY EXPLORATION FOR WEAKLY SUPERVISED OBJECT DETECTION 29

CLASS ACTIVATION MAP REFINEMENT VIA SEMANTIC AFFINITY EXPLOR...

引用

ieee international conference on image processing (ICIP)

作者： Wang, Zhendong Chen, Zhenyuan Gong, Chen Nanjing Univ Sci & Technol PCA Lab Key Lab Intelligent Percept & Syst High Dimens In Minist Educ Nanjing Peoples R China Nanjing Univ Sci & Technol Sch Comp Sci & Engn Jiangsu Key Lab Image & Video Understanding Socia Nanjing Peoples R China

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Weakly Supervised Object Detection (WSOD) aims to train a detector to specify the interesting targets in an image by only using image-level labels. An important trend of current WSOD methods is to integrate object detection with Weakly Supervised Semantic Segmentation (WSSS), so that more discriminative regions can be obtained and more accurate detection can be achieved. However, due to the unreliable segmentation supervision generated by WSOD, their performance is still very limited. To address this problem, in this paper, we propose a novel end-to-end framework termed Class activation map Guided Detection Network (CGDN), where the detection process is guided by Class Activation Map (CAM) rather than the segmentation results. The proposed CGDN is composed of a detection branch and a CAM refinement branch, where the CAM refinement branch critically refines the CAMs generated by the detection branch, and then the refined CAMs are deployed to provide more reliable foreground cues for the detection branch in turn. Therefore, the two branches interact which leads to progressively improved detection and CAM outputs. Extensive experiments on PASCAL VOC 2007 and 2012 datasets verify the effectiveness of our proposed network.

关键词： weakly supervised learning object detection class activation map

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 << < 463 464 465 466 467 468 469 470 471 472 > >>

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：