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

3,916 篇 会议
176 篇 期刊文献
23 册 图书
3 篇 学位论文

馆藏范围

4,118 篇 电子文献
10 种 纸本馆藏

日期分布

学科分类号

2,870 篇 工学
- 1,419 篇 计算机科学与技术...
- 1,411 篇 电气工程
- 575 篇 软件工程
- 464 篇 信息与通信工程
- 280 篇 测绘科学与技术
- 206 篇 生物医学工程（可授...
- 203 篇 仪器科学与技术
- 181 篇 光学工程
- 177 篇 电子科学与技术（可...
- 99 篇 机械工程
- 85 篇 控制科学与工程
- 70 篇 材料科学与工程（可...
- 58 篇 航空宇航科学与技...
- 49 篇 生物工程
- 24 篇 化学工程与技术
- 19 篇 核科学与技术
- 17 篇 动力工程及工程热...
2,120 篇 理学
- 1,704 篇 物理学
- 503 篇 数学
- 65 篇 生物学
- 45 篇 系统科学
- 43 篇 化学
- 43 篇 统计学（可授理学、...
1,308 篇 医学
- 1,207 篇 临床医学
- 128 篇 特种医学
- 39 篇 基础医学(可授医学...
- 28 篇 药学(可授医学、理...
- 15 篇 公共卫生与预防医...
70 篇 管理学
- 46 篇 管理科学与工程(可...
- 25 篇 图书情报与档案管...
12 篇 法学
8 篇 军事学
6 篇 农学
5 篇 教育学
5 篇 文学
5 篇 艺术学
4 篇 经济学

主题

580 篇 image processing
494 篇 wavelets
349 篇 signal processin...
205 篇 image compressio...
189 篇 wavelet transfor...
176 篇 image segmentati...
145 篇 image coding
136 篇 image reconstruc...
122 篇 signal to noise ...
122 篇 feature extracti...
107 篇 sensors
105 篇 image quality
104 篇 image enhancemen...
101 篇 visualization
97 篇 image analysis
87 篇 denoising
81 篇 digital signal p...
78 篇 image resolution
77 篇 image filtering
77 篇 signal processin...

机构

11 篇 rice univ dept e...
11 篇 ecole polytech f...
10 篇 chelyabinsk stat...
9 篇 ecole polytech f...
9 篇 tampere univ tec...
8 篇 cicese dept comp...
7 篇 ecole polytech f...
7 篇 univ illinois de...
7 篇 ohu univ sch pha...
7 篇 don state tech u...
7 篇 rice univ dept e...
6 篇 ecole polytech f...
6 篇 univ southern ca...
6 篇 swiss fed inst t...
6 篇 univ maryland de...
6 篇 swiss fed inst t...
5 篇 rice univ dept m...
5 篇 mks imaging tech...
5 篇 univ houston dep...
5 篇 cicese dept comp...

作者

45 篇 ebrahimi touradj
18 篇 unser m
17 篇 kober vitaly
17 篇 agaian sos s.
13 篇 richter thomas
12 篇 schelkens peter
12 篇 ebrahimi t
10 篇 blu t
10 篇 upenik evgeniy
10 篇 ramchandran k
10 篇 baraniuk r
9 篇 astola j
9 篇 philips wilfried
8 篇 vetterli m
8 篇 jones kj
8 篇 alparone l
8 篇 cohen l
8 篇 pizurica aleksan...
8 篇 choi h
8 篇 testolina michel...

语言

4,038 篇 英文
35 篇 其他
26 篇 土耳其文
19 篇 中文

检索条件"任意字段=Wavelets - Applications in Signal and Image Processing X Conference"

共 4118 条记录，以下是321-330 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：

Adapting Without Seeing: Text-Aided Domain Adaptation for Adapting CLIP-like Models to Novel Domains

Adapting Without Seeing: Text-Aided Domain Adaptation for Ad...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Louis Hémadou Héléna Vorobieva Ewa Kijak Frédéric Jurie Digital Sciences & Technologies Department Safran Tech Université de Rennes IRISA INRIA CNRS Université de Caen Normandie ENSICAEN CNRS

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

This paper addresses the challenge of adapting large vision models, such as CLIP, to domain shifts in image classification tasks. While these models, pre-trained on vast datasets like LAION 2B, offer powerful visual representations, they may struggle when applied to domains significantly different from their training data, such as industrial applications. We introduce TADA, a Text-Aided Domain Adaptation method that adapts the visual representations of these models to new domains without requiring target domain images. TADA leverages verbal descriptions of the domain shift to capture the differences between the pre-training and target domains. Our method integrates seamlessly with fine-tuning strategies, including prompt learning methods. We demonstrate TADA’s effectiveness in improving the performance of large vision models on domain-shifted data, achieving state-of-the-art results on benchmarks like DomainNet.

关键词： Learning systems Adaptation models Visualization Training data signal processing Benchmark testing Data models Acoustics Speech processing image classification

来源：评论

学校读者我要写书评

暂无评论

A Fast Saturation Based Dehazing Framework with Accelerated Convolution and Attention Block

A Fast Saturation Based Dehazing Framework with Accelerated ...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Shuocheng Wang Jiaming Liu Yilian Zhong Ruoxi Zhu Jiazheng Lian Hao Zhang Yibo Fan State Key Laboratory of Integrated Chips and Systems Fudan University

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Real-time image dehazmg is crucial for applications such as autonomous driving, surveillance, and remote sensing, where haze can significantly reduce visibility. However, many deep learning algorithms are hindered by large model sizes, making real-time processing difficult to achieve. Several fast and lightweight dehazing networks rely on estimating K(x), but they often fail to deliver satisfying performance. In this paper, we present a novel fast dehazing framework built upon the saturation-based algorithm. We design a new convolution module called Feature Extraction Partial Convolution (FEPC), which is faster and achieves better performance than the vanilla 3×3 convolution. Additionally, we fully leverage the information redundancy between feature map channels by dividing it into two parts along the channel dimension and designing a Self-Cross Attention Block (SCAB). The reduction in channel count significantly reduces computational load and improves the framework’s speed. Through extensive experiments, our method demonstrates not only a fast inference speed but also superior dehazing performance, providing a promising solution for real-time practical deployment. Our code will be available at https://***/superwscZFSB-Dehazing-Framework.

关键词： Deep learning image quality Convolution Surveillance Redundancy signal processing algorithms Feature extraction Real-time systems Speech processing Remote sensing

来源：评论

学校读者我要写书评

暂无评论

Mask Augmentation For Tumor Classification In Medical images

Mask Augmentation For Tumor Classification In Medical Images

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Chun-Chieh Weng Huan-Yu Chen Jing-Tong Tzeng Ching-Heng Lin Po-Chih Kuo Chi-Chun Lee Department of Electrical Engineering National Tsing Hua University Taiwan College of Semiconductor Research National Tsing Hua University Taiwan Department of Medical Research Taichung Veteran General Hospital Taichung Taiwan Department of Computer Science National Tsing Hua University Taiwan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Tumor detection and classification in medical images are critical for guiding patient management and treatment decisions. However, accurate segmentation and classification of tumors remain challenging due to their small size relative to the overall image. Existing approaches often face difficulties with limited data and potential segmentation errors, resulting in suboptimal performance in real-world applications. To address these challenges, we propose a novel approach leveraging the Segmentation Mask Augmentation (SMA) framework. Our framework enhances the robustness of tumor classification models by generating diverse and imprecise segmentation masks during training, thereby simulating real-world scenarios. Experimental results across four distinct datasets demonstrate the effectiveness of our approach. Our framework presents a promising solution for robust tumor classification, with potential implications for improving clinical diagnosis and patient management.

关键词： Training image segmentation Accuracy Decision making signal processing Robustness Speech processing Medical diagnostic imaging Faces Tumors

来源：评论

学校读者我要写书评

暂无评论

Identifying Adversarial Attacks in Crowdsourcing via Dense Subgraph Detection

Identifying Adversarial Attacks in Crowdsourcing via Dense S...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Abdullah Karaaslanli Panagiotis A. Traganitis Aritra Konar Dept. of Electrical & Computer Engineering Michigan State University East Lansing MI USA Dept. of Electrical Engineering KU Leuven Leuven Belgium

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Crowdsourcing is becoming increasingly important for contemporary applications in machine learning and artificial intelligence. However, crowdsourcing systems may be susceptible to adversarial attacks where a subset of annotators deliberately provide erroneous responses. This paper introduces a novel algorithm for identifying adversarial attacks in crowdsourcing systems by recasting the problem as dense subgraph detection in bipartite graphs. In particular, we represent crowdsourced data as a weighted bipartite graph between workers and data points which are connected with edges whose weights are computed from annotators’ responses. The constructed bipartite graph is then analyzed with a sequential peeling algorithm to detect the dense subgraph that includes adversarial attacks. Compared to previous methods where only adversaries are detected, our proposed method can simultaneously identify adversarial annotators as well as affected data points. Preliminary results on real datasets showcase the potential of this novel approach.

关键词： Crowdsourcing Machine learning algorithms image edge detection signal processing algorithms Machine learning signal processing Acoustics Bipartite graph Speech processing

来源：评论

学校读者我要写书评

暂无评论

Enhanced DSP Blocks for Full High-Definition Video Bridging Application on FPGAs

Enhanced DSP Blocks for Full High-Definition Video Bridging ...

引用

International conference on Communications, Circuits and Systems (ICCCAS)

作者： Panfeng Wang Yici Cai Department of Computer Science and Technology Tsinghua University Beijing China

ISBN: (数字)9798350386271

ISBN: (纸本)9798350386288

FPGA chips are widely used in video bridging applications. The DSP (Digital signal processing) in FPGA can effectively improve the efficiency of video image processing algorithms. The 10 bits of pixel depth is common for Full High-Definition (FHD). However, in the existing commercial FPGAs, the DSP does not naturally support 10x10 multiplication. This brings some waste in area and power consumption. This paper proposes a new architecture of embedded DSP. It increases the maximum number of 10x10 multiplications in a DSP block to 8. It is also compatible with common working modes such as multiplication (18x18, 18x9), and accumulation. Meanwhile, introduce power gate and clock gate units in the DSP block to achieve fine-grained control of the power consumption. Users can dynamically control the power supply through their own logic. The entire circuit was successfully designed and implemented in an industrial 22nm process. The experimental results show that the static power consumption of the DSP block is about 20uW, the dynamic power consumption is about 200uW. And the maximum operating frequency can reach 670MHz. The effective area utilization of our DSP in 10x10 mode is 2.2 and 2.5 times higher than that in Intel Arria 10 series and xilinx UltraScale series FPGAs, respectively.

关键词： Power demand Circuits and systems image processing signal processing algorithms Digital signal processing Logic gates Logic

来源：评论

学校读者我要写书评

暂无评论

OSR: Toward Developing Efficient Federated Learning-based Human Activity Recognition using Optimal Server Representations

OSR: Toward Developing Efficient Federated Learning-based Hu...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Ensieh Khazaei Bilal Taha Alireza Esmaeilzehi Dimitrios Hatzinakos Department of Electrical and Computer Engineering University of Toronto Canada

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Federated Learning (FL) is a privacy-preserving algorithm that enables multiple clients to collaboratively train a global model without sharing their local data. This learning algorithm is particularly valuable in privacy-sensitive applications such as Human Activity Recognition (HAR), where users are reluctant to share their personal data. However, a conventional FL system suffers from data heterogeneity and communication overhead. To address these issues, we propose an efficient FL algorithm for image-based HAR using optimal server representations (OSR). OSR efficiently selects a representative set of privacy-preserved images for transmission to the server and improves the global model quality by training on privacy-preserved data. Our comprehensive experiments carried out on three public datasets, namely Stanford40, PPMI, and VOC2012, demonstrate the superiority of OSR in terms of performance and bandwidth usage compared to state-of-the-art approaches.

关键词： Training Federated learning signal processing algorithms Speech recognition Bandwidth signal processing Data models Human activity recognition Servers Speech processing

来源：评论

学校读者我要写书评

暂无评论

Review on Deep Learning Network Architectures for image Reconstruction

Review on Deep Learning Network Architectures for Image Reco...

引用

image processing and Capsule Networks (ICIPCN), International conference on

作者： Babitha Lokula L.V Narasimha Prasad Ramakrishna Tirumuri department of ECE K L deemed to be university Institute of Aeronautical Engineering Vaddeshwaram India department of ECE Institute of Aeronautical Engineering Hyderabad India department of ECE K L deemed to be university Vaddeshwaram India

ISBN: (数字)9798350367171

ISBN: (纸本)9798350367188

In order to obtain the low resolution(LR) image’s detailed information, super resolution(SR) image reconstruction is essential. From 1D projections, we can reconstruct images in 2D and 3D. The LR images attained have different details of the same scene for which the super resolution reconstruction is possible. In the field of computer vision, image reconstruction is used in a variety of applications including robotics, entertainment, reverse engineering, augmented reality, human-computer interaction, and animation. In addition, applications in the medical field like Magnetic Resonance Imaging (MRI), Computed Tomography (CT), x-rays, and ultrasound, among others, make use of image reconstruction. We may encounter limitations while reconstructing the image, such as noise, missing information, a low signal to noise ratio, and a low contrast to noise ratio. We even come across different issues and challenges in application of SR techniques like image registration, computational efficiency, robustness and performance limitations. To address the above-mentioned issues, we study numerous SISR architectures. In this paper, we’ll talk about various techniques, their benefits, drawbacks, and Single image Super Resolution (SISR) architectures that can help improve super resolution image reconstruction in a variety of applications.

关键词： image registration Magnetic resonance imaging Computed tomography Superresolution Computer architecture x-rays Robustness

来源：评论

学校读者我要写书评

暂无评论

Not All Regions are Equal in Registration: A Segmentation-Assisted Registration Network

Not All Regions are Equal in Registration: A Segmentation-As...

引用

IEEE International conference on signal and image processing (ICSIP)

作者： xiaohong Qin Feng Gu Runchun Fan Ying Chen Beijing Institute of Electronic Science and Technology Beijing China

ISBN: (数字)9798350350920

ISBN: (纸本)9798350350937

Existing learning-based image registration methods learn a network that outputs a spatial transformation to warp a source image to align to the target image, which is carried out through optimizing matching similarities. Such matching criteria are mostly agnostic of regions. However, in many applications of medical image registration, the correspondence with specific regions of interest (ROIs) such as organs in source and target images is more important than the whole images as not all regions are equal. Motivated by this, we hereby propose a segmentation-assisted registration network to emphasize the ROIs more. We promote the estimation of registration fields by encoding the anatomical structure extracted by manual or predicted segmentation label generated from fusing the outputs of a multi-atlas-based registration model and a deep segmentation network which is trained using a few manual labeled images. The experiments on 3D brain MRI indicate that our approach improves the registration performance with few manual segmentation labels or ROIs. Our approach also outputs competitive segmentation results.

关键词： image segmentation image registration Three-dimensional displays image coding Magnetic resonance imaging Estimation Manuals

来源：评论

学校读者我要写书评

暂无评论

On Momentum Acceleration for Randomized Coordinate Descent in Matrix Completion

On Momentum Acceleration for Randomized Coordinate Descent i...

引用

International conference on Acoustics, Speech, and signal processing (ICASSP)

作者： Matthew Callahan Trung Vu Raviv Raich School of EECS Oregon State University Corvallis OR USA Department of CSEE University of Maryland Baltimore County MD USA

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Matrix completion plays an important role in machine learning and signal processing, with applications ranging from recommender systems to image inpainting. Many approaches have been considered to solve the problem and some offer computationally efficient solutions. In particular, a highly-efficient random coordinate descent approach reduces the per-epoch computation dramatically. This paper is concerned with further improvement of computational efficiency to expand the range of problem sizes and conditions that can be solved. Momentum acceleration is a well-known method to improve the efficiency of iterative algorithms, but applying it to random coordinate descent methods without increasing the computational complexity is non-trivial. To address this challenge, we introduce a momentum-accelerated randomized coordinate descent for matrix completion approach that does not increase computational complexity by accelerating at the level of epochs. Additionally, we propose an analysis-driven, tuning-free method for step size selection. To that end, we offer a convergence rate analysis for the algorithm. Using numerical evaluations, we demonstrate the competitiveness of the method and verify the theoretical analysis.

关键词： Closed-form solutions Shape signal processing algorithms Machine learning signal processing Computational efficiency Computational complexity Speech processing Recommender systems Convergence

来源：评论

学校读者我要写书评

暂无评论

Filter-Based Photonic Reservoir Computing as a key-enabling platform for all-optical high-speed processing of time-stretched images and telecomm data 3

Filter-Based Photonic Reservoir Computing as a key-enabling ...

引用

conference on AI and Optical Data Sciences III

作者： Tsirigotis, Aris Tsilikas, Ioannis Sozos, Kostas Bogris, Adonis Mesaritakis, Charis Univ Aegean Dept Informat & Commun Syst Engn Palama 2 Str Karlovassi 83200 Samos Greece Natl & Kapodistrian Univ Athens Dept Informat & Telecommun Athens 15784 Greece Natl Tech Univ Athens Sch Appl Math & Phys Sci Phys Dept Zografou Campus Athens 15780 Greece Univ West Attica Dept Informat & Comp Engn Egaleo 12243 Greece

ISBN: (数字)9781510649101

ISBN: (纸本)9781510649101;9781510649095

We present an integrated photonic reservoir computing (RC) scheme that relies on the use of passive optical filters placed within waveguide loops;namely filter-in-a-loop nodes. The proposed photonic neuromorphic nodes aim to provide an alternative all-optical computational paradigm, circumventing previous power-hungry or bandwidth-limiting approaches. The computational efficiency is based, firstly on an optical spectral decomposition process of the incoming signal and secondly on the non-linear mapping of the input's phase to the filter's amplitude. The efficiency of the proposed approach has been evaluated numerically, through two demanding applications that can exploit the inherent advantages of the photonic platform. The first application, consists of transmission impairment amendment of 224 Gbps optical PAM-4 signal subject to chromatic dispersion induced power fading. In this case, numerical results confirm that the proposed neuromorphic scheme can vastly surpasses state-of-the-art equalizers offering real-time sub HD-FEC performance with marginal power-footprint and hardware complexity. The second, application aims at image processing using a time-stretched microscopy system. In this scenario, the proposed RC, allowed 93% Jurkat cell image classification with a processing rate of 200Mframe/sec.

关键词： photonic neuromorphic computing reservoir computing integrated photonics

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412页 << < 29 30 31 32 33 34 35 36 37 38 > >>

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：