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

7,403 篇 会议
348 篇 期刊文献
57 册 图书
17 篇 学位论文

馆藏范围

7,825 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

4,450 篇 工学
- 3,422 篇 计算机科学与技术...
- 1,717 篇 软件工程
- 1,076 篇 电气工程
- 714 篇 信息与通信工程
- 343 篇 控制科学与工程
- 342 篇 电子科学与技术（可...
- 304 篇 光学工程
- 233 篇 机械工程
- 224 篇 生物医学工程（可授...
- 178 篇 仪器科学与技术
- 154 篇 生物工程
- 90 篇 测绘科学与技术
- 59 篇 化学工程与技术
- 56 篇 航空宇航科学与技...
- 53 篇 材料科学与工程（可...
- 47 篇 土木工程
- 42 篇 动力工程及工程热...
- 40 篇 力学（可授工学、理...
1,599 篇 理学
- 781 篇 物理学
- 690 篇 数学
- 181 篇 生物学
- 145 篇 统计学（可授理学、...
- 142 篇 系统科学
- 80 篇 化学
556 篇 医学
- 456 篇 临床医学
- 103 篇 特种医学
- 80 篇 基础医学(可授医学...
446 篇 管理学
- 288 篇 管理科学与工程(可...
- 176 篇 图书情报与档案管...
- 74 篇 工商管理
37 篇 法学
36 篇 农学
23 篇 经济学
20 篇 文学
17 篇 教育学
7 篇 艺术学
6 篇 军事学

主题

868 篇 parallel process...
693 篇 image processing
326 篇 image segmentati...
297 篇 concurrent compu...
273 篇 distributed comp...
259 篇 computational mo...
252 篇 computer archite...
250 篇 feature extracti...
215 篇 image reconstruc...
195 篇 image edge detec...
186 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
166 篇 hardware
165 篇 algorithm design...
164 篇 neural networks
160 篇 deep learning
159 篇 computer science
142 篇 pixel
140 篇 graphics process...

机构

47 篇 national laborat...
25 篇 college of compu...
21 篇 natl univ def te...
20 篇 natl univ def te...
19 篇 science and tech...
14 篇 natl univ def te...
13 篇 school of comput...
12 篇 univ chinese aca...
11 篇 king saud univer...
11 篇 university of ch...
11 篇 natl univ def te...
10 篇 national univers...
9 篇 natl univ def te...
9 篇 institute of inf...
9 篇 national laborat...
8 篇 natl univ def te...
8 篇 department of co...
8 篇 national laborat...
8 篇 college of compu...
8 篇 school of comput...

作者

37 篇 dou yong
28 篇 luo zhigang
27 篇 yong dou
21 篇 zhang xiang
19 篇 zhigang luo
18 篇 li dongsheng
17 篇 naiyang guan
17 篇 qiao peng
15 篇 huang xuhui
15 篇 jie liu
14 篇 niu xin
13 篇 yijie wang
13 篇 lan long
13 篇 wang huaimin
12 篇 anon
11 篇 xiang zhang
11 篇 yang yang
11 篇 liu jie
11 篇 wang yijie
11 篇 pesquet jean-chr...

语言

7,657 篇 英文
112 篇 其他
52 篇 中文
7 篇 土耳其文
3 篇 俄文

检索条件"任意字段=Conference on Parallel and Distributed Methods for Image Processing"

共 7825 条记录，以下是911-920 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：

TSFC: Texture and Structure Features Coupling for image Inpainting

TSFC: Texture and Structure Features Coupling for Image Inpa...

引用

IEEE International conference on image processing

作者： Lu Liu Qi Wang Wenxin Yu Shiyu Chen Jun Gong Peng Chen Southwest University of Science and Technology Southwest Automation Research Institute Chengdu Hongchengyun Technology Co. Ltd

image inpainting has made significant progress benefiting from the advantages of convolutional neural networks (CNNs). Deep learning-based methods have shown extraordinary performance in this field. In this paper, we propose a novel image inpainting architecture with pure CNN that can jointly reconstruct the structure and texture of the image. Our generative network architecture (TSFC) consists of two parallel stages: structure generation and texture generation. In the structure generation stage, we use the large convolution kernel, which is highly neglected in modern networks, using the effective perceptual field of the large convolution kernel to enhance the perception of overall structural features. In the texture generation stage, we use the small convolution kernel to extract local texture features. Qualitative and quantitative experimental results on CelebA-HQ and Paris Street View datasets demonstrate the effectiveness and superiority of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Investigation of electroencephalogram-based emotion recognition and channel importance analysis for dual-induction patterns

Investigation of electroencephalogram-based emotion recognit...

引用

2024 International conference on Computer Graphics, Artificial Intelligence, and Data processing, ICCAID 2024

作者： Li, Zhengxiu Liao, Yijie Li, Zebin Chen, Hao Key Laboratory of Jiangxi Province for Image Processing and Pattern Recognition Nanchang Hangkong University Nanchang 330063 China School of Information Engineering Nanchang Hangkong University Nanchang 330063 China

ISBN: (纸本)9781510689275

Both external stimulus and self-induction can evoke human emotions. However, most current research on emotion recognition by Electroencephalogram (EEG) signals focuses only on external stimuli. It was found that ignoring the differences between induced patterns results in lower emotion recognition accuracy. To overcome this problem, we construct a hierarchical emotion recognition model, which first determines whether emotions originate from external stimulus induction or self-induction and then classifies specific emotion categories. Meanwhile, we systematically evaluate the performance of multiple feature types, feature selection, and channel reduction schemes in identifying induction methods and emotional categories. Notably, we make channel importance analysis operators to investigate the distribution of electrodes associated with different induction patterns. Our model works on a dataset that simulates real induced-emotion scenarios. The experimental results show for the first time that the features extracted in the time domain can most effectively discriminate between the induction modalities. And the hierarchical emotion recognition model with feature selection and channel importance analysis operators achieves the best accuracy of 88.53%, which is 14.69% higher than a baseline model. More critically, channel importance analysis indicates that both induction modalities display similar electrode distributions, with EEG signals from temporal and prefrontal electrodes considered to be highly correlated with emotions;stimulus-induced emotion showing an apparent lateralization effect with higher importance of the left side of the brain electrodes, while self-induction is equally distributed on the left and right sides. © 2025 SPIE.

关键词： Channel importance analysis Electroencephalogram Emotion induction method Emotion recognition Self-induction

来源：评论

学校读者我要写书评

暂无评论

EmbRace: Accelerating Sparse Communication for distributed Training of Deep Neural Networks 22

EmbRace: Accelerating Sparse Communication for Distributed T...

引用

Proceedings of the 51st International conference on parallel processing

作者： Shengwei Li Zhiquan Lai Dongsheng Li Yiming Zhang Xiangyu Ye Yabo Duan National University of Defense Technology China National University of Defense Technology China and Xiamen University China

ISBN: (纸本)9781450397339

distributed data-parallel training has been widely adopted for deep neural network (DNN) models. Although current deep learning (DL) frameworks scale well for dense models like image classification models, we find that these DL frameworks have relatively low scalability for sparse models like natural language processing (NLP) models that have highly sparse embedding tables. Most existing works overlook the sparsity of model parameters thus suffering from significant but unnecessary communication overhead. In this paper, we propose EmbRace, an efficient communication framework to accelerate communications of distributed training for sparse models. EmbRace introduces Sparsity-aware Hybrid Communication, which integrates AlltoAll and model parallelism into data-parallel training, so as to reduce the communication overhead of highly sparse parameters. To effectively overlap sparse communication with both backward and forward computation, EmbRace further designs a 2D Communication Scheduling approach which optimizes the model computation procedure, relaxes the dependency of embeddings, and schedules the sparse communications of each embedding row with a priority queue. We have implemented a prototype of EmbRace based on PyTorch and Horovod, and conducted comprehensive evaluations with four representative NLP models. Experimental results show that EmbRace achieves up to 2.41 × speedup compared to the state-of-the-art distributed training baselines.

关键词： communication scheduling deep learning distributed training sparsity of NLP models

来源：评论

学校读者我要写书评

暂无评论

m2Vib: 2D Vibration Measurement Using a Single mmWave Radar

m2Vib: 2D Vibration Measurement Using a Single mmWave Radar

引用

International conference on parallel and distributed Systems (ICPADS)

作者： Haolin Wang Wei Xu Zezhao Li Yanni Yang Zhijian Huang School of Computer Science and Technology Shandong University Qingdao China National Key Laboratory of Science and Technology on Information System Security China

ISBN: (数字)9798331515966

ISBN: (纸本)9798331515973

Two-dimensional vibration measurement is essential for monitoring structure and machine health, especially providing more information than those 1D solutions. However, most existing 2D vibration monitoring methods require multi-dimension sensors, which can be costly for large-scale deployment. In this paper, we propose $m^methods$ Vib, the first work that can realize accurate 2D vibration measurement using a single mmWave radar. Our system is achieved by creating a virtual radar with non-line-of-sight (NLoS) signals from a nearby reflector (e.g., wall) to offer the 2nd-dimension vibration observations. We further establish a geometric model to unveil the relationship between 2D vibration displacement and mmWave signal. Such an idea still encounters challenges from significantly attenuated NLoS signals and low-resolution geometric parameters from the commercial mmWave radar. Thus, we design a new retroreflector to enhance NLoS signals and advanced signal processing methods to obtain fine-grained geometric parameters. Extensive experimental results show that we can achieve sub-mm level 2D vibration measurement with an average vibration displacement error of 62.2 um and frequency error of 0.01 Hz in the X-axis and Y-axis.

关键词： Vibrations Radar measurements Geometric modeling Radar Displacement measurement Vibration measurement Signal processing Frequency measurement Millimeter wave communication Monitoring

来源：评论

学校读者我要写书评

暂无评论

Empirical Insight into Question Similarity with Embedding Approaches and Learning Ecosystems

Empirical Insight into Question Similarity with Embedding Ap...

引用

International conference on parallel distributed and Grid Computing (PDGC)

作者： Sunjit Kaur Vikram Singh Lov Kumar Pratyush Mishra Proksh Proksh National Institute of Technology Kurukshetra India

ISBN: (数字)9798331521349

ISBN: (纸本)9798331521356

Question similarity estimation is crucial in various natural language processing (NLP) applications, predominately in community QA platforms and information retrieval, for building context-aware NLP tasks and steering improved search accuracy and personalizing. The state-of-the-art approaches adapted to numerous methods range from traditional feature-based methods to state-of-the-art deep learning models, with linguistic features, syntactic structures, and semantic representations capturing the similarity between pairs of questions. With this intent, in this paper, we are conducting an empirical study to empirically investigate the proposed similarity estimation pipeline, including dataset selection, feature engineering techniques, and evaluation metrics. Each pipeline is uniquely constructed with ML and DL-based classification techniques in connection with NLP-based word embedding schemes. The datasets are adapted to training and testing Our empirical results highlight the impact of training dataset size, domain specificity, and feature representations on the performance of question similarity models. Our analysis found that GloVe Twitter 200 (GVTW200) embeddings consistently outperformed others in question similarity tasks, with higher Accuracy and AUC compared to TF-IDF and GloVe Wiki 100 (GVWI100). GVTW200 was the most reliable across models. By combining semantic features from pre-trained embeddings with syntactic features like question length and token overlaps, we achieved robust results. KNN, EXTR, and SVCR models showed the highest accuracy and consistency, with advanced metrics like fuzz ratios further enhancing performance for precise similarity estimation.

关键词： Measurement Deep learning Training Adaptation models Accuracy Biological system modeling Semantics Estimation Syntactics Natural language processing

来源：评论

学校读者我要写书评

暂无评论

Long Short-Term Memory and Gated Recurrent Unit Based Brain Tumor Detection

Long Short-Term Memory and Gated Recurrent Unit Based Brain ...

引用

distributed Computing and Electrical Circuits and Electronics (ICDCECE), IEEE International conference on

作者： S. Prabu M. Kiran Arasu R. Gopinath R. Kamalesh M. Mathivanan Rajavel J Department of ECE Mahendra Institute of Technology Namakkal India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318616

Early detection is crucial in identifying brain cancers, as they can lead to serious and incurable illnesses if left Background. Accurate identification of brain tumors is essential in determining the appropriate treatment, which significantly increases the chances of survival for patients. This research work is driven by the high demand and necessity for understanding brain tumors. Our proposed methodology utilizes brain tumor MRI images from an open-source repository. The identification of brain tumors involves four methods: image processing, segmentation, feature extraction, and classification. There are various methods currently used for classifying and segmenting brain tumors. Our hybrid classification algorithm, which combines Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU), compares trained and test data to provide accurate results. The use of a large dataset is crucial in achieving accurate predictions. These predictions assist radiologists in making prompt decisions and implementing appropriate treatment plans by detecting brain cancers early on

关键词： Training image segmentation Magnetic resonance imaging Brain cancer Logic gates Brain modeling Software

来源：评论

学校读者我要写书评

暂无评论

Xphase3d: Memory-distributed Phase Retrieval for Reconstructing Large-Scale 3D Density Maps of Biological Macromolecules

Xphase3d: Memory-Distributed Phase Retrieval for Reconstruct...

引用

IEEE International conference on Cluster Computing

作者： Wenyang Zhao Osamu Miyashita Miki Nakano Florence Tama Center for Computational Science RIKEN Kobe Japan Institute of Transformative Bio-Molecules Nagoya University Nagoya Japan

ISBN: (数字)9798350358711

ISBN: (纸本)9798350358728

Phase retrieval is a crucial step in processing data from advanced X-ray diffraction imaging experiments to analyze the 3D structure of biological macromolecules. However, when the 3D volume is large-scale and consists of numerous fine voxels, performing phase retrieval on it requires a significant amount of memory, often exceeding the capacity of individual workstations. To address this issue, we developed xphase3d, an open-source software package for performing multiprocessing parallel 3D phase retrieval to utilize distributed memory in clusters and supercomputers. Xphase3d has been successfully deployed on the supercomputer Fugaku and has contributed to research in the fields of structural biology and X-ray analysis. It is also compatible with other high-performance computing systems.

关键词： Three-dimensional displays High performance computing Molecular biophysics X-ray diffraction Supercomputers Biology Workstations Open source software image reconstruction Testing

来源：评论

学校读者我要写书评

暂无评论

parallel image Signal processing in a distributed Car Plate Recognition System

Parallel Image Signal Processing in a Distributed Car Plate ...

引用

conference on New Trends in Signal processing (NTSP)

作者： Handrik, Marian Handrikova, Jana Vasko, Milan Univ Zilina Dept Appl Mech Zilina Slovakia Univ Zilina Dept Tech Sci & Informat Zilina Slovakia

The paper describes the use of parallel image processing in a distributed car plate recognition system. parallel image analysis designed for Raspberry PI device. Car plate recognition application OpenALPR has been mod... 详细信息

ISBN: (数字)9781728161556

ISBN: (纸本)9781728161556

关键词： image processing parallel processing car plate recognition BOINC OpenALPR

来源：评论

学校读者我要写书评

暂无评论

Design of Programmable parallel Vision Processor 16

Design of Programmable Parallel Vision Processor

引用

16th IEEE International conference on Solid-State and Integrated Circuit Technology, ICSICT 2022

作者： Yu, Shuangming Liu, Liyuan Wu, Nanjian Institute of Semiconductors Chinese Academy of Sciences State Key Laboratory of Superlattices and Microstructures Beijing100083 China University of Chinese Academy of Sciences Beijing100049 China

ISBN: (数字)9781665469067

ISBN: (纸本)9781665469067

Vision processor is favorable for edge computing scenarios due to its advantages of high computing efficiency and low power consumption. It can operate various image processing algorithms on a single chip. This paper firstly overviews the progress of vision processor researches in decades. Then, the paper introduces a design of programmable parallel vision processor architecture, which can flexibly implement both computer vision algorithms and deep learning neural network algorithms. A vision processing enhanced RISC instruction set is designed to accelerate the execution of deep learning algorithms. Moreover, this paper introduces a set of algorithm optimization methods from an algorithm/hardware co-design perspective, and deploys algorithms on the vision processor efficiently. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

An Infrared and Visible image Fusion Network for Dark Scenes

An Infrared and Visible Image Fusion Network for Dark Scenes

引用

Algorithm, image processing and Machine Vision (AIPMV), International conference on

作者： Jiahao Zhang Zongshou Wei Gansu Key Laboratory of Plateau Traffic Information Engineering and Control Key Laboratory of Optoelectronic Technology and Intelligent Control of Ministry of Education Lanzhou Jiaotong University Lanzhou China

ISBN: (数字)9798350390254

ISBN: (纸本)9798350390261

The purpose of fusing infrared and visible photos is to provide high-quality combined images with clear objects and detailed textures, even in very dark environments. The visual quality and contrast of both infrared and visible images tend to suffer in low-light situations. Previous algorithms fused poor- quality source images directly, resulting in fused images that still had low contrast and lost detail information. Thus, in this paper, we first design a multi-level brightness adjustment unit to learn visible light illumination components layer by layer and perform luminance enhancement while fusing multi-source image information. Second, to enhance the network's capacity for feature extraction, we developed the parallel attention module. This module was inserted after each brightness adjustment module. Extensive trials show that our technique works better than nine common fusion methods when compared visually and using objective measures.

关键词： Training Learning systems Degradation Visualization Machine vision Brightness Lighting Feature extraction image fusion Testing

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 << < 88 89 90 91 92 93 94 95 96 97 > >>

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：