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

528 篇 会议
17 篇 期刊文献
7 册 图书

馆藏范围

552 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

355 篇 工学
- 283 篇 计算机科学与技术...
- 155 篇 软件工程
- 74 篇 电气工程
- 37 篇 信息与通信工程
- 20 篇 控制科学与工程
- 19 篇 光学工程
- 19 篇 生物医学工程（可授...
- 15 篇 电子科学与技术（可...
- 11 篇 仪器科学与技术
- 10 篇 机械工程
- 9 篇 生物工程
- 5 篇 测绘科学与技术
- 4 篇 建筑学
- 4 篇 土木工程
- 4 篇 化学工程与技术
- 3 篇 安全科学与工程
- 2 篇 力学（可授工学、理...
125 篇 理学
- 82 篇 物理学
- 40 篇 数学
- 13 篇 生物学
- 8 篇 统计学（可授理学、...
- 4 篇 化学
- 3 篇 系统科学
32 篇 医学
- 26 篇 临床医学
- 7 篇 特种医学
- 5 篇 基础医学(可授医学...
- 3 篇 药学(可授医学、理...
26 篇 管理学
- 21 篇 管理科学与工程(可...
- 6 篇 图书情报与档案管...
- 5 篇 工商管理
1 篇 农学

主题

53 篇 image processing
41 篇 parallel process...
26 篇 feature extracti...
25 篇 image segmentati...
23 篇 deep learning
23 篇 computer vision
21 篇 image edge detec...
20 篇 training
19 篇 image reconstruc...
17 篇 image analysis
16 篇 computer archite...
15 篇 neural networks
15 篇 computational mo...
14 篇 image color anal...
13 篇 distributed comp...
13 篇 accuracy
12 篇 image enhancemen...
12 篇 graphics process...
12 篇 parallel computi...
11 篇 algorithm design...

机构

7 篇 natl univ def te...
5 篇 national laborat...
4 篇 college of compu...
3 篇 hong kong polyte...
3 篇 univ carlos iii ...
3 篇 cnr inst biomed ...
3 篇 natl univ def te...
3 篇 sensetime res pe...
3 篇 cnr inst appl ma...
3 篇 natl univ def te...
2 篇 nanjing audit un...
2 篇 college of compu...
2 篇 school of comput...
2 篇 uni. of pisa
2 篇 univ sydney sch ...
2 篇 tsinghua univ ts...
2 篇 department of in...
2 篇 school of comput...
2 篇 univ aegean dept...
2 篇 lsi laboratory u...

作者

11 篇 dou yong
8 篇 zhigang luo
8 篇 naiyang guan
8 篇 qiao peng
8 篇 carretero jesus
6 篇 yong dou
5 篇 xiang zhang
5 篇 shi hc
5 篇 xu kele
5 篇 dacheng tao
5 篇 li hz
3 篇 ercan mf
3 篇 luo zhigang
3 篇 milanesi luciano
3 篇 garcia-blas javi...
3 篇 peng qiao
3 篇 li dongsheng
3 篇 abella monica
3 篇 xuhui huang
3 篇 huang xuhui

语言

547 篇 英文
4 篇 其他
1 篇 中文

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

共 552 条记录，以下是31-40 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：

Efficient Allocation of image Recognition and LLM Tasks on Multi-GPU System 15th

Efficient Allocation of Image Recognition and LLM Tasks on...

引用

15th International conference on parallel processing and Applied Mathematics, PPAM 2024

作者： Lawenda, Marcin Samborski, Krzesimir Khloponin, Kyrylo Szustak, Lukasz Poznan Supercomputing and Networking Center Jana Pawla II 10 Poznań61-139 Poland Czestochowa University of Technology Dąbrowskiego 69 Częstochowa42-201 Poland

ISBN: (纸本)9783031857027

This work is concerned with the evaluation of the performance of parallelization of learning and tuning processes for image classification and large language models. For machine learning model in image recognition, various parallelization methods are developed based on different hardware and software scenarios: simple data parallelism, distributed data parallelism, and distributed processing. A detailed description of presented strategies is given, highlighting the challenges and benefits of their application. Furthermore, the impact of different dataset types on the tuning process of large language models is investigated. Experiments show to what extent the task type affects the iteration time in a multi-GPU environment, offering valuable insights into the optimal data utilization strategies to improve model performance. Furthermore, this study leverages the built-in parallelization mechanisms of PyTorch that can facilitate these tasks. Furthermore, performance profiling is incorporated into the study to thoroughly evaluate the impact of memory and communication operations during the training/tuning procedure. Test scenarios are developed and tested with numerous benchmarks on the NVIDIA H100 architecture showing efficiency through selected metrics. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

2HDED:NET FOR JOINT DEPTH ESTIMATION AND image DEBLURRING FROM A SINGLE OUT-OF-FOCUS image 29

2HDED:NET FOR JOINT DEPTH ESTIMATION AND IMAGE DEBLURRING FR...

引用

IEEE International conference on image processing (ICIP)

作者： Nazir, Saqib Vaquero, Lorenzo Mucientes, Manuel Brea, Victor M. Coltuc, Daniela Univ POLITEHN Bucharest UPB CEOSpaceTech Bucharest Romania Univ Santiago Compostela USC Ctr Singular Invest & Tecnoloxias Intelixentes C Santiago De Compostela Spain

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

Depth estimation and all-in-focus image restoration from de-focused RGB images are related problems, although most of the existing methods address them separately. The few approaches that solve both problems use a pipeline processing to derive a depth or defocus map as an intermediary product that serves as a support for image deblurring, which remains the primary goal. In this paper, we propose a new Deep Neural Network (DNN) architecture that performs in parallel the tasks of depth estimation and image deblurring, by attaching them the same importance. Our Two-headed Depth Estimation and Deblurring Network (2HDED:NET) is an encoderdecoder network for Depth from Defocus (DFD) that is extended with a deblurring branch, sharing the same encoder. The network is tested on NYU-Depth V2 dataset and compared with several state-of-the-art methods for depth estimation and image deblurring.

关键词： Depth from Defocus image Deblurring Deep learning

来源：评论

学校读者我要写书评

暂无评论

Area-NeRF: Area-based Neural Radiance Fields 2

Area-NeRF: Area-based Neural Radiance Fields

引用

2nd International conference on image processing, Computer Vision and Machine Learning, ICICML 2023

作者： Ye, Zonxin Li, Wenyu Qiao, Peng Dou, Yong National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing School of Computer Changsha China

ISBN: (纸本)9798350331417

Neural Radiance Field (NeRF) has received widespread attention for its photo-realistic novel view synthesis quality. Current methods mainly represent the scene based on point sampling of ray casting, ignoring the influence of the observed area changing with distance. In addition, The current sampling strategies are all focused on the distribution of sampling points on the ray, without paying attention to the sampling of the ray. We found that the current ray sampling strategy for scenes with the camera moving forward severely reduces the convergence speed. In this work, we extend the point representation to area representation by using relative positional encoding, and propose a ray sampling strategy that is suitable for camera trajectory moving forward. We validated the effectiveness of our method on multiple public datasets. © 2023 IEEE.

关键词： NeRF neural radiance field neural rendering novel view synthesis

来源：评论

学校读者我要写书评

暂无评论

Dual Dreamer: Extending Single-View Dreamer with Few Shot of Complementary Views 33rd

Dual Dreamer: Extending Single-View Dreamer with Few Shot of...

引用

33rd International conference on Artificial Neural Networks and Machine Learning (ICANN)

作者： Zhang, Ziteng Qiao, Peng Yong, Dou Liu, Sidun Li, Wenyu Cao, Li Chen, Luo Natl Univ Def Technol Natl Key Lab Parallel & Distributed Comp Sch Comp Changsha Peoples R China Minist Nat Resources Key Lab Nat Resources Monitoring & Supervis South Changsha Peoples R China

ISBN: (纸本)9783031723377;9783031723384

Recently, diffusion models demonstrate the potential of generating consistent novel views from a single view. Due to the limited object information contained in a single input view, controlling generation of out-of-sight views becomes challenging. In this work, we propose Dual Dreamer, a method of generating novel views with complementary views. Specifically, we focus on fine-tuning the single-view input diffusion model to extract complementary information from additional known views and combine it with the original information for novel view synthesis (NVS). To achieve this, Dual Dreamer introduces a 3D attention mechanism to enable the model to learn common features of the complementary views and enhance information exchange. By utilizing view difference between predefined and target views as weights, predefined views are fused as priors to enhance the consistency of multi-view synthesis. Finally, in order to avoid consuming resources on large-scale datasets, the proposed Dual Dreamer model is trained in a similar way like ControlNet, enabling efficient training on small datasets. Extensive evaluation on various datasets demonstrates that our approach achieves consistent, high-quality generation results compared to methods that rely on a single input view.

关键词： Novel Views Synthesis Few Shot Diffusion Model

来源：评论

学校读者我要写书评

暂无评论

distributed Deep Learning-based Model for Large image Data Classification 7

Distributed Deep Learning-based Model for Large Image Data C...

引用

7th International conference on Future Networks and distributed Systems, ICFNDS 2023

作者： Nurnoby, M Faisal Shawarib, Khalid A. Abu Khan, Ayaz Ul Hassan King Fahd University Of Petroleum And Minerals Dhahran Saudi Arabia King Fahd University Of Petroleum And Minerals Khobar Saudi Arabia SDAIA-KFUPM Joint Research Center For Artificial Intelligence King Fahd University Of Petroleum And Minerals Dhahran Saudi Arabia

ISBN: (纸本)9798400709036

Artificial intelligence has shown great potential in a variety of applications, from natural language models to audio visual recognition, classification, and manipulation. AI Researchers have to work with massive amount of collected data for use in machine learning, raising some challenges in effectively managing and utilizing the collected data in the training phase to develop and iterate on more accurate, and more generalized models. In this paper we conducted a review on parallel and distributed machine learning methods and challenges. We also propose a distributed and scalable deep learning model architecture which can span across multiple processing nodes. We tested the model on the MIT Indoor dataset, to evaluate the performance and scalability of the model using multiple hardware nodes, and showed the scaling characteristics of the different model using different model sizes. We find that distributed training is 80% faster using 2 GPUs than 1 GPU. We also find that the model keeps the benefits of distributed training such as speed and accuracy regardless of its size or training batch size. © 2023 ACM.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Low-Dimensional Feature Representation with Hybrid Attention for Few-Shot image Classification 29

Low-Dimensional Feature Representation with Hybrid Attention...

引用

29th IEEE International conference on parallel and distributed Systems, ICPADS 2023

作者： Yao, Xin-Wei Yuan, Zhi-Heng Fang, Yu-Li He, Chuan Zhang, Yu-Chen Li, Qiang Zhejiang University of Technology College of Computer Science and Technology Hangzhou China Zhejiang University of Technology Taizhou Research Institute Taizhou China Zhejiang University of Technology Institute for Frontier and Interdisciplinary Sciences Hangzhou China

ISBN: (纸本)9798350330717

Learning effective image representation and constructing a suitable metric space are two main challenges in few-shot image classification. Existing methods normally consider the joint characteristic distribution of the image to improve the image representation ability, but it also brings high computational cost and produces high-dimensional embedding vectors, which limit their real-world applicability. In this paper, in order to reduce computational complexity and embedding dimension, we propose an effectively low-dimensional feature representation module (LDFR), which introduces a window mechanism to make the model focus on the correlation between local channels by using Brownian Distance Covariance. Furthermore, we combine LDFR with Hybrid Attention (LDFR-HA) to solve the problem of unbalanced sample features in few-shot image classification. Specifically, weighted average is adopted in the Hybrid Attention to construct the metric space and perform classification. Numerous experiments are conducted on two standard few-shot image classification benchmarks, i.e., general object recognition and fine-grained categorization. Extensive evaluations demonstrate that LDFR-HA significantly outperforms existing approaches. On popular datasets miniimageNet and CUB, LDFR-HA achieves 3.52 percentage point(pp)/2.29pp and 2.1pp/1.45pp gains over the state-of-the-art method on 5-way 1-shot/5-shot tasks, respectively. © 2023 IEEE.

关键词： Brownian Distance Covariance Few-shot image classification Hybrid Attention Low-Dimensional Feature

来源：评论

学校读者我要写书评

暂无评论

A Differential Privacy image Publishing Method Based on Wavelet Transform 22nd

A Differential Privacy Image Publishing Method Based on Wave...

引用

22nd International conference on parallel and distributed Computing, Applications and Technologies (PDCAT 2021)

作者： Zhang, Guifen Wei, Hangui Ge, Lina Qin, Xia Guangxi Univ Nationalities Sch Artificial Intelligence Nanning Peoples R China Guangxi Univ Nationalities Key Lab Network Commun Engn Nanning Peoples R China

ISBN: (纸本)9783030967727;9783030967710

image is an important information-bearing medium with many important attributes. If the image data is released directly, personal privacy will be compromised. This paper aims at how to use the method of differential privacy to protect the privacy of image data and make the image data have high usability. In this paper, a WIP method based on wavelet change is proposed. Firstly, wavelet transform is used to compress the image. Then, noise is added to the main features after transformation to obtain the published image satisfying the differential privacy. It solves the problem of low usability of large images and the problem that Fourier transform cannot deal with abrupt signal. Experimental results show that compared with similar methods in the frequency domain, the denoised image obtained by the proposed WIP method is more distinguishable and the information entropy is closer to the original image. The accuracy is 10% higher than other methods. Compared with other frequency-domain methods for image differential privacy protection, the proposed WIP method has higher usability and robustness.

关键词： image processing Differential privacy Privacy protection The wavelet transform

来源：评论

学校读者我要写书评

暂无评论

distributed Cloud Computing Architecture in Hyperspectral Remote Sensing image Classification under Big Data 5

Distributed Cloud Computing Architecture in Hyperspectral Re...

引用

5th IEEE International conference on Information Systems and Computer Aided Education, ICISCAE 2022

作者： Feng, Kai Wu, Yi Shaanxi Academy of Aerospace Technology Application Co. Ltd. Xi'an China

ISBN: (数字)9781665481229

ISBN: (纸本)9781665481229

By using the cloud computing platform that has achieved excellent commercial results to perform parallel classification processing of massive remote sensing data, it can meet the requirements of improving the parallel processing efficiency of massive remote sensing data. The purpose of this paper is to study the application of distributed cloud computing architecture in hyperspectral remote sensing image classification based on big data. The related technologies of cloud computing are expounded, and the model of SCSRC, a sparse representation classification method based on spatial correlation constraints, is proposed. By analyzing the principle and solution method of SCSRC model, a distributed classification algorithm DP-SCSRC based on spatial correlation constraint sparse representation is proposed on the Spark platform, and the following optimization methods are designed for the core steps. Finally, through experiments with different computing nodes and different amounts of computing data, it is proved that the DP-SCSRC algorithm has a good distributed speedup ratio and data scalability under the premise of ensuring the classification accuracy. © 2022 IEEE.

关键词： distributed cloud

来源：评论

学校读者我要写书评

暂无评论

The Art of Deception: Black-box Attack Against Text-to-image Diffusion Model 29

The Art of Deception: Black-box Attack Against Text-to-Image...

引用

29th IEEE International conference on parallel and distributed Systems, ICPADS 2023

作者： Lu, Yuetong Xu, Jingyao Li, Yandong Lu, Siyang Wei, Xiang Lu, Wei Beijing Jiaotong University School of Software Engineering Beijing China Beijing Jiaotong University School of Computer and Information Technology Beijing China University of Central Florida Department of Computer Science OrlandoFL United States

ISBN: (纸本)9798350330717

With the rise of Foundation models, Text-to-image models, as one of its important branches, have been increasingly applied. While focusing on the impressive generation capabilities of these models, it is also crucial to pay attention to the robustness of the models against attacks. In this paper, we shift our focus towards studying the vulnerability of Text-to-image (T2I) models. To this end, we propose a black-box attack method and demonstrate that T2I models are susceptible to adversarial text attacks. Specifically, this method can disrupt T2I models by making subtle modifications to the model's input (i.e., prompt) without accessing the model parameters, resulting in the generation of incorrect images. It is worth mentioning that we discovered the ability to switch different types of tokenizers within this black-box framework to handle text, furthermore, this attack framework can be applied to target different versions of T2I models. The experiments indicate that the images generated through adversarial text exhibit noticeable errors. We also employ CLIP score, a metric used to evaluate the similarity between images and image descriptions, to assess the results. The findings demonstrate a significant decrease in the visual-textual similarity after the model is subjected to attacks. Additionally, we have identified a specific type of error that T2I models tend to make when facing attacks - when confronted with unrecognizable text, the model often interprets it as human-related content. This paper not only highlights the vulnerability of T2I models to adversarial text attacks but also further discusses potential methods that could enhance the robustness of these attack techniques. This provides a valuable reference for future research directions in this field. © 2023 IEEE.

关键词： Diffusion ModelAdversarial Attack Foundation Model Text-to-image

来源：评论

学校读者我要写书评

暂无评论

Hercules: Scalable and Network Portable In-Memory Ad-Hoc File System for Data-Centric and High-Performance Applications 29th

Hercules: Scalable and Network Portable In-Memory Ad-Hoc Fil...

引用

29th International conference on parallel and distributed Computing (Euro-Par)

作者： Garcia-Blas, Javier Sanchez-Gallegos, Genaro Petre, Cosmin Martinelli, Alberto Riccardo Aldinucci, Marco Carretero, Jesus Univ Carlos III Madrid Leganes Spain Univ Torino Turin Italy

ISBN: (纸本)9783031396977;9783031396984

The growing demands for data processing by new data-intensive applications are putting pressure on the performance and capacity of HPC storage systems. The advancement in storage technologies, such as NVMe and persistent memory, are aimed at meeting these demands. However, relying solely on ultra-fast storage devices is not cost-effective, leading to the need for multi-tier storage hierarchies to move data based on its usage. To address this issue, ad-hoc file systems have been proposed as a solution. They utilise the available storage of compute nodes, such as memory and persistent storage, to create a temporary file system that adapts to the application behaviour in the HPC environment. This work presents the design, implementation, and evaluation of a distributed ad-hoc in-memory storage system (Hercules), highlighting the new communication model included in Hercules. This communication model takes advantage of the Unified Communication X framework (UCX). This solution leverages the capabilities of RDMA protocols, including Infiniband, Onmipath, shared memory, and zero-copy transfers. The preliminary evaluation results show excellent network utilisation compared with other existing technologies.

关键词： HPC Data intensive In-memory storage

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56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：