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

7,402 篇 会议
350 篇 期刊文献
57 册 图书
17 篇 学位论文

馆藏范围

7,826 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
- 3,421 篇 计算机科学与技术...
- 1,719 篇 软件工程
- 1,074 篇 电气工程
- 713 篇 信息与通信工程
- 343 篇 控制科学与工程
- 339 篇 电子科学与技术（可...
- 307 篇 光学工程
- 233 篇 机械工程
- 224 篇 生物医学工程（可授...
- 177 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...
- 50 篇 材料科学与工程（可...
- 47 篇 土木工程
- 41 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
- 79 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

869 篇 parallel process...
693 篇 image processing
326 篇 image segmentati...
297 篇 concurrent compu...
272 篇 distributed comp...
260 篇 computational mo...
252 篇 computer archite...
250 篇 feature extracti...
215 篇 image reconstruc...
195 篇 image edge detec...
185 篇 image coding
177 篇 graphics process...
170 篇 iterative method...
165 篇 algorithm design...
165 篇 hardware
164 篇 neural networks
159 篇 computer science
159 篇 deep learning
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

7,661 篇 英文
109 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 7826 条记录，以下是1361-1370 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：

Computing on Functions Using Randomized Vector Representations (in brief) 2022

Computing on Functions Using Randomized Vector Representatio...

引用

Annual Neuro-Inspired Computational Elements conference (NICE)

作者： Frady, E. Paxon Kleyko, Denis Kymn, Christopher J. Olshausen, Bruno A. Sommer, Friedrich T. Intel Labs Santa Clara CA 95054 USA Univ Calif Berkeley Berkeley CA USA Res Inst Sweden Kista Sweden

ISBN: (纸本)9781450395595

Vector space models for symbolic processing that encode symbols by random vectors have been proposed in cognitive science and connectionist communities under the names Vector Symbolic Architecture (VSA), and, synonymously, Hyperdimensional (HD) computing [22, 31, 46]. In this paper, we generalize VSAs to function spaces by mapping continuous-valued data into a vector space such that the inner product between the representations of any two data points approximately represents a similarity kernel. By analogy to VSA, we call this new function encoding and computing framework Vector Function Architecture (VFA). In VFAs, vectors can represent individual data points as well as elements of a function space (a reproducing kernel Hilbert space). The algebraic vector operations, inherited from VSA, correspond to well-defined operations in function space. Furthermore, we study a previously proposed method for encoding continuous data, fractional power encoding (FPE), which uses exponentiation of a random base vector to produce randomized representations of data points and fulfills the kernel properties for inducing a VFA. We show that the distribution from which components of the base vector are sampled determines the shape of the FPE kernel, which in turn induces a VFA for computing with band-limited functions. In particular, VFAs provide an algebraic framework for implementing large-scale kernel machines with random features, extending [51]. Finally, we demonstrate several applications of VFA models to problems in image recognition, density estimation and nonlinear regression. Our analyses and results suggest that VFAs constitute a powerful new framework for representing and manipulating functions in distributed neural systems, with myriad potential applications in artificial intelligence.

关键词： Hyperdimensional Computing Vector Symbolic Architectures Holographic Reduced Representations Kernel methods Population Coding Theoretical Neuroscience

来源：评论

学校读者我要写书评

暂无评论

Learning to Identify Correct 2D-2D Line Correspondences on Sphere

Learning to Identify Correct 2D-2D Line Correspondences on S...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Li, Haoang Chen, Kai Zhao, Ji Wang, Jiangliu Kim, Pyojin Liu, Zhe Liu, Yun-Hui Chinese Univ Hong Kong Hong Kong Peoples R China TuSimple Beijing Peoples R China Sookmyung Womens Univ Seoul South Korea Univ Cambridge Cambridge England

ISBN: (纸本)9781665445092

Given a set of putative 2D-2D line correspondences, we aim to identify correct matches. Existing methods exploit the geometric constraints. They are only applicable to structured scenes with orthogonality, parallelism and coplanarity. In contrast, we propose the first approach suitable for both structured and unstructured scenes. Instead of geometric constraint, we leverage the spatial regularity on sphere. Specifically, we propose to map line correspondences into vectors tangent to sphere. We use these vectors to encode both angular and positional variations of image lines, which is more reliable and concise than directly using inclinations, midpoints or endpoints of image lines. Neighboring vectors mapped from correct matches exhibit a spatial regularity called local trend consistency, regardless of the type of scenes. To encode this regularity, we design a neural network and also propose a novel loss function that enforces the smoothness constraint of vector field. In addition, we establish a large real-world dataset for image line matching. Experiments showed that our approach outperforms state-of-the-art ones in terms of accuracy, efficiency and robustness, and also leads to high generalization.

关键词： Computer vision Computer network reliability Neural networks parallel processing Market research Robustness Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Research and Design of Remote Management of distributed Airport Security Inspection Equipment Based on Machine Vision 2021

Research and Design of Remote Management of Distributed Airp...

引用

2021 International conference on Aviation Safety and Information Technology

作者： Ying Chen Ruiqing Shi Hainan College of Vocational and Technical China Haikou Meilan International Airport security station China

ISBN: (纸本)9781450390422

With the rapid increase of domestic airport scale, passenger throughput and the change of international situation, the types and quantity of airport security inspection equipment have increased greatly, and centralized management will greatly improve its management efficiency. However, there are no related products or systems in China at present. This paper studies a distributed remote management system of airport security inspection equipment based on machine vision. The hardware system of acquisition terminal is designed and implemented, and the sensor network of security inspection equipment of single terminal building based on ZigBee technology is established. In this paper, aiming at machine vision and image processing technology, through effective image processing and pattern recognition methods, such as geometric transformation, filtering and denoising, threshold processing, etc., the image is converted into machine-readable form, and then the software program is used to process, analyze and read to obtain the corresponding information, so as to realize card and card reading. The embedded Web Server function is adopted to publish the monitoring platform to the work local area network, which realizes the remote monitoring of security inspection equipment by users in the local area network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Dual-Branch Network: Design and Optimization of High-Accuracy Sky Segmentation

Deep Dual-Branch Network: Design and Optimization of High-Ac...

引用

Computer Science, Electronic Information Engineering and Intelligent Control Technology (CEI), IEEE International conference on

作者： Xiangrong Fu Yang Shu Liya Tian Binzi Wang Wanyu Yang Youdong Ding Shanghai Film Academy Shanghai University Shanghai China

ISBN: (数字)9798350372052

ISBN: (纸本)9798350372069

This paper presents an innovative network based on deep learning for sky segmentation, a key task in image processing. Sky segmentation has various applications in computer vision, but traditional methods struggle to meet accuracy and efficiency requirements due to the diverse and complex nature of the sky in different scenes. To address this challenge, we propose a semantic-detail dual-branch sky segmentation network that draws inspiration from the visual characteristics and segmentation needs of the sky. The network aims to enhance the accuracy and detail sensitivity of the sky area through the parallel design of the semantic branch and the detail branch, along with the introduction of a feature fusion module. We train the network using the AED20K subset of datasets, which enables fine segmentation of sky regions. Through extensive experiments on multiple datasets, we demonstrate that our network achieves significant performance improvements in sky segmentation tasks, delivering excellent accuracy and outstanding sensitivity to detail.

关键词： Deep learning image segmentation Visualization Computer vision Sensitivity Semantics Process control

来源：评论

学校读者我要写书评

暂无评论

Developing a Loss Prediction-based Asynchronous Stochastic Gradient Descent Algorithm for distributed Training of Deep Neural Networks 20

Developing a Loss Prediction-based Asynchronous Stochastic G...

引用

49th International conference on parallel processing (ICPP)

作者： Li, Junyu He, Ligang Ren, Shenyuan Mao, Rui Univ Warwick Coventry W Midlands England Univ Oxford Oxford England Shenzhen Univ Shenzhen Peoples R China

ISBN: (纸本)9781450388160

Training Deep Neural Network is a computation-intensive and time-consuming task. Asynchronous Stochastic Gradient Descent (ASGD) is an effective solution to accelerate the training process since it enables the network to be trained in a distributed fashion, but with a main issue of the delayed gradient update. A recent notable work called DC-ASGD improves the performance of ASGD by compensating the delay using a cheap approximation of the Hessian matrix. DC-ASGD works well with a short delay;however, the performance drops considerably with an increasing delay between the workers and the server. In real-life large-scale distributed training, such gradient delay experienced by the worker is usually high and volatile. In this paper, we propose a novel algorithm called LC-ASGD to compensate for the delay, basing on Loss Prediction. It effectively extends the tolerable delay duration for the compensation mechanism. Specifically, LC-ASGD utilizes additional models that reside in the parameter server and predict the loss to compensate for the delay, basing on historical losses collected from each worker. The algorithm is evaluated on the popular networks and benchmark datasets. The experimental results show that our LC-ASGD significantly improves over existing methods, especially when the networks are trained with a large number of workers.

关键词： Neural Networks distributed Training Machine Learning

来源：评论

学校读者我要写书评

暂无评论

Hourglass Dehazing Network Based on Multi-scale parallel Fusion

Hourglass Dehazing Network Based on Multi-scale Parallel Fus...

引用

image processing, Computer Vision and Machine Learning (ICICML), International conference on

作者： Yishu Mao Xingcehn Song Xinman Zhang School of Automation Science and Engineering Xi’an Jiaotong University Xi’an China Institute of Artificial Intelligence and Robotics Xi’an Jiaotong University Xi’an China

ISBN: (纸本)9781665464697

As a common weather phenomenon, haze currently has some negative effects on advanced computer vision tasks. image dehazing, as a significant technique, plays a crucial role in deploying downstream vision tasks. In recent years, CNN-based end-to-end models have been proved to have great advantages over traditional image enhancement-based methods in removing image haze. However, some previous works failed to effectively utilize multi-scale features and perform reasonable feature fusion, resulting in the model losing the ability to restore details and colors. In this work, we adopt hourglass network which is a mature framework to better utilize the bottom-up and top-down symmetric topology structure for feature fusion and representation, so as to better recover the details and color information of haze-free images. At the same time, for the phenomenon of relatively indirect feature fusion in hourglass network, we propose a multi-scale parallel feature fusion module to perform more direct and effective feature fusion, thereby promoting the flow of features within different scales. What’s more, for the sake of strengthening the recovery power of the network for high-frequency information, we raise a spatial-frequency domain channel attention mechanism, so as to more effectively utilize spatial and frequency information for feature representation and enhancement. Comprehensive experiments on the public RESIDE dataset confirm the effectiveness of our proposed network that can satisfactorily reconstruct more elaborate and realistic colors.

关键词： Computer vision Time-frequency analysis image color analysis Network topology Computational modeling Machine learning image restoration

来源：评论

学校读者我要写书评

暂无评论

Analytical Modeling and Empirical Validation of Performability of Service- and Cloud-Based Dynamic Routing Architecture Patterns

Analytical Modeling and Empirical Validation of Performabili...

引用

Asia-Pacific conference on Software Engineering

作者： Amirali Amiri Uwe Zdun André van Hoorn Faculty of Computer Science Research Group Software Architecture University of Vienna Vienna Austria Department of Informatics Software Engineering and Construction Methods University of Hamburg Hamburg Germany

Many dynamic routing architectural patterns are available, including distributed routing, e.g., using the sidecar pattern, or centralized routing, e.g., using event stores or service buses. Different Quality-of-Service (QoS) factors influence routing schemas and technology selection, such as performance, reliability, scalability, and control properties offered by the patterns. An analytical model can formalize the QoS factors and facilitate the architectural decision-making when changing the routing scheme, i.e., to more distributed or centralized routing. So far, the impact of these architectural patterns on performability, i.e., the overall performance of a system with impeded reliability, has not been extensively studied. This is important because deciding to increase performance, e.g., by parallel processing of requests, may lead to decreased reliability because of the added points of a crash. We propose an analytical performability model during component crashes. For the empirical validation of our proposed model, we ran an extensive experiment of 2412 hours of runtime on a private cloud infrastructure and Google Cloud Platform. The low prediction error of 1.75 % indicates the high accuracy of our performability model. These results provide important insights when making architectural decisions regarding service- and cloud-based dynamic routing.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FUNCTIONAL FIBER JUNCTIONS FOR CIRCUIT ROUTING IN E-TEXTILES: DETERMINISTIC ALIGNMENT OF MEMS LAYOUT WITH FABRIC STRUCTURE 16

FUNCTIONAL FIBER JUNCTIONS FOR CIRCUIT ROUTING IN E-TEXTILES...

引用

16th ASME International Manufacturing Science and Engineering conference (MSEC)

作者： Challa, Sushmita Islam, M. Shafquatul Wei, Danming Beharic, Jasmin Popa, Dan O. Harnett, C. K. Univ Louisville Dept Elect & Comp Engn Louisville KY 40292 USA

ISBN: (纸本)9780791885079

Fabrics and fibrous materials offer a soft, porous, and flexible substrate for microelectromechanical systems (MEMS) packaging in breathable, wearable formats that allow airflow. Device-on-fiber systems require developments in the field of E-Textiles including smart fibers, functional fiber intersections, textile circuit routing, and alignment methods that adapt to irregular materials. In this paper, we demonstrate a MEMS-on-fabric layout workflow that obtains fiber intersection locations from high-resolution fabric images. We implement an image processing algorithm to drive the MEMS layout software, creating an individualized MEMS "gripper" layout designed to grasp fibers on a specific fabric substrate during a wafer-to-fabric parallel transfer step. The efficiency of the algorithm in terms of a number of intersections identified on the complete image is analyzed. The specifications of the MEMS layout design such as the length of the MEMS gripper, spatial distribution, and orientation are derivable from the MATLAB routine implemented on the image. Furthermore, the alignment procedure, tolerance, and hardware setup for the alignment method of the framed sample fabric to the wafer processed using the custom gripper layout are discussed along with the challenges of the release of MEMS devices from the Si substrate to the fabric substrate.

关键词： MEMS Textile Circuit Routing Binary image Analysis Algorithm

来源：评论

学校读者我要写书评

暂无评论

Robust Detection of Lighting LEDs by Analyzing the Geometric Structure of the Tunnel Interior Environment in Vehicle-Mounted Video Sequences 40

Robust Detection of Lighting LEDs by Analyzing the Geometric...

引用

40th Chinese Control conference (CCC)

作者： Xin, Le Shi, Zeyu Chen, Yangzhou Beijing Univ Technol Informat Dept Coll Artificial Intelligence & Automat Beijing 100124 Peoples R China Beijing Univ Technol Coll Metropolitan Transportat Beijing 100124 Peoples R China

ISBN: (纸本)9789881563804

Tunnel LED lighting system is an important infrastructure to ensure the safety and comfort of driving in highway tunnels. In this paper, an automatic robust detection of lighting LED lamps in highway tunnels based on vehicle-mounted video processing is proposed. By analyzing the geometric structure of the interior road environment in tunnels, this method includes the following three aspects. Firstly, the front-vehicle vanishing point is detected by using the M-estimator sample and consensus (MSAC) algorithm, just with the set of significant parallel lines extracted using the LSD (Line Segment Detector) operator. Secondly, after the dark region on the top of the tunnel is accurately segmented, an image segmentation algorithm based on adaptive threshold is adopted, realizing the LED lamp candidate region detection. Thirdly, this paper proposes post-processing methods to ensure the accurate detection of LED lamps in complex scenes with highlight-interference in the tunnel. The experimental results show that this method can robustly detect the LED lamps in the tunnel under complex conditions with high accuracy, which can meet the needs of efficient acceptance inspection and daily maintenance of tunnel LED lighting system.

关键词： Tunnel Lighting System Robust Detection of Lighting LEDs On-board Video processing Front-vehicle Vanishing Point Adaptive Threshold Segmentation

来源：评论

学校读者我要写书评

暂无评论

Deformable Spatial Pyramid Pooling for Road Scene Semantic Segmentation

Deformable Spatial Pyramid Pooling for Road Scene Semantic S...

引用

IEEE Intelligent Transportation Systems conference (ITSC)

作者： Lee, Jaeyoung Hyundai Mobis Seoul South Korea

ISBN: (纸本)9781728191423

Deformable convolution can handle the geometric transform appearing in the front camera image of the autonomous driving system. However, this method increases the size of the intermediate feature maps because it finds samples referenced by the kernel for each location. Moreover, the feature maps are interpolated to obtain accurate location data. Thus, it is difficult to configure modules due to increased GPU memory usage. In this paper, we propose squeezed deformable convolution robust to geometric changes while optimizing resource usage and a deformable spatial pyramid pooling (DSPP) module. The proposed convolution estimates the same data location as deformable convolution, but it uses squeeze convolution to compress the number of channels in feature processing. Therefore, memory usage and computations are decreased during sampling processing. Furthermore, memory usage can be more optimized for edge networks by removing the interpolation process using integer offsets additionally. The proposed DSPP module reinforces the scale-invariant characteristics by placing squeezed deformable convolutions in parallel and supplying inputs of different sizes. By sharing weights except for the squeeze layer, constraints are added to the sampling process, and the number of effective training samples is increased. The proposed methods are applied to the representative semantic segmentation network, ESPNet V2 and DeepLab V3+ with ResNet-50 to verify the effect. The mean intersection over union (mIoU) of DeepLab V3+ with the DSPP module is increased 1.5% on Cityscapes validation set. Also, ESPNet V2 with it provides 1.4% higher mIoU on Camvid test set. Therefore, the proposed method not only optimizes memory usage and computations but also improves recognition performance with enough margin.

关键词： Training Interpolation Convolution Roads conferences Semantics Graphics processing units

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 << < 133 134 135 136 137 138 139 140 141 142 > >>

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：