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

1,778 篇 会议
14 册 图书
11 篇 期刊文献

馆藏范围

1,803 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,386 篇 工学
- 1,114 篇 计算机科学与技术...
- 818 篇 软件工程
- 457 篇 信息与通信工程
- 331 篇 光学工程
- 303 篇 控制科学与工程
- 199 篇 电气工程
- 181 篇 生物工程
- 152 篇 机械工程
- 126 篇 生物医学工程（可授...
- 97 篇 电子科学与技术（可...
- 85 篇 仪器科学与技术
- 65 篇 安全科学与工程
- 60 篇 化学工程与技术
- 42 篇 材料科学与工程（可...
- 40 篇 交通运输工程
- 25 篇 网络空间安全
615 篇 理学
- 373 篇 物理学
- 194 篇 数学
- 192 篇 生物学
- 61 篇 统计学（可授理学、...
- 58 篇 化学
- 25 篇 系统科学
222 篇 管理学
- 129 篇 管理科学与工程(可...
- 107 篇 图书情报与档案管...
- 46 篇 工商管理
136 篇 医学
- 125 篇 临床医学
- 58 篇 基础医学(可授医学...
- 48 篇 药学(可授医学、理...
37 篇 农学
- 33 篇 作物学
25 篇 艺术学
- 25 篇 设计学（可授艺术学...
20 篇 教育学
18 篇 法学
15 篇 经济学
4 篇 军事学
1 篇 文学

主题

289 篇 computer vision
164 篇 image processing
106 篇 feature extracti...
99 篇 deep learning
99 篇 image segmentati...
50 篇 object detection
47 篇 machine vision
47 篇 computational mo...
47 篇 convolutional ne...
45 篇 image enhancemen...
44 篇 image recognitio...
43 篇 cameras
37 篇 accuracy
36 篇 image edge detec...
36 篇 face recognition
34 篇 machine learning
33 篇 image color anal...
33 篇 training
31 篇 image reconstruc...
30 篇 visualization

机构

6 篇 shenyang institu...
6 篇 university of ch...
6 篇 shenyang ligong ...
5 篇 department of co...
4 篇 key laboratory o...
4 篇 school of softwa...
4 篇 school of inform...
4 篇 department of co...
4 篇 college of compu...
4 篇 beijing informat...
3 篇 school of comput...
3 篇 shanghaitech uni...
3 篇 chitkara univers...
3 篇 university of el...
3 篇 school of comput...
3 篇 institute for co...
3 篇 guangzhou civil ...
3 篇 institutes for r...
3 篇 babol noshirvani...
3 篇 computer vision ...

作者

5 篇 raman balasubram...
5 篇 lu zongqing
4 篇 zhang chao
4 篇 balasubramanian ...
4 篇 ramani sanjeev k...
4 篇 wang wei
4 篇 hossain syed akh...
4 篇 iyengar s.s.
4 篇 sanjeev kaushik ...
3 篇 liu bo
3 篇 kumar krishan
3 篇 zhang ji
3 篇 elizabeth rani g...
3 篇 neehal nafis
3 篇 rabby akm shahar...
3 篇 luc van gool
3 篇 farag aly a.
3 篇 zhao jiewen
3 篇 zou xiaobo
3 篇 zhang hualiang

语言

1,721 篇 英文
65 篇 其他
19 篇 中文
1 篇 土耳其文

检索条件"任意字段=2nd International Conference on Computer Vision and Image Processing, CVIP 2017"

共 1803 条记录，以下是571-580 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：

Application of computer vision Technology in Environmental Art Design

Application of Computer Vision Technology in Environmental A...

引用

international conference on Artificial Intelligence and computer Information Technology (AICIT)

作者： Qian Li Sichuan Agricultural University Chengdu Sichuan Province China

computer vision technology is a multidisciplinary field that encompasses a diverse range of research areas, including image processing, automation, computer science, and optics. Within the context of environmental art design, the use of virtual reality technology can provide designers with a wealth of opportunities to explore and create innovative design solutions. By utilizing computer vision technology in environmental art design, designers can remain at the forefront of the latest technological developments, while also being able to more effectively showcase a range of design solutions and styles. The use of computer vision technology in environmental art design has become increasingly important, as designers seek to explore new ways to create unique and engaging environments. With the ability to utilize virtual reality technology, designers can create immersive and interactive environments that are rich in detail and complexity. by leveraging the power of computer vision technology, designers can explore new design solutions that may have been previously difficult or impossible to achieve. This paper will examine the various advantages of utilizing computer vision technology in environmental art design, and explore the most effective application strategies for promoting the improvement of environmental art design. By analyzing the latest research and technological developments in the field of computer vision, this paper will provide designers with the tools and resources they need to create truly innovative and engaging environmental designs. Ultimately, by embracing the power of computer vision technology, designers can help to transform the field of environmental art design, and create environments that are both visually stunning and functionally effective.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LS DETR: Lightweight DETR with Selective Transmission Training Strategy

LS DETR: Lightweight DETR with Selective Transmission Traini...

引用

Algorithm, image processing and Machine vision (AIPMV), international conference on

作者： Xvjian Li Xuekuan Zhang School of Computer Science and Engineering Shandong University of Science and Technology Qingdao Shandong Province China

ISBN: (数字)9798350390254

ISBN: (纸本)9798350390261

Recently, models based on Detection Transformer (DETR) have achieved significant accomplishments due to their end-to-end performance. However, DETR-like models consistently face challenges such as high computational costs and the phenomenon of correct predictions in the intermediate stages but incorrect predictions in the final decoding stage. This paper introduces a new end-to-end object detection framework, namely LS DETR. In response to the large number of query tokens brought by the multi-scale attention in Deformable DETR, the authors designed an alternating updating method. This method interleaves the updates of high-level and low-level features in the encoder to reduce computational costs. Additionally, the authors noted a common issue in existing DETR models where intermediate stage predictions are often correct, but final stage predictions are erroneous. To address this issue, this paper proposes a selective transmission training strategy. It selectively collects queries from the intermediate stages and sends them to the later decoding stages while simultaneously strengthening the training of the later stages. Comprehensive experiments demonstrate that LS DETR outperforms existing models and can be applied to various DETR-like models. For instance, on COCO val2017, LS DETR achieves a 2.2% higher performance than Co-DINO, with a simultaneous 59% reduction in GFLOPs.

关键词： Training Accuracy Computational modeling Machine vision Object detection Predictive models Transformers Computational efficiency Decoding Faces

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based Finger Visual Feature Recognition and Realization 2021

FPGA-Based Finger Visual Feature Recognition and Realization

引用

2nd international conference on Artificial Intelligence and Information Systems (ICAIIS )

作者： Feng, Qingjuan Gao, Jingmin Beijing Informat Sci & Technol Univ Beijing 100101 Peoples R China

ISBN: (纸本)9781450390200

To increase human-computer interaction speed and accuracy, this paper first studies the application of color clustering-based skin color recognition algorithm in finger touch screen. Next, it optimizes rectangular template-based dynamic threshold algorithm from two aspects: rectangular scanning template size and dynamic threshold selection, thereby proposing a new algorithm for finger visual feature recognition under dynamic conditions. The simulation results indicate that this algorithm is less affected by the environment with higher recognition accuracy, which enables accurate calculation and extraction of center point position of the finger image. Finally, this recognition algorithm is implemented in hardware on FPGA. The test results show that both the image processing speed and algorithm recognition accuracy can meet the requirements of human-computer interaction system.

关键词： computer vision finger recognition rectangular template dynamic threshold

来源：评论

学校读者我要写书评

暂无评论

Video Captioning using Deep Learning and NLP to Detect Suspicious Activities 2

Video Captioning using Deep Learning and NLP to Detect Suspi...

引用

2nd international conference on Signal and Information processing, IConSIP 2022

作者： Shingare, Santuk Haribhakta, Yashodhara Rajmane, Dhananjay Manufacturing Engineering & Industrial Management College of Engineering Pune Pune India Computer & It College of Engineering Pune Pune India Software Engineer

ISBN: (纸本)9781728168852

In recent years, computer vision has been getting a lot of attention. Big data is being generated from surveillance videos. Analysis of this video data in real-time helps in getting the gist of events occurring. Video captioning is the task of generating the descriptions of the video. The transformer model has shown remarkable accuracy on machine translation tasks. Visual transformers have shown great accuracy in the classification of videos. Using the existing method to extract the entity, motion, and textual features from a given video. These extracted features are later used for generating the captions. The custom dataset used here is based on the military domain. These captions are further analyzed to detect suspicious activity in real-time. This paper is the implementation of the video captioning model for the military-specific domain. The generative model is based on a transformer model combined with PWC (pyramid, wrap, cost volume) architecture pre-trained on the Kinetic dataset and pre-trained Glove embeddings. We will be using custom military-specific captions. The detailed results from the video captioning experiment are presented here. The captions generated from the test image are evaluated. The BLEU (bilingual evaluation understudy) and METEOR scores are evaluated. © 2022 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Research on Optimization Algorithm of image Recognition Performance Based on Convolution Neural Network computer Big Data Technology

Research on Optimization Algorithm of Image Recognition Perf...

引用

image processing and computer Applications (ICIPCA), IEEE international conference on

作者： Liqiong Pan Anhui Sanlian University Anhui Hefei China

ISBN: (数字)9798350360240

ISBN: (纸本)9798350384161

With the development of computer vision and deep learning technology, the application of fusion convolutional neural network (CNN) and big data technology in the field of image recognition is increasingly extensive and deep. In this paper, a fusion convolutional neural network model named CI-Net is designed to optimize image recognition performance based on CNN. The model uses the technology of integrating multi-size convolution kernel in the same layer structure to extract image features from different scales through multiple independent branches, which not only effectively broadens the width of the network to capture rich and diverse feature information, but also enhances the robustness and generalization ability of the network. In terms of model optimization, the paper abandons the traditional fully connected layer and adopts convolutional layer instead, which significantly reduces the total number of model parameters and effectively reduces the risk of overfitting. Experiments show that the structure design of CI-Net network is scientific and reasonable, and its convergence speed is faster in the training process. Under the premise of keeping the number of parameters far lower than that of similar convolutional neural network models, it can still achieve lower recognition error rate, fully demonstrating its superior performance and efficient generalization ability in image recognition tasks. This research is of great value for improving the performance of image recognition system based on computer big data technology.

关键词： image recognition Error analysis Convolution Computational modeling Big Data Feature extraction Convolutional neural networks Kernel Optimization Convergence

来源：评论

学校读者我要写书评

暂无评论

FPGA-Based High-Speed Infrared image Acquisition and Transmission Design

FPGA-Based High-Speed Infrared Image Acquisition and Transmi...

引用

international conference on Artificial Intelligence and computer Information Technology (AICIT)

作者： Gang Ye Tianxu Zhang Lu Fang School of Electrical and Information Enginerring WuHan Institute of Technology WuHan China School of Artificial Intelligence and Automation Huazhong University of Science and Technology WuHan China

With the rapid development of electronic technology and computer vision technology, the requirements for real-time and fast image acquisition are increasing, and it is difficult to implement on a dedicated integrated chip with long development cycle, while the design features of FPGA parallel pipeline, in addition to low power consumption and low cost of the chip, make the real-time and fast image acquisition and transmission on FPGA chips are guaranteed. The interface between the infrared detector and the FPGA acquisition system uses the industrial high-speed serial data and connection protocol Camera Link interface, and due to the very large amount of data transmission, an easy-to-use Gigabit Ethernet port is used as the interface between the high-speed transmission system and the host computer. The system is implemented under VIVADO2019 software, and the logic functions are developed using hardware description language, in addition to the modelsim simulation verification. In the normal operation of the system: the system can achieve high speed image acquisition and transmission, and the image acquisition reaches 50 frames per second, and the transmission to the host computer can also display the image processing results in real time, which has high practical application value.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Network (GNN) in image and Video Understanding Using Deep Learning for computer vision Applications 2

Graph Neural Network (GNN) in Image and Video Understanding ...

引用

2nd international conference on Electronics and Sustainable Communication Systems, ICESC 2021

作者： Pradhyumna, P. Shreya, G.P. Mohana RV College of Engineering® Electronics and Telecommunication Engineering Karnataka Bengaluru India

ISBN: (纸本)9781665428675

Graph neural networks (GNNs) is an information - processing system that uses message passing among graph nodes. In recent years, GNN variants including graph attention network (GAT), graph convolutional network (GCN), and graph recurrent network (GRN) have shown revolutionary performance in computer vision applications using deep learning and artificial intelligence. These neural network model extensions, collect information in the form of graphs. GNN may be divided into three groups based on the challenges it solves: link prediction, node classification, graph classification. Machines can differentiate and recognise objects in image and video using standard CNNs. Extensive amount of research work needs to be done before robots can have same visual intuition as humans. GNN architectures, on the other hand, may be used to solve various image categorization and video challenges. The number of GNN applications in computer vision not limited, continues to expand. Human-object interaction, actin understanding, image categorization from a few shots and many more. In this paper use of GNN in image and video understanding, design aspects, architecture, applications and implementation challenges towards computer vision is described. GNN is a strong tool for analysing graph data and is still a relatively active area that needs further researches attention to solve many computer vision applications. © 2021 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

FPGA-based image signal processing CEPST module design 2

FPGA-based image signal processing CEPST module design

引用

2nd international conference on Frontiers of Applied Optics and computer Engineering, AOCE 2025

作者： Tsai, Lifen Chen, Chinta Yang, Chihchung Tang, Lijie Wang, Xiahui Xue, Wuyang Ma, Huan Zhaoqing University Guangdong China Zhaoqing University Guangdong China

ISBN: (纸本)9781510689404

CEPST algorithm is an important step in image processing, which is widely used in computer vision, pattern recognition, and machine learning. In order to improve the efficiency and performance of CEPST algorithm, more and more studies have implemented the task of CEPST algorithm on FPGA boards in recent years. FPGA boards offer parallel computing capabilities, low power consumption, and low latency, making them suitable for high-performance computing and real-time applications. In this paper, the Vivado tool is used to implement the method of CEPST algorithm. Vivado has a complete toolchain and debugging environment, supports a variety of hardware description languages, and provides a rich set of IP cores and acceleration libraries to facilitate FPGA design and development. This paper details the steps of CEPST algorithm using Vivado, from algorithm design to simulation. The CEPST algorithm was designed to improve the accuracy and speed, and further improve the performance of the overall system. © The Authors.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Deep Graph Convolutional Neural Network based on Adaptive Sampling and Aggregation Strategy

Deep Graph Convolutional Neural Network based on Adaptive Sa...

引用

Machine vision, image processing and Imaging Technology (MVIPIT), international conference on

作者： Xueli Wang Wei Zhang Gege Li Lin Zhou Hongkai Liu Zhonglin Ye School of Computer Qinghai Normal University Xining Qinghai Provincial Key Laboratory of Tibetan Information Processing and Machine Translation Xining Graduate School of Engineering Nagasaki Institute of Applied Science Nagasaki

ISBN: (数字)9798331543037

ISBN: (纸本)9798331543044

Graph neural networks learn node embeddings by recursively sampling and aggregating nodes in a graph, while existing methods have a fixed pattern of node sampling and aggregation, and usually only consider direct neighborhood. When sampling high-order neighborhood, it is easy to produce over-smoothing, which affects the model performance and accuracy. Therefore, this paper proposes an adaptive sampling and aggregation deep graph convolutional network (Adaptive Sampling and Aggregation Depth Graph Convolutional Network, ASA-GCN). A sampling strategy based on node importance is designed to adaptively sample high-order neighbors of nodes. Meanwhile, an aggregation strategy based on self-attention mechanism is proposed to adaptively aggregate node information within a given neighborhood. Finally, experimental results on multiple benchmark graph datasets show that the model has superior performance on the node classification task.

关键词： Representation learning Adaptation models Adaptive systems Accuracy Graph convolutional networks Aggregates Imaging Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

STFP: Automatic Video Occlusion Detection and Reconstruction via Spatial-Temporal Feature Propagation

STFP: Automatic Video Occlusion Detection and Reconstruction...

引用

Algorithm, image processing and Machine vision (AIPMV), international conference on

作者： Yanhan Zheng Hubin Middle School Xiamen China

ISBN: (数字)9798350390254

ISBN: (纸本)9798350390261

With the maturity of computer networks and camera equipment, video data in the Internet is growing exponentially. However, video resource usually exhibits hole-like missing or occlusion, which may affect the visual content presentation. Occlusion detection and reconstruction is an effective way for general missing problem, which aims to recognize all the missing areas and fill them with appropriate pixels to complete the reconstruction task. The technology is still challenging due to the difficulties of high computational complexity, complex occluded shapes and high requirement on the spatial-temporal consistency between sequential video frames. In this paper, we propose a novel method called STFP to automatically detect the occlusions or missing regions in the video frames and complete the corresponding content reconstruction based on spatial-temporal feature propagation. Specifically, we make full reference to the feature values of adjacent pixels in temporal and spatial frames to estimate coarse pixels in the occluded regions, and then we formulate the occlusion reconstruction as a feature-interpolated optimization problem by filling and propagating the best-match pixels from the candidate content. Experimental results indicate that the proposed STFP can produce competitive results, both in objective and subjective quality. It outperforms competing method significantly with an average PSNR and SSIM as high as 39.60 and 0.92, respectively.

关键词： Visualization Technological innovation Shape Heuristic algorithms Machine vision Reconstruction algorithms Feature extraction Internet image reconstruction Optimization

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181页 << < 54 55 56 57 58 59 60 61 62 63 > >>

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：