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

4,884 篇 会议
91 篇 期刊文献
21 册 图书

馆藏范围

4,996 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,835 篇 工学
- 1,763 篇 计算机科学与技术...
- 1,191 篇 信息与通信工程
- 935 篇 软件工程
- 878 篇 电气工程
- 274 篇 光学工程
- 139 篇 控制科学与工程
- 129 篇 电子科学与技术（可...
- 124 篇 生物工程
- 103 篇 生物医学工程（可授...
- 99 篇 仪器科学与技术
- 85 篇 机械工程
- 68 篇 网络空间安全
- 45 篇 化学工程与技术
- 30 篇 安全科学与工程
- 27 篇 动力工程及工程热...
- 26 篇 测绘科学与技术
1,207 篇 医学
- 1,186 篇 临床医学
- 34 篇 基础医学(可授医学...
- 31 篇 药学(可授医学、理...
- 28 篇 特种医学
1,056 篇 理学
- 755 篇 物理学
- 299 篇 数学
- 138 篇 生物学
- 84 篇 统计学（可授理学、...
- 53 篇 系统科学
- 50 篇 化学
254 篇 管理学
- 161 篇 管理科学与工程(可...
- 100 篇 图书情报与档案管...
47 篇 军事学
- 45 篇 军队指挥学
38 篇 法学
- 34 篇 社会学
14 篇 农学
10 篇 文学
8 篇 经济学
7 篇 教育学
2 篇 艺术学

主题

562 篇 image coding
549 篇 image processing
354 篇 visual communica...
326 篇 visualization
308 篇 feature extracti...
298 篇 image segmentati...
189 篇 image reconstruc...
181 篇 cameras
178 篇 image compressio...
175 篇 humans
161 篇 video coding
161 篇 signal processin...
131 篇 image enhancemen...
131 篇 image quality
127 篇 image analysis
127 篇 image color anal...
125 篇 image edge detec...
122 篇 training
119 篇 image retrieval
107 篇 decoding

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
25 篇 school of electr...
22 篇 school of electr...
20 篇 university of sc...
18 篇 shanghai jiao to...
16 篇 shanghai jiao to...
16 篇 tianjin univ sch...
16 篇 beijing universi...
13 篇 institute of ima...
12 篇 cas key laborato...
11 篇 university of el...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 school of comput...
10 篇 peking univ inst...
10 篇 tsinghua univ de...
10 篇 xidian univ sch ...
9 篇 zhejiang univers...
9 篇 microsoft res as...

作者

34 篇 zhai guangtao
26 篇 sumei li
25 篇 song li
22 篇 guangtao zhai
22 篇 li sumei
19 篇 li song
18 篇 li li
18 篇 min xiongkuo
16 篇 andré kaup
16 篇 dong liu
16 篇 shan liu
15 篇 yang xiaokang
14 篇 chen zhibo
14 篇 gao wen
13 篇 xie rong
13 篇 xiongkuo min
12 篇 kaup andre
11 篇 heming sun
11 篇 zhibo chen
11 篇 zhenzhong chen

语言

4,898 篇 英文
64 篇 土耳其文
31 篇 中文
20 篇 其他

检索条件"任意字段=Conference on Visual Communications and Image Processing 2007"

共 4996 条记录，以下是921-930 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 CBAM and IAL to Bayesian Loss-based Crowd Counting 23

Adapting CBAM and IAL to Bayesian Loss-based Crowd Counting

引用

Proceedings of the 2023 6th International conference on Artificial Intelligence and Pattern Recognition

作者： Huimin Du Yu Hao Xiaoyang Zhang Ying Liu Center for Image and Information Processing School of Communications and Information Engineering Xi'an University of Posts and Telecommunications China

ISBN: (纸本)9798400707674

Probability-originated crowding counting strategy has advantages of providing additional spatial information of pedestrians and smaller model scale. This paper proposes a novel Bayesian Loss-based crowd counting model which integrates the Convolutional Block Attention Module (CBAM)and Instance Attention Loss (IAL) to further address typical issues in crowd counting such as complicated background, occlusion, and uneven crowd distribution. After adapting the VGG-19 as the front-end network to efficiently extract visual features, the CBAM is implemented as the intermediate process to concentrate on the key features with the attention mechanism, before using the back-end network to output the predicted density map. To handle the deviation of manual labeled head positions in the dataset and improve the training efficiency, the IAL where only 90% of the annotation points with the smallest deviation from the prediction is adapted by the approach. Experiments results on two benchmarking datasets demonstrated the network's efficiency in enhancing headcount accuracy by significantly optimized the MAE(mean absolute error) and MSE(mean square error).

关键词： Bayesian loss CBAM IAL crowd counting density map

来源：评论

学校读者我要写书评

暂无评论

Improvement of Detection Rate for Small Objects Using Pre-processing Network 21

Improvement of Detection Rate for Small Objects Using Pre-pr...

引用

4th International conference on Control and Computer Vision, ICCCV 2021

作者： Lee, Doo Hee Cha, Gi Soon Iqbal, Ehtesham Song, Hyun Chul Choi, Kwang Nam Visual Image Media Lab Chung-Ang University Korea Republic of Nam-Seoul University Nam-Seoul University Korea Republic of

ISBN: (纸本)9781450390477

Artificial intelligence (AI) has been developing in a variety of methods over the past decade. However most AI experts worried to build a deep or wide network because the accuracy of AI models depends heavily on the depth of the network. In general deep and wide networks are better at learning than those that are less deep and wide and wide. On the other hand deeper networks are more complex and have many disadvantages such as computational cost and system specification dependency. We propose a novel method to improve the average recall rate for small objects in the deep convolutional network in the paper. The proposed method added pre-processing layer before the network rather than stacking the networks deeper or wide. The presented pre-processing layer consists of two major parts: up-sampling and down-sampling of the data. The overall objective of up-sampling and down-sampling is to enhance the resolution of small objects in the input image. The pre-processing network improves the average recall rate of the base network to 3.56%. This experiment result depicts that the proposed method outperforms the small object detection performance. © 2021 ACM.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Game Character Generation with Generative Adversarial Networks

Game Character Generation with Generative Adversarial Networ...

引用

IEEE Signal processing and communications Applications (SIU)

作者： Ferda Gü l Aydı n Emekligil İ lkay Ö ksü z Oyun ve Etkile&#x015F im Teknolojileri B&#x00F6 l&#x00FC m&#x00FC &#x0130 stanbul Teknik &#x00DC niversitesi &#x0130 stanbul T&#x00FC rkiye Bilgisayar M&#x00FC hendisli&#x011F i B&#x00F6

ISBN: (数字)9781665450928

ISBN: (纸本)9781665450935

Designing visual content and characters for games is a time consuming task even for designers and illustrators with experience. Most of the game companies and developers use procedural methods to automate the design process. The visual content produced by these algorithms is limited in terms of variation. In this paper, we propose to use Generative Adversarial Networks (GANs) for visual content production. Two different rpg and dnd visual image datasets were collected over the internet for training and 6 different GAN models were trained on them. In 3 of 18 experiments, transfer learning methods are used because of the limited datasets. The Frechet Inception Distance metric was used to compare the model results. As a result, SNGAN was the most successful in both datasets. Moreover, the transfer learning method (WGAN-GP, BigGAN) was more successful than the from scratch method.

关键词： Training visualization Transfer learning Character generation Signal processing algorithms Games Production

来源：评论

学校读者我要写书评

暂无评论

Geolocated visual Summarization of Social Media Data 28

Geolocated Visual Summarization of Social Media Data

引用

28th Signal processing and communications Applications conference (SIU)

作者： Sanhalp, Elif Bulbul, M. Abdullah Ankara Yildirim Beyazit Univ Bilgisayar Muhendisligi Ankara Turkey

ISBN: (纸本)9781728172064

The usage of social media is increasing day by day. People use social media platforms to communicate with their friends or other users and to demonstrate what they are interested in by sharing different kinds of media such as photos, texts, and videos. A portion of the posted content also include location information. Such posts having location information are called geo-tagged posts in social networks. According to the analysis of geo-tagged posts, popular locations or activities can be identified. This study proposes a method to identify the most representative subset of the visual content shared in a region through social media. Our approach aims to detect the popular places and events and utilizes Scale-Invariant Feature Transform (SIFT) features. Identified representative visuals are used to generate a web based tourist map. In this study, Flickr is used as the source of geo-tagged visual content.

关键词： image processing social media analysis geo-tagged images Flickr location information SIFT feature extraction

来源：评论

学校读者我要写书评

暂无评论

Involution Based Speech Autoencoder: Investigating the Advanced Vision Operator Performance on Speech Feature Extraction 10

Involution Based Speech Autoencoder: Investigating the Advan...

引用

10th IEEE Global conference on Consumer Electronics, GCCE 2021

作者： Zhong, Tianle Velazquez, Israel Mendoza Haneda, Yoichi University of Electronic Science And Technology of China School of Computer Science And Engineering Chengdu China University of Electro-Communications Graduate School of Informatics Tokyo Japan

ISBN: (纸本)9781665436762

Feature extraction is an important aspect of deep learning. In recent studies, various methods from image processing have been applied to speech feature extraction. Although the involution operator has achieved great success in vision recognition, the use of the involution operator in speech tasks has not been investigated. To determine whether the performance improvement of this operator on visual tasks is reflected directly in the speech processing domain, this study investigated autoencoder networks operating on Mel-spectrograms utilizing involution and convolution. It was determined that convolution continues to outperform involution as a direct replacement. The reasons for discrepancies in the input feature dimensions of different fields are discussed. Based on its channel-agnostic property, involution in combination with convolution requires additional research. © 2021 IEEE.

关键词： Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Encoded Deep Features for visual Place Recognition 28

Encoded Deep Features for Visual Place Recognition

引用

28th Signal processing and communications Applications conference (SIU)

作者： Hafez, A. H. Abdul Alqaraleh, Saed Tello, Ammar Hasan Kalyoncu Univ Comp Engn Dept Gaziantep Turkey

ISBN: (纸本)9781728172064

In this work, a new VPR approach that uses the features extracted from a Convolutional Neural Network (CNN) architecture that will be encoded by the Fisher Vector (FV) is introduced. As the main aim of this work is to develop a robust approach that can meet real-life challenges, the deep features are encoded with FV, which as shown in the experiments section, can lead to getting more robust features. Our approach was evaluated using two classifiers, Dynamic Time Warping (DTW) and Support Vector Machine (SVM) in particular. Using both classifiers, the FV-based encoded features have outperformed the non-encoded features.

关键词： Dynamic time warping Deep features Fisher Vector CNN image sequence matching visual place recognition

来源：评论

学校读者我要写书评

暂无评论

TSAN et: Two-subnet Attention Network for Single image Dehazing

TSAN et: Two-subnet Attention Network for Single Image Dehaz...

引用

International conference on Wireless communications and Signal processing (WCSP)

作者： Chenran Jiang Fei Yan Tao Deng Lin Sun Jun Li School of Information Science and Technology Southwest Jiaotong University Chengdu China China Electronic Product Reliability and Environmental Testing Research Institute Guangzhou China

ISBN: (纸本)9781665450867

Haze restricts visual quality and degrades the qual-ity of captured images. The aim of single image dehazing is to recover a haze-free image from a hazy one. However, most present image dehazing methods treat different feature information in channels and pixels evenly, which may influence the dehazing result because of the uneven distribution of haze. To address hazy uneven distribution, we propose an end-to-end two-sub net attention network (TSANet), which consists of attention-recurrent (AR) and asymmetric u-shaped dehazing refinement (AUDR). In addition, a feature residual attention (FRA) block is designed to focus on thick-hazy regions and high-frequency regions of a hazy image when dehazing. In the model, the input image is first fed into the AR sub-network to extract feature information like thick hazy regions and high-frequency regions. For further feature refinement, we propose the AUDR sub-network to further process feature information from the AR sub-network. The AUDR sub-network adopts an encoder-decoder module containing FRA and transformer blocks to further process feature information of high-frequency regions and filter hazy feature information, and uses skip connections to enhance the representation of our TSANet. The extensive experimental results demonstrate the effectiveness of our method and outperform other dehazing methods on synthetic and real-world hazy datasets.

关键词： Wireless communication visualization Computer vision Signal processing Feature extraction Information filters Transformers

来源：评论

学校读者我要写书评

暂无评论

Research on image Defogging Algorithm for Power Monitoring

Research on Image Defogging Algorithm for Power Monitoring

引用

International conference on Communication Technology (ICCT)

作者： Li Jiang Chaoxing Zhao School of Electrical and Information Engineerin Zhengzhou University Zhengzhou China

With the continuous expansion of power grid scale, smart grid has become the mainstream of power monitoring. Bad weather conditions such as smog will lead to the deterioration of the quality of captured images, which will further restrict the development of smart grid. In this paper, an image defogging algorithm is proposed according to the characteristics of power monitoring images. According to the characteristics of image regions, the image is divided into sky regions and non sky regions. For non sky regions, an improved dark channel prior algorithm is used to solve the problem of poor detail processing. For sky regions, a large number of experiments have observed that there is a linear relationship between the minimum channels of fog free images and fog images. It improves the poor segmentation effect of the conventional algorithm in the sky area, and applies the synthetic projection rate and atmospheric light to the defogging of the power monitoring image. Compared with other defogging methods, its objective indicators are improved, and the overall visual effect of the defogging image is good.

关键词： image segmentation Force visual effects communications technology Smart grids Complexity theory Monitoring

来源：评论

学校读者我要写书评

暂无评论

An algorithm for parallel processing of traffic signs video on a graphics processor

An algorithm for parallel processing of traffic signs video ...

引用

International conference on Information Science and communications Technologies (ICISCT)

作者： Mukhriddin Umarov Jamshid Elov Sirojiddin Khalilov Inomjon Narzullayev Marat Karimov dept. Department of Software Engineering Samarkand branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Samarkand Uzbekistan dept. Department of Hardware and Software of Management Systems in Telecommunication Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Tashkent Uzbekistan dept. Department of Information Technologies Nurafshan branch of Tashkent University of Information Technologies named after Muhammad al-Khwarizmi Tashkent Uzbekistan

In the lighting conditions such as snowing, hazing, raining, and weak lighting condition, the accuracy of traffic sign recognition is not very high. It is important to develop an algorithms for real-time fast detection of road signs from video images and use them in driver assistance systems. Firstly, we image preprocessing by using dark channel prior based image dehazing for remove noises from the input image. In this article, we develop a transposed image filtering method combined with other fast parallel filtering algorithms. We propose a high-speed and high-accuracy method by improving image dehazing algorithms and analyzing GPU architecture. In this, we quickly removing fog from HD video images using DCP with image quality and visual effects.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Human Attention Based Movie Summarization: Dataset and Baseline Model

Human Attention Based Movie Summarization: Dataset and Basel...

引用

2022 IEEE International conference on Multimedia and Expo, ICME 2022

作者： Zhao, Defang Zhu, Dandan Min, Xiongkuo Yue, Jiaomin Zhang, Kaiwei Zhou, Qiangqiang Zhai, Guangtao Yang, Xiaokang CloudWalk Technology Shanghai China School of Computer Science and Technology Donghua University Shanghai China Institute of Image Communication and Network Engineering Shanghai Jiao Tong University Shanghai China School of Software Jiangxi Normal University Nanchang China Ai Institute Shanghai Jiao Tong University MOE Key Lab of Artificial Intelligence Shanghai China

ISBN: (数字)9781665485630

ISBN: (纸本)9781665485630

The movie summarization model can automatically edit a condensed and succinct version of the movie by selecting the keyframes. Previous works mainly resort to hand-crafted heuristics and most of them are unsupervised. Supervised movie summarization is a new research field and, there is currently no publicly suitable dataset available. Moreover, existing works only focus on the movies themselves while neglecting the audiences, who have the most say in which part of the movie is more attractive. To deal with the aforementioned limitations, we establish a human attention based movie summarization dataset Movie50. Specifically, we explore the human attention variations when watching videos and have the following findings: (1) The attention of humans is concentrated when watching keyframes. (2) The attention of humans is distracted when watching non-keyframes. Inspired by these findings, we collect the eye fixations of 20 participants when watching 50 movies and propose a novel human attention based annotation pipeline. In addition, we introduce A/V-MSNet, an audiovisual neural network that takes advantage of spatio-temporal visual and auditory information to better model human attention as well as exploit more plentiful information. Extensive experiments demonstrate the superiority of the proposed method. © 2022 IEEE.

关键词： Motion pictures

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 << < 89 90 91 92 93 94 95 96 97 98 > >>

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：