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
90 篇 期刊文献
21 册 图书

馆藏范围

4,995 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,834 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
- 128 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...
325 篇 visualization
308 篇 feature extracti...
297 篇 image segmentati...
189 篇 image reconstruc...
181 篇 cameras
178 篇 image compressio...
175 篇 humans
161 篇 video coding
160 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

4,896 篇 英文
64 篇 土耳其文
31 篇 中文
21 篇 其他

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

共 4995 条记录，以下是1301-1310 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：

Mono is Enough: Instance Segmentation from Single Annotated Sample

Mono is Enough: Instance Segmentation from Single Annotated ...

引用

IEEE visual communications and image processing (VCIP)

作者： Longrong Yang Hongliang Li Qingbo Wu Fanman Meng King Ngi Ngan University of Electronic Science and Technology of China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

With the help of various Deep Neural Networks, instance segmentation has achieved significant progress. How-ever, these successes are heavily reliant on large-scale manually annotated samples, which are extremely time-consuming and expensive. To address this issue, we propose a highly efficient anisotropic data augmentation method, which generates high quality training data from a single manually annotated sample. Instead of equivalently modifying foreground and background like traditional data augmentation methods, we focus on enriching the diversities of foreground appearance and positional relation between foreground and background, which are beneficial for the classification and localization sub-tasks respectively. All foreground instances of the source annotated sample undergo various rotation, brightness change, rescale, distortion and frequency-component mixup (FCM). Then, these modified instances are randomly embedded into background, which serve as new training samples. Experiments on Cityscapes dataset show that our method significantly outperforms traditional data augmentation methods.

关键词： image segmentation Distortion Brightness Data models Annotations Training data Task analysis

来源：评论

学校读者我要写书评

暂无评论

CLASSIFIER REFINEMENT FOR WEAKLY SUPERVISED OBJECT DETECTION WITH CLASS-SPECIFIC ACTIVATION MAP 26

CLASSIFIER REFINEMENT FOR WEAKLY SUPERVISED OBJECT DETECTION...

引用

26th IEEE International conference on image processing (ICIP)

作者： Du, Peilun Zhang, Haitao Ma, Huadong Beijing Univ Posts & Telecomm Beijing Key Lab Intelligent Telecomm Software & M Beijing Peoples R China

ISBN: (纸本)9781538662496

Weakly Supervised Object Detection (WSOD) is a challenging visual understanding task due to the absence of expensive human annotations like bounding boxes and segmentation. Recent WSOD methods usually generate a bounding box for the most contrastive part of the object rather than the entire object. Some methods alleviate the incompleteness problem of detection object with segmentation supplement or classifier refinement. However, segmentation requires high model cost and classifier refinement highly relies on the quality of initial candidate boxes at the beginning. In this paper, we propose a WSOD classifier refinement approach to overcome candidate boxes initialization and high segmentation model cost problems. Our approach can get high-quality class-specific activation maps for the objects and generate nail boxes at the maximum response point of the activation map to suppress incorrect refinement direction. Compared with previous methods, our WSOD classifier refinement approach can achieve 42.1% mAP on PASCAL VOC 2007 benchmarks without high segmentation model cost.

关键词： Weakly supervised learning object detection image-level annotations class-specific activation map

来源：评论

学校读者我要写书评

暂无评论

Comparison of Deep Learning, Data Augmentation and Bag of-visual-Words for Classification of Imbalanced image Datasets 2nd

Comparison of Deep Learning, Data Augmentation and Bag of-Vi...

引用

2nd International conference on Recent Trends in image processing and Pattern Recognition, RTIP2R 2018

作者： Saini, Manisha Susan, Seba Delhi Technological University Delhi India

ISBN: (纸本)9789811391804

image classification is a supervised machine learning task to classify images into different categories. As most real-world datasets are imbalanced in nature, instances are not equally distributed in all classes which often results in biased classification. So considering this objective, we are dealing with an imbalanced dataset. We have created a small size of an imbalanced dataset consisting of Ant and Plane images from Caltech-101 dataset. This paper illustrates the comparison between Deep learning, Data Augmentation and the Bag-of-visual Words (BOVW) for classification of imbalanced image datasets. According to the experimental results, it was found that deep learning results in higher accuracy in comparison to bag-of-visual-words (BOVW) and data augmentation. © 2019, Springer Nature Singapore Pte Ltd.

关键词： image classification

来源：评论

学校读者我要写书评

暂无评论

Dual-Graph Regularized Sparse Low-Rank Matrix Recovery for Tag Refinement 14th

Dual-Graph Regularized Sparse Low-Rank Matrix Recovery for T...

引用

14th International conference on Bio-inspired Computing: Theories and Applications, BIC-TA 2019

作者： Sun, Dengdi Bao, Yuanyuan Ge, Meiling Ding, Zhuanlian Luo, Bin Key Lab of Intelligent Computing and Signal Processing of Ministry of Education School of Computer Science and Technology Anhui University Hefei230601 China School of Internet Anhui University Hefei230039 China

ISBN: (纸本)9789811534140

In recent years, extremely large amounts of images with manual tags are easily available in many social websites such as Twitter, Flickr, and Instagram. However, these user-provided tags are often imprecise and incomplete, which inevitably limits the performances of image retrieval and other related applications. To this end, tag refitment technology aims at improving the quality of images tags automatically, and has been a fundamental challenge in Internet era. In this paper, we propose a novel dual-graph regularized sparse low-rank matrix recovery method, referred to as DGSLR briefly, to infer and improve the manual tags. Specifically, our DGSLR model first suppress the sparse noisy tags by norm, and decompose simultaneously the residual low-rank matrix to learning the low-dimensional vector representations of images and tags. Moreover, the visual similarities and the tag pairwise correlation are fully exploited to smooth the decomposition results by using the dual lapalcian graph regularization terms. For optimization, an improved alternative iteration strategy is designed to solve the resulting objective function. Extensive experiments on the tasks of tag refinement demonstrate the superior performance of the proposed algorithms over several representative methods, especially when the manual tag data is highly noisy and sparse. © 2020, Springer Nature Singapore Pte Ltd.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

A Progressive background updating based coding scheme for surveillance videos 34

A Progressive background updating based coding scheme for su...

引用

34th IEEE International conference on visual communications and image processing, VCIP 2019

作者： Li, Meng Shi, Yunhui Ding, Wenpeng Liu, Xiaojie Liu, Jiaying Yin, Baocai Beijing University of Technology Beijing Key Laboratory of Multimedia and Intelligent Software Technology Faculty of Information Technology Beijing100124 China Baidu Inc China Henan Institute of Technology School of Computer Science and Technology Xinxiang China Peking University China Dalian University of Technology Faculty of Electronic Information and Electrical Engineering Dalian China

ISBN: (纸本)9781728137230

Background based coding is an effective scheme to improve the coding efficiency of surveillance videos. However, it takes a long time to generate a high quality background picture (BG-picture). And the encoding of the high quality BG-picture will increase the bitrate abruptly. To solve these problems, a progressive background updating based coding scheme is proposed in this paper. In the proposed scheme, the BG-picture is updated block by block. To improve the overall coding efficiency, an importance map is designed to select the valid background blocks (B-blocks) progressively which will be encoded with high quality. It is worth noting that only the valid B-blocks is encoded instead of the entire BG-picture. Compared with the reference software of Versatile Video Coding (VVC), the proposed scheme achieves about 23.3 percent bit-rate saving on average. © 2019 IEEE.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Disparity compensation of light fields for improved efficiency in 4D transform-based encoders

Disparity compensation of light fields for improved efficien...

引用

IEEE visual communications and image processing (VCIP)

作者： João M. Santos Lucas A. Thomaz Pedro A. A. Assuncao Luis A. da Silva Cruz Luis M. N. Tavora Sergio M. M. Faria Instituto de Telecomunicações Portugal University of Coimbra Coimbra Portugal ESTG Polytechnic of Leiria Leiria Portugal

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

Efficient light field encoders take advantage of the inherent 4D data structures to achieve high compression performance. This is accomplished by exploiting the redundancy of co-located pixels in different sub-aperture images (SAIs) through prediction and/or transform schemes to find a m ore compact representation of the signal. However, in image regions with higher disparity between SAIs, such scheme's performance tends to decrease, thus reducing the compression efficiency. This paper introduces a reversible pre-processing algorithm for disparity compensation that operates on the SAI domain of light field data. The proposed method contributes to improve the transform efficiency of the encoder, since the disparity-compensated data presents higher correlation between co-located image blocks. The experimental results show significant improvements in the compression performance of 4D light fields, achieving Bjontegaard delta rate gains of about 44% on average for MuLE codec using the 4D discrete cosine transform, when encoding High Density Camera Arrays (HDCA) light field images.

关键词： image coding Cameras Transform coding Codecs Redundancy Prediction algorithms Encoding

来源：评论

学校读者我要写书评

暂无评论

Random-access-aware Light Field Video Coding using Tree Pruning Method

Random-access-aware Light Field Video Coding using Tree Prun...

引用

IEEE visual communications and image processing (VCIP)

作者： Thuc Nguyen Huu Vinh Van Duong Byeungwoo Jeon Sungkyunkwan University South Korea

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

The increasing prevalence of VR/AR as well as the expected availability of Light Field (LF) display soon call for more practical methods to transmit LF image/video for services. In that aspect, the LF video coding should not only consider the compression efficiency but also the view random-access capability (especially in the multi-view-based system). The multi-view coding system heavily exploits view dependencies coming from both inter-view and temporal correlation. While such a system greatly improves the compression efficiency, its view random-access capability can be much reduced due to so called "chain of dependencies." In this paper, we first model the chain of dependencies by a tree, then a cost function is used to assign an importance value to each tree node. By travelling from top to bottom, a node of lesser importance is cut-off, forming a pruned tree to achieve reduction of random-access complexity. Our tree pruning method has shown to reduce about 40% of random-access complexity at the cost of minor compression loss compared to the state-of-the-art methods. Furthermore, it is expected that our method is very lightweight in its realization and also effective on a practical LF video coding system.

关键词： Complexity theory Encoding Decoding Video coding Light fields image coding Correlation

来源：评论

学校读者我要写书评

暂无评论

Orthogonal Coded Multi-view Structured Light for Inter-view Interference Elimination

Orthogonal Coded Multi-view Structured Light for Inter-view ...

引用

IEEE visual communications and image processing (VCIP)

作者： Zaichao Sun Guochao Qian Zhaoyu Peng Weiju Dai Dongjun Sun Gongyuan Zhang Nongtao Zhang Jun Xu Ren Wang Chunlin Li Electronic Power Research Institute of Yunnan Electronic Power Grid Co. Ltd Kunming China

ISBN: (数字)9781728180687

ISBN: (纸本)9781728180694

Rapid 3D reconstruction of dynamic scenes is very useful in 3D object structure analysis, accident avoidance for UAV, and other visual applications. Against dynamic scenes, coded structured light methods have been proposed to obtain the depth information of an object in 3D world, and most of them are based on spatial codification. A brutal truth is that two or more cameras and projectors from different viewpoints are needed to measure the dynamic scene simultaneously for rapid 3D reconstruction. However, when two traditional patterns, especially the binaries, are mutually overlapped, interference between them arises to a new challenge to 3D reconstruction. Traditional patterns can hardly be separated from each other, which surely influence the quality of the 3D reconstruction. To eliminate the interference problem, we propose a scheme of orthogonal coded multi-view structured light systems, which can obtain accurate of depth maps for a scene. Besides, we also test the stability of the orthogonal patterns by establishing three different scenes and making a comparisons to traditional patterns. New state-of-the-art results can be obtained by our scheme in the experiments.

关键词： Interference Cameras Three-dimensional displays Power system dynamics Sun image coding Decoding

来源：评论

学校读者我要写书评

暂无评论

Making Large Ensemble of Convolutional Neural Networks via Bootstrap Re-sampling 34

Making Large Ensemble of Convolutional Neural Networks via B...

引用

34th IEEE International conference on visual communications and image processing, VCIP 2019

作者： Li, Jiawei Xiang, Xingchun Dai, Tao Xia, Shu-Tao Tsinghua University Department of Computer Science and Technology Beijing China PCL Research Center of Networks and Communications Peng Cheng Laboratory Shenzhen China

ISBN: (纸本)9781728137230

The ensemble of Convolutional Neural Networks (CNNs) is known to be more accurate and robust than the component CNNs models. Along with the development of a fast training method, current research has managed to make an effective ensemble of several CNNs models and require no additional training cost. However, when the ensemble size of CNNs is further increased, it is hard to observe a corresponding performance enhancement. According to the generalization capability analysis of CNNs, this phenomenon can be explained by the oversaturation of model capacity and the close correlation among the component CNNs, especially when the CNNs are trained within the same dataset. To address this problem, we propose to train CNNs on re-sampled bootstrap datasets. Extensive experiments demonstrate the bootstrap re-sampling is effective for a large ensemble size (up to 80). Besides, benefiting from the usage of the bootstrap re-sampling technique, we can also have an unbiased estimate of the standard deviation of the ensemble output. © 2019 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

DCM: A Dense-Attention Context Module For Semantic Segmentation

DCM: A Dense-Attention Context Module For Semantic Segmentat...

引用

IEEE International conference on image processing

作者： Shenghua Li Quan Zhou Jia Liu Jie Wang Yawen Fan Xiaofu Wu Longin Jan Latecki National Engineering Research Center of Communications and Networking Nanjing University of Posts & Telecommunications P.R. China Department of Computer and Information Sciences Temple University Philadelphia USA

ISBN: (数字)9781728163956

ISBN: (纸本)9781728163963

For image semantic segmentation, a fully convolutional network is usually employed as the encoder to abstract visual features of the input image. A meticulously designed decoder is used to decoding the final feature map of the backbone. The output resolution of backbones which are designed for image classification task is too low to match segmentation task. Most existing methods for obtaining the final high-resolution feature map can not fully utilize the information of different layers of the backbone. To adequately extract the information of a single layer, the multi-scale context information of different layers, and the global information of backbone, we present a new attention-augmented module named Dense-attention Context Module (DCM), which is used to connect the common backbones and the other decoding heads. The experiments show the promising results of our method on Cityscapes dataset.

关键词： Convolution Feature extraction Semantics Data mining image segmentation Kernel Decoding

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 << < 127 128 129 130 131 132 133 134 135 136 > >>

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：