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
89 篇 期刊文献
21 册 图书

馆藏范围

4,994 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,833 篇 工学
- 1,762 篇 计算机科学与技术...
- 1,191 篇 信息与通信工程
- 934 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
- 44 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
1,208 篇 医学
- 1,187 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
1,055 篇 理学
- 754 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
550 篇 image processing
355 篇 visual communica...
329 篇 visualization
308 篇 feature extracti...
300 篇 image segmentati...
187 篇 image reconstruc...
181 篇 cameras
180 篇 image compressio...
177 篇 humans
162 篇 video coding
161 篇 signal processin...
134 篇 image quality
132 篇 image color anal...
131 篇 image enhancemen...
130 篇 image analysis
125 篇 image edge detec...
119 篇 image retrieval
114 篇 training
108 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

4,789 篇 英文
127 篇 其他
64 篇 土耳其文
45 篇 中文

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

共 4994 条记录，以下是1411-1420 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：

Hybrid Regularization with Elastic Net and Linear Discriminant Analysis for Zero-Shot image Recognition

Hybrid Regularization with Elastic Net and Linear Discrimina...

引用

IEEE visual communications and image processing conference

作者： Zhen Qin Yan Li School of Information and Communication Engineering Beijing University of Posts and Telecommunications Beijing China School of Information and Electronics Beijing Institute of Technology Beijing China

Zero-shot learning (ZSL) is the process of recognizing unseen samples from their related classes. Generally, ZSL is realized with the help of some pre-defined semantic information via projecting high dimensional visual features of data samples and class-related semantic vectors into a common embedding space. Although classification can be simply decided through the nearest-neighbor strategy, it usually suffers from problems of domain shift and hubness. In order to address these challenges, majority of researches have introduced regularization with some existing norms, such as lasso or ridge, to constrain the learned embedding. However, the sparse estimation of lasso may cause underfitting of training data, while ridge may introduce bias in the embedding space. In order to resolve these problems, this paper proposes a novel hybrid regularization approach by leveraging elastic net and linear discriminant analysis, and formulates a unified objective function that can be solved efficiently via a synchronous optimization strategy. The proposed method is evaluated on several benchmark image datasets for the task of generalized ZSL. The obtained results demonstrate the superiority of the proposed method over simple regularized methods as well as several previous models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

RSNet: A Compact Relative Squeezing Net for image Recognition

RSNet: A Compact Relative Squeezing Net for Image Recognitio...

引用

IEEE visual communications and image processing conference

作者： Qi Zhao Nauman Raoof Shuchang Lyu Boxue Zhang Wenquan Feng School of Electronic Information Engineering Beihang University Beijing China Autonomous Driving Group Sensetime Beijing China

Convolutional neural networks (CNN) are showing powerful performance on image recognition tasks. However, when CNN is applied to mobile devices, with limited computing and memory resource, it requires more compact design to maintain a relatively high performance. In this paper, we propose Relative Squeezing Net (RSNet) that provides technical insight into CNN structure for designing a compact model. In an endeavor to improve CondenseNet, we introduce Relative-Squeezing bottleneck where output is weighted percentage of input channels. The design of our bottleneck can transmit diverse and most useful features at all stages. We also employ multiple compression layers to constrain the output channels of feature maps which can eliminate superfluous feature maps and transmit powerful representations to next layers. We evaluate our model on two benchmark datasets;CIFAR and imageNet. Experimental results show that RSNet achieves state-of-the-art results with less parameters and FLOPs and is more efficient than compact architectures such as CondenseNet, MobileNet and ShuffleNet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

LF-TSP: Traveling salesman problem for HEVC-based light-field coding

LF-TSP: Traveling salesman problem for HEVC-based light-fiel...

引用

IEEE visual communications and image processing conference

作者： Kota Imaeda Kohei Isechi Keita Takahashi Toshiaki Fujii Yukihiro Bandoh Takehito Miyazawa Seishi Takamura Atsushi Shimizu Department of Information and Communication Engineering Nagoya University Japan NTT Media Intelligence Laboratories Nippon Telegraph and Telephone Corporation Japan

We studied a coding scheme where light field (LF) images (dense multi-view images) are regarded as a sequence of temporal video frames and encoded with video codecs such as High Efficiency Video Coding (HEVC). An important issue with this scheme is how to determine the frame order of the LF images. We propose a method to find the optimum frame order through a formulation of the traveling salesman problem (TSP). Under the assumption that video codecs are more effective with temporally smooth videos, our method, named LF-TSP, defines frame-to-frame distances for each image pairs in an LF, and attempted to find the shortest route that visits all frames. Experiments showed that our method achieved an overall better rate-distortion performance than several previous methods.

关键词： Video codecs Traveling salesman problems image coding Rate-distortion Delays Video sequences

来源：评论

学校读者我要写书评

暂无评论

Advertisement Logo Compositing via Adversarial Geometric Consistency Pursuit

Advertisement Logo Compositing via Adversarial Geometric Con...

引用

IEEE visual communications and image processing conference

作者： Xiang Li Guowei Teng Ping An Haiyan Yao Yilei Chen Shanghai Institute for Advanced Communication and Data Science School of Communication and Information Engineering Shanghai University Shanghai China

Advertisement logo compositing is aiming to embed some specified logos in a suitable position of target images with alike geometric distortion and same appearance characteristic. Unsupervised learning has gained considerable attention recently. To synthetically address the problems about geometric distortion and appearance realism, we propose a novel learnable module, the adversarial geometric consistency pursuit model (AGCP), which explicitly allows seamless image compositing. On one hand, we design an adversarial structure that generates composite images taking geometric correction and appearance harmonization into account. Our proposed adversarial learning approach is able to obtain better harmonization in the region of interest. On the other hand, a novel geometric consistency pursuit loss is designed which encourages the network to learn the warp parameters of target images while preserving the feature of the source object. Our comparative evaluation demonstrates the effectiveness of the proposed method.

关键词： Distortion Generative adversarial networks Training Data models Computer vision image color analysis Transforms

来源：评论

学校读者我要写书评

暂无评论

A Novel Pan Sharpening Method via Sparse Representation over Learned Dictionary 26

A Novel Pan Sharpening Method via Sparse Representation over...

引用

26th IEEE Signal processing and communications Applications conference (SIU)

作者： Ayas, Selen Gormus, Esra Tunc Ekinci, Murat Karadeniz Tech Univ Bilgisayar Muhendisligi Trabzon Turkey Karadeniz Tech Univ Harita Muhendisligi Trabzon Turkey

ISBN: (纸本)9781538615010

Remote sensing pan sharpening aims to enhance spatial resolution of multispectral image by injecting spatial details of a panchromatic image to multispectral image. In this study, a novel sparse representation based pan sharpening method is proposed to overcome the disadvantages of traditional methods such as color distortion and blurring effect. A data set acquired for each IKONOS and Quickbird satellites are used to evaluate the performance and robustness of the proposed algorithm. The proposed method is compared with four traditional methods using several quality measurement indices with reference image. The experimental results demonstrate that the proposed algorithm is competitive or superior to other conventional methods in terms of visual and quantitative analysis as it preserves spectral information and provides high quality spatial details in the final product image.

关键词： dictionary learning multispectral image panchromatic image pan sharpening sparse representation

来源：评论

学校读者我要写书评

暂无评论

FICAL: Focal Inter-Class Angular Loss for image Classification

FICAL: Focal Inter-Class Angular Loss for Image Classificati...

引用

IEEE visual communications and image processing conference

作者： Xinran Wei Dongliang Chang Jiyang Xie Yixiao Zheng Chen Gong Chuang Zhang Zhanyu Ma Pattern Recognition and Intelligent Systems Lab. Beijing University of Posts and Telecommunications Beijing China PCA Lab Key Lab of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education

Convolutional Neural Networks (CNNs) have been successfully applied in various image analysis tasks and gradually become one of the most powerful machine learning approaches. In order to improve the capability of the model generalization and performance in image classification, a new trend is to learn more discriminative features via CNNs. The main contribution of this paper is to increase the angles between the categories to extract discriminative features and enlarge the inter-class variance. To this end, we propose a loss function named focal inter-class angular loss (FICAL) which introduces the confusion rate-weighted cosine distance as the similarity measurement between categories. This measurement is dynamically evaluated during each iteration to adapt the model. Compared with other loss functions, experimental results demonstrate that the proposed FICAL achieved best performance among the referred loss functions on two image classification datasets.

关键词： Task analysis Training Feature extraction Computer vision Computational modeling Loss measurement Neural networks

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

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

引用

IEEE visual communications and image processing conference

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

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 over-saturation 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.

关键词： Training Correlation Predictive models Standards Cats Annealing Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Identifying and Pruning Redundant Structures for Deep Neural Networks

Identifying and Pruning Redundant Structures for Deep Neural...

引用

IEEE visual communications and image processing conference

作者： Wenyao Gan Li Song Li Chen Rong Xie Xiao Gu Institute of Image Communication and Network Engineering Shanghai Jiao Tong University

Deep convolutional neural networks have achieved considerable success in the field of computer vision. However, it is difficult to deploy state-of-the-art models on resource-constrained platforms due to their high storage, memory bandwidth, and computational costs. In this paper, we propose a structured pruning method which employs a three-step process to reduce the resource consumption of neural networks. First, we train an initial network on the training set and evaluate it on the validation set. Next, we introduce an iterative pruning and fine-tuning algorithm to identify and prune redundant structures, which results in a pruned network with a compact architecture. Finally, we train the pruned network from scratch on both the training set and validation set to obtain the final accuracy on the test set. In the experiments, our pruning method significantly reduces the model size (by 87.2% on CIFAR-10), saves inference time (53.3% on CIFAR-10), and achieves better performance as compared to recent state-of-the-art methods.

关键词： Training Shape Redundancy Network architecture Computational modeling Iterative algorithms Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Improving Action Recognition with the Graph-Neural-Network-based Interaction Reasoning

Improving Action Recognition with the Graph-Neural-Network-b...

引用

IEEE visual communications and image processing conference

作者： Wu Luo Chongyang Zhang Xiaoyun Zhang Haiyan Wu School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China Department of Image and Network Investigation Railway Police College Zhengzhou China

Recent human action recognition methods mainly model a two-stream or 3D convolution deep learning network, with which humans spatial-temporal features can be exploited and utilized effectively. However, due to the ignoring of interaction exploiting, most of these methods cannot get good enough performance. In this paper, we propose a novel action recognition framework with Graph Convolutional Network (GCN) based Interaction Reasoning: Objects and discriminative scene patches are detected using an object detector and class active mapping (CAM), respectively;and then a GCN is introduced to model the interaction among the detected objects and scene patches. Evaluation of two widely used video action benchmarks shows that the proposed work can achieve comparable performance: the accuracy up to 43.6% at EPIC Kitchen, and 47.0% at VLOG benchmark without using optical flow, respectively.

关键词： Feature extraction Detectors Cognition Mathematical model Three-dimensional displays Convolution Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

YesilcamGAN: Automatic Face Translation to Yesilcam Artists 26

YesilcamGAN: Automatic Face Translation to Yesilcam Artists

引用

26th IEEE Signal processing and communications Applications conference (SIU)

作者： Ozkan, Savas Akar, Gozde Bozdagi Ortadogu Tekn Univ Multimedia Lab Ankara Turkey

ISBN: (纸本)9781538615010

In this paper, we propose a method that can automatically translate regular human faces to Yesilcam artists. Throughout the paper, two important contributions are presented. First, since a classifier based approach is used, the proposed method automatically selects the most similar artist and makes the face translation. Second, so as to obtain the latent information about faces, a pre-trained model is utilized at the encoder part. Experiments show that visual results which are perceptually promising, Yesilcam artist-like yet preserving facial features of a person, can be synthesized.

关键词： Cycle-Generative Adversarial Networks image-to-image Translation

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 << < 138 139 140 141 142 143 144 145 146 147 > >>

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：