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

4,875 篇 会议
92 篇 期刊文献
21 册 图书

馆藏范围

4,988 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

2,832 篇 工学
- 1,759 篇 计算机科学与技术...
- 1,192 篇 信息与通信工程
- 931 篇 软件工程
- 878 篇 电气工程
- 272 篇 光学工程
- 138 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
1,054 篇 理学
- 755 篇 物理学
- 297 篇 数学
- 138 篇 生物学
- 82 篇 统计学（可授理学、...
- 53 篇 系统科学
- 50 篇 化学
251 篇 管理学
- 160 篇 管理科学与工程(可...
- 98 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
13 篇 农学
10 篇 文学
8 篇 经济学
6 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
307 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
128 篇 image color anal...
127 篇 image analysis
123 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

4,900 篇 英文
64 篇 土耳其文
28 篇 中文
10 篇 其他

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

共 4988 条记录，以下是91-100 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：

image Inpainting with Frequency Domain Wavelet Convolution

Image Inpainting with Frequency Domain Wavelet Convolution

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Huang, Jain-Kai Liu, Tsung-Jung Liu, Kuan-Hsien Natl Chung Hsing Univ Dept Comp Sci & Engn Taichung Taiwan Natl Chung Hsing Univ Dept Elect Engn Taichung Taiwan Natl Chung Hsing Univ Grad Inst Commun Engn Taichung Taiwan Natl Taichung Univ Sci & Technol Dept Comp Sci & Informat Engn Taichung Taiwan

ISBN: (纸本)9781665475921

This paper used Time-Frequency Analysis (TFA) techniques for signal processing on tasks of computer vision. Our main idea is as follows: To build a simple network architecture without two or more convolutional neural networks (CNNs), analyze hidden features by Discrete Wavelet Transform (DWT), and send them into filters as weights by convolutions, transformers or other methods. And we do not need to build the network with 2 or more stages to accomplish this idea. Actually, we try to directly use TFA skills on CNN to build one-stage network. Networks which build by this way not only keep their outstanding performance, but also cost lower computing resources. In this paper, we mainly use DWT on CNN to solve image inpainting problems. And the results show that our model can work stably in frequency domain to realize free-form image inpainting.

关键词： image Inpainting Signal processing Computer Vision Deep Learning Neural Network

来源：评论

学校读者我要写书评

暂无评论

Dual-stream Self-attention Network for image Captioning

Dual-stream Self-attention Network for Image Captioning

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Wan, Boyang Jiang, Wenhui Fang, Yuming Wen, Wenying Liu, Hantao Jiangxi Univ Finance & Econ Nanchang Jiangxi Peoples R China Cardiff Univ Cardiff Wales

ISBN: (纸本)9781665475921

Self-attention based encoder-decoder models achieve dominant performance in image captioning. However, most existing image captioning models (ICMs) only focus on modeling the relation between spatial tokens, while channel-wise attention is neglected for getting visual representation. Considering that different channels of visual representation usually denote different visual objects, it may lead to poor performance in terms of object and attribute words in the captioning sentences generated by the ICMs. In this paper, we propose a novel dual-stream self-attention module (DSM) to alleviate the above issue. Specifically, we propose a parallel self-attention based module that simultaneously encodes visual information from the spatial and channel dimensions. Besides, to obtain channel-wise visual features effectively and efficiently, we introduce a group self-attention block with linear computational complexity. To validate the effectiveness of our model, we conduct extensive experiments on the standard IC benchmarks including MSCOCO and Flickr30k. Without bells and whistles, the proposed model performs new SOTAs containing 135.4 CIDEr score on MSCOCO and 70.8 CIDEr score on Flickr30k.

关键词： image Captioning Self-Attention Spatial Attention Channel Attention

来源：评论

学校读者我要写书评

暂无评论

Tire Pattern image Classification using Variational Auto-Encoder with Contrastive Learning

Tire Pattern Image Classification using Variational Auto-Enc...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Yang, Jianning Xue, Jiahao Feng, Xiaodong Song, Chaoqi Hao, Yu Xian Univ Posts & Telecommunicat Sch Communicat & Informat Engn Xian Peoples R China

ISBN: (纸本)9781665475921

Tire pattern image classification is an important computer vision problem in pubic security, which can guide policeman to detect criminal cases. It remains challenge due to the small diversity within different classes. Generally, a tire pattern image classification system may require two characteristics: high accuracy and low computation. In this paper, we first assume that capturing rich feature representation will benefits tire classification and learning through a lightweight network will improve computing efficiency. We then propose a simple yet efficient two-stage training mechanism: 1) We learn a feature extractor using a Variational Auto-Encoder framework constrained by contrastive learning, projecting images to latent space owing rich feature representation. 2) We train a single-layer linear classification network depend on the features extracted by the previous trained encoder. The Top-1 and Top-5 accuracy on tire pattern dataset is 89.8% and 96.6% respectively, validating the effectiveness of our strategy.

关键词： Tire Pattern image classification Variational Auto-Encoder Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

An Efficient Method for Real-Time image Exposure Correction

An Efficient Method for Real-Time Image Exposure Correction

引用

2023 IEEE International conference on visual communications and image processing, VCIP 2023

作者： Yang, Jie Zhang, Yuantong Yang, Daiqin Chen, Zhenzhong Wuhan University School of Remote Sensing and Information Engineering Wuhan China

ISBN: (纸本)9798350359855

Exposure errors in images, including both underexposure and overexposure, significantly diminish images' contrast and visual appeal. Existing deep learning-based exposure correction methods either require large networks or longer processing time for inference and are thus not applicable for embedded devices and real-time applications. To address these issues, a lightweight network is proposed in this paper to correct exposure errors with limited memory occupation and inference steps. It adopts the Laplacian pyramid to incrementally recover the color and details of the image through a layer-by-layer procedure. A structural re-parameterization structure is designed to both reduce model size for inference speed up and improve performance with a multi-branch learning structure. Extensive experiments demonstrate that our method achieves a better performance-efficiency trade-off than other exposure correction methods. © 2023 IEEE.

关键词： image enhancement

来源：评论

学校读者我要写书评

暂无评论

Learning from the NN-based Compressed Domain with Deep Feature Reconstruction Loss

Learning from the NN-based Compressed Domain with Deep Featu...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Chen, Liuhong Sun, Heming Zeng, Xiaoyang Fan, Yibo Fudan Univ Shanghai Peoples R China Waseda Univ Tokyo Japan JST PRESTO Saitama Japan

ISBN: (纸本)9781665475921

To speedup the image classification process which conventionally takes the reconstructed images as input, compressed domain methods choose to use the compressed images without decompression as input. Correspondingly, there will be a certain decline about the accuracy. Our goal in this paper is to raise the accuracy of compressed domain classification method using compressed images output by the NN-based image compression networks. Firstly, we design a hybrid objective loss function which contains the reconstruction loss of deep feature map. Secondly, one image reconstruction layer is integrated into the image classification network for up-sampling the compressed representation. These methods greatly help increase the compressed domain image classification accuracy and need no extra computational complexity. Experimental results on the benchmark imageNet prove that our design outperforms the latest work ResNet-41 with a large accuracy gain, about 4.49% on the top-1 classification accuracy. Besides, the accuracy lagging behinds the method using reconstructed images is also reduced to 0.47%. Moreover, our designed classification network has the lowest computational complexity and model complexity.

关键词： Compressed domain image analysis image classification LIC (Learned image Compression) feature reconstruction

来源：评论

学校读者我要写书评

暂无评论

Rate Controllable Learned image Compression Based on RFL Model

Rate Controllable Learned Image Compression Based on RFL Mod...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Zhang, Saiping Wang, Luge Mao, Xionghui Yang, Fuzheng Wan, Shuai Xidian Univ Sch Telecommun Engn Xian Peoples R China Northwestern Polytech Univ Sch Elect & Informat Xian Peoples R China

ISBN: (纸本)9781665475921

In this paper, we propose a rate controllable image compression framework, Rate Controllable Variational Autoencoder (RC-VAE), based on the Rate-Feature-Level (RFL) model established through our exploration on the correlation among target rates, image features and quantization levels. Considering that, when meeting the same target rate, different images should be quantized in different levels, we focus on jointly utilizing the target rate and the extracted features of the image to predict the corresponding quantization level and propose the RFL model. Combining the proposed RFL model with a Hyperprior Continuously Variable Rate (HCVR) image compression network, we further propose the RC-VAE. By controlling information loss in quantization process, the RC-VAE can work at the target rate. Experimental results have demonstrated that one single RC-VAE model can adapt to multiple target rates with higher rate control accuracy and better R-D performance compared with the stateof-the-art rate controllable image compression networks.

关键词： Deep image compression rate control variational autoencoder rate-distortion

来源：评论

学校读者我要写书评

暂无评论

Improving Latent Quantization of Learned image Compression with Gradient Scaling

Improving Latent Quantization of Learned Image Compression w...

引用

IEEE International conference on visual communications and image processing (VCIP)

作者： Sun, Heming Yu, Lu Katto, Jiro Waseda Univ Waseda Res Inst Sci & Engn Tokyo Japan Zhejiang Univ Inst Informat & Commun Engn Hangzhou Peoples R China JST PRESTO 4-1-8 Honcho Kawaguchi Saitama Japan Waseda Univ Dept Comp Sci & Commun Engn Tokyo Japan

ISBN: (纸本)9781665475921

Learned image compression (LIC) has shown its superior compression ability. Quantization is an inevitable stage to generate quantized latent for the entropy coding. To solve the non-differentiable problem of quantization in the training phase, many differentiable approximated quantization methods have been proposed. However, the derivative of quantized latent to non-quantized latent are set as one in most of the previous methods. As a result, the quantization error between non-quantized and quantized latent is not taken into consideration in the gradient descent. To address this issue, we exploit the gradient scaling method to scale the gradient of non-quantized latent in the back-propagation. The experimental results show that we can outperform the recent LIC quantization methods.

关键词： Learned image compression Quantization Gradient scaling

来源：评论

学校读者我要写书评

暂无评论

Pyramidal Cross-Modal Transformer with Sustained visual Guidance for Multi-Label image Classification 24

Pyramidal Cross-Modal Transformer with Sustained Visual Guid...

引用

4th Annual International conference on Multimedia Retrieval (ICMR)

作者： Li, Zhuohua Wang, Ruyun Zhu, Fuqing Han, Jizhong Hu, Songlin Chinese Acad Sci Inst Informat Engn Beijing Peoples R China Univ Chinese Acad Sci Sch Cyber Secur Beijing Peoples R China

ISBN: (纸本)9798400706028

Multi-label image classification poses a formidable challenge due to the presence of multiple objects in each image, rendering it notably complex to decipher the visual content comprehensively. Discriminating between multiple objects necessitates the establishment of robust visual label dependencies. Previous methods attempt to formulate cross-modal interaction or one-shot co-occurrence relationship guidance. However, it not only exhibits limitations when handling occluded or blurry objects but also fails to fully leverage the diverse hierarchical properties for sustainably guiding the learning process of label dependencies. To sustainably establish hierarchical visual label dependencies, this paper introduces a Pyramidal Cross-modal Transformer framework for MLIC tasks. Specifically, the pyramidal visual guidance layer parses the visual features into a multi-resolution pyramid structure, allowing the updated visual-related information to provide sustained guidance for label semantics. This surpasses the conventional pre-processing of co-occurrence relationships. Besides, the hybrid modal interaction layer is proposed to effectively mitigate the semantic disparities between visual and label information with modal-blended indiscriminate attention, replacing vanilla self-attention. Several combination blocks consisting of these two layers are integrated and embedded within the encoder-decoder structure to facilitate the exploration of meticulous visual label dependencies. Extensive experiments on two widely-used benchmarks, including MS-COCO and PASCAL VOC 2007, consistently demonstrate that PCMT could provide state-of-the-art results.

关键词： Pyramidal Transformer Sustained visual Guidance Multi-label image classification

来源：评论

学校读者我要写书评

暂无评论

image Data Hiding in Neural Compressed Latent Representations

Image Data Hiding in Neural Compressed Latent Representation...

引用

2023 IEEE International conference on visual communications and image processing, VCIP 2023

作者： Huang, Chen-Hsiu Wu, Ja-Ling National Taiwan University Dept. of Computer Science and Information Engineering Taipei Taiwan

ISBN: (纸本)9798350359855

We propose an end-To-end learned image data hiding framework that embeds and extracts secrets in the latent representations of a generic neural compressor. By leveraging a perceptual loss function in conjunction with our proposed message encoder and decoder, our approach simultaneously achieves high image quality and high bit accuracy. Compared to existing techniques, our framework offers superior image secrecy and competitive watermarking robustness in the compressed domain while accelerating the embedding speed by over 50 times. These results demonstrate the potential of combining data hiding techniques and neural compression and offer new insights into developing neural compression techniques and their applications. © 2023 IEEE.

关键词： Steganography

来源：评论

学校读者我要写书评

暂无评论

MTE: Learned image Compression with a Merge-Then-Estimate Entropy Model

MTE: Learned Image Compression with a Merge-Then-Estimate En...

引用

2023 IEEE International conference on visual communications and image processing, VCIP 2023

作者： Shizhan, Liu Shanghai Jiao Tong University China

ISBN: (纸本)9798350359855

Recent advancements in learning-based image compression methods have shown promising results. The success of these methods heavily relies on the entropy model, which predicts the probability distribution of the quantized latent representation of the image based on available knowledge. However, most existing entropy models follow an estimate-Then-merge pipeline, leading to two potential issues: limited flexibility in modeling spatial context and inadequate fusion of different prior sources. In this paper, we propose a novel approach called the MergeThen-Estimate (MTE) entropy model. Our method addresses these issues by first uniformly merging available priors into a 'prior token' using a Prior Embedding Module for each spatial location in the quantized latent representation. Next, we introduce a Content-Aware Context Model to dynamically capture the dependencies of the currently coding representation on its neighboring available priors. Experiments on the Kodak dataset demonstrate the superiority of our proposed MTE entropy model. © 2023 IEEE.

关键词： image compression

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499页 << < 6 7 8 9 10 11 12 13 14 15 > >>

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：