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

3,429 篇 会议
27 篇 期刊文献
14 册 图书

馆藏范围

3,470 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

1,946 篇 工学
- 1,271 篇 计算机科学与技术...
- 955 篇 信息与通信工程
- 686 篇 软件工程
- 520 篇 电气工程
- 190 篇 光学工程
- 108 篇 生物工程
- 79 篇 电子科学与技术（可...
- 62 篇 生物医学工程（可授...
- 60 篇 仪器科学与技术
- 60 篇 控制科学与工程
- 54 篇 机械工程
- 33 篇 化学工程与技术
- 32 篇 网络空间安全
- 23 篇 动力工程及工程热...
- 23 篇 安全科学与工程
- 13 篇 土木工程
- 13 篇 交通运输工程
959 篇 医学
- 951 篇 临床医学
- 29 篇 基础医学(可授医学...
- 26 篇 药学(可授医学、理...
774 篇 理学
- 574 篇 物理学
- 192 篇 数学
- 114 篇 生物学
- 53 篇 统计学（可授理学、...
- 33 篇 化学
- 29 篇 系统科学
132 篇 管理学
- 71 篇 管理科学与工程(可...
- 69 篇 图书情报与档案管...
- 17 篇 工商管理
30 篇 法学
- 28 篇 社会学
11 篇 军事学
9 篇 文学
5 篇 经济学
5 篇 农学
4 篇 教育学

主题

418 篇 image coding
349 篇 visual communica...
308 篇 image processing
293 篇 visualization
222 篇 feature extracti...
177 篇 image segmentati...
147 篇 image compressio...
139 篇 training
136 篇 video coding
130 篇 image reconstruc...
117 篇 image color anal...
107 篇 cameras
103 篇 image quality
100 篇 deep learning
95 篇 image enhancemen...
88 篇 image edge detec...
85 篇 humans
83 篇 three-dimensiona...
77 篇 motion estimatio...
76 篇 decoding

机构

36 篇 shanghai jiao to...
29 篇 institute of ima...
24 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...
11 篇 university of el...
11 篇 cas key laborato...
11 篇 tsinghua univ de...
10 篇 univ sci & techn...
10 篇 peking univ inst...
10 篇 institute of ima...
9 篇 zhejiang univers...
9 篇 tsinghua univ de...
9 篇 school of electr...
9 篇 xidian univ sch ...
9 篇 shanghai jiao to...
8 篇 school of remote...

作者

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

语言

3,406 篇 英文
49 篇 土耳其文
22 篇 中文
7 篇 其他

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

共 3470 条记录，以下是451-460 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：

Variable-rate Learned image Compression with Adaptive Quantization Step Size

Variable-rate Learned Image Compression with Adaptive Quanti...

引用

IEEE visual communications and image processing (VCIP)

作者： Feihong Mei Li Li Dong Liu Deep Space Exploration Laboratory USTC Hefei China

Nowadays, learned image compression has outperformed traditional coding methods like VVC. However, learned image compression methods are often optimized for specific rates and lack support for variable rate compression. Though some efforts have been made to address variable rate compression, striking the right balance between performance and complexity remains a challenge. To address this, we propose the Adaptive Quantize Step Size (AQS) technique, allowing continuous variable rate within a single model. Unlike methods that learn to scale the latent representation, AQS enables learning of different quantization step sizes for different rates, preserving the latent representation’s distribution while only affecting the quantization step size, which is beneficial for the entropy model. As a result, our method achieves superior performance compared to existing methods while maintaining similar complexity. It delivers comparable results across a wide range of rates using a single model with minimal additional parameters.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Low-complexity Transform Network Architecture for JPEG AI image Codec

Low-complexity Transform Network Architecture for JPEG AI Im...

引用

IEEE visual communications and image processing (VCIP)

作者： Xiang Pan Ding Ding Liqiang Wang Xiaozhong Xu Shan Liu Tencent Media Lab Shenzhen China Tencent Media Lab Palo Alto CA USA

Learning-based image coding schemes, exemplified by JPEG AI, have shown potential by greatly exceeding the conventional image compression standards in rate-distortion (RD) performance. However, their widespread applications are hindered by high decoding complexity, particularly from the upsampling and attention modules. Existing works sought to reduce this complexity, but their solutions are not fully effective, leaving considerable complexity unaddressed. In this paper, we present a simplified transform network architecture that employs an optimized attention module, a streamlined upsampling module, and a pared-down activation function to tackle this issue. Simulation results show that the simplified decoder sees its complexity (measured by kMACs/pixel) reduced by 80% (from 833 to 172), while the gain over Versatile Video Coding (VVC) increases slightly (from 27.3% to 27.5%). Partial methods in this paper have been integrated into the JPEG AI Verification Model (VM) software.

关键词：

来源：评论

学校读者我要写书评

暂无评论

No-Reference Point Cloud Quality Assessment with Adaptive Keyframe Selection

No-Reference Point Cloud Quality Assessment with Adaptive Ke...

引用

IEEE visual communications and image processing (VCIP)

作者： Haomiao Wang Xiaochuan Wang Xianpeng Yuan Xianming Chen Haisheng Li School of Computer and Artificial Intelligence Beijing Technology and Business University China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

In recent years, projection-based no-reference point cloud quality metrics have shown remarkable performance on public datasets. These metrics involve projecting the point cloud onto a 2D space from multiple viewpoints and applying traditional image quality metrics to the resulting projected images. However, these existing methods suffer from a measurable projection strategy, which would induce information loss or redundancy leading to training bias and reduced generalizability. To overcome these limitations, we propose AKSNet, a novel no-reference point cloud quality metric that utilizes an adaptive keyframe selection strategy. In particular, we treat the process of point cloud projection as video sequences captured from successive viewpoints and design a keyframe selection module to pick the most representative frames. Based on the selected frames, we can subsequently predict the quality score of the point cloud. Experimental results demonstrate that our method achieves competitive performance in comparison with state-of-the-art methods. While the proposed adaptive keyframe selecting strategy can effectively promote the generalization performance.

关键词： Point cloud compression Training image quality visual communication image processing Video sequences Redundancy Particle measurements Loss measurement Quality assessment

来源：评论

学校读者我要写书评

暂无评论

Frequency-Aware Hierarchical image Compression for Humans and Machines

Frequency-Aware Hierarchical Image Compression for Humans an...

引用

IEEE visual communications and image processing (VCIP)

作者： Yue Luo Zixiang Zhang Jinhao Kuang Li Yu Huazhong University of Science and Technology Wuhan China Research Institute of Huazhong University of Science and Technology in Shenzhen Shenzhen China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

To achieve efficient compression for both human vision and machine perception, scalable coding methods have been proposed in recent years. However, existing methods do not fully eliminate the redundancy between features corresponding to different tasks, resulting in suboptimal coding performance. In this paper, we propose a frequency-aware hierarchical image compression framework designed for humans and machines. Specifically, we investigate task relationships from a frequency perspective, utilizing only HF information for machine vision tasks and leveraging both HF and LF features for image reconstruction. Besides, the residual block embedded octave convolution module is designed to enhance the information interaction between HF features and LF features. Additionally, a dual-frequency channel-wise entropy model is applied to reasonably exploit the correlation between different tasks, thereby improving multi-task performance. The experiments show that the proposed method offers -69.3%∼-75.3% coding gains on machine vision tasks compared to the relevant benchmarks, and -19.1% gains over state-of-the-art scalable image codec in terms of image reconstruction quality.

关键词： image coding Correlation Codecs Convolution visual communication Machine vision Redundancy Multitasking Entropy image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Towards Efficient Learned image Coding for Machines via Saliency-Driven Rate Allocation

Towards Efficient Learned Image Coding for Machines via Sali...

引用

IEEE visual communications and image processing (VCIP)

作者： Zixiang Zhang Li Yu Qiang Zhang Junjun Mei Tao Guan Huazhong University of Science and Technology Wuhan China ZTE Corporation Nanjing China

Recently, efficient image coding for machines method is widely required under machine vision task-oriented coding scenarios. To achieve higher task accuracy under a certain bitrate constraint, existing solutions take advantage of cutting-edge learned image compression methods and cascade the compression and specific task model straightly to carry out the joint optimization, which lacks adaptability and flexibility to handling machine vision saliency and non-saliency regions, thus obtaining inferior performance. In this paper, we propose a learned image compression model with a saliency-driven rate allocation strategy for machine vision. Specifically, an auxiliary network is introduced to provide reference latent first which contains full image reconstruction required information. And then, a machine vision saliency detector is applied to generate the adjustment factor to achieve rate allocation in the latent domain. In addition, a spatial dynamic convolution module is designed to facilitate the compressor adaptively processing the different spatial areas. Finally, the multi-distortion constraint is utilized to achieve an end-to-end optimization. Experimental results show that the proposed method achieves -77.48% coding gains over VVC using Mask R-CNN as the back-end task network on the Cityscapes dataset. Moreover, the reconstructed image maintains considerable visual fidelity, making it possible both for human and machine consumption.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Feature Detectors and Descriptors with Close-Range Solar Panel images

Performance Evaluation of Feature Detectors and Descriptors ...

引用

IEEE visual communications and image processing (VCIP)

作者： Eman Ansar Sara Sewil Fathimath Zuha Maksood Eduardo Feo-Flushing School of Computer Science Carnegie Mellon University Carnegie Mellon University in Qatar

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

Recent advancements in photovoltaic (PV) systems for power generation necessitate continuous inspection, fault detection, and maintenance to maximize energy production. While prior research has primarily focused on image processing and algorithms using long-range shots of PV systems, this study evaluates existing feature detectors and descriptors for processing close-range thermal images of solar panels. Utilizing a dataset captured with the FLIR Duo Pro R camera, which includes variations such as camera angle rotation, motion blur, and different times of day, we assessed the performance of various feature detectors (SIFT, FAST, AKAZE, BRISK, ORB) and descriptors (SIFT, FREAK, ORB, SURF, BRISK) with FAST as a keypoint detector. Additionally, the study examines the impact of different color maps (JET, RAINBOW, HOT, COOL, BONE, GRAY) on these metrics. Our results indicate that AKAZE is the most effective detector, while SURF is the most robust descriptor, particularly when used with multichromatic, high-contrast color maps like JET and RAINBOW. These findings provide a basis for improving various applications, such as image stitching and object detection, and have potential future work in PV fault detection.

关键词： Performance evaluation image color analysis visual communication Fault detection Detectors Production Object detection Feature extraction Cameras Solar panels

来源：评论

学校读者我要写书评

暂无评论

A Secure Network Coding based image communications in Two-Hop Wireless Relay Networks

A Secure Network Coding based Image Communications in Two-Ho...

引用

IEEE visual communications and image processing (VCIP)

作者： Quoc-Tuan Vien Tuan T. Nguyen Faculty of Science and Technology Middlesex University UK School of Computing and Mathematical Sciences University of Greenwich UK

This paper investigates the image communications in two-hop wireless relay networks (TH-WRNs) where a source node sends images to a destination node with the assistance of a relay node via two hops, i.e. source-to-relay and relay-to-destination links. Due to the broadcast nature of wireless media, there exists an eavesdropper who tries to overhear and recover the images. Aiming to enhance the security and also to save transmission bandwidth of the image communications, we propose a secure relaying transmission (SRT) protocol by exploiting both random linear network coding (RLNC) and image super-resolution (ISR) techniques. In the proposed protocol, the original high-resolution (HR) images are downscaled at the source node and the RLNC is employed at both the source and relay nodes to conceal the original images from the eavesdropper. The RLNC decoding and ISR are adopted at the destination node to decode and recover the HR images, while the eavesdropper cannot decode the images due to the unawareness of the coefficient matrices and the reference images in the RLNC. It is shown that the proposed SRT protocol achieves a significantly higher performance at the destination than at the eavesdropper. Furthermore, with high-quality relaying hops, the SRT protocol outperforms the secure direct transmission (SDT) protocol with only a direct link between the source and the destination nodes. Finally, simulation results are provided to verify the findings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Reversible Data Hiding Scheme in Compressible Encrypted Grayscale-Based images

A Novel Reversible Data Hiding Scheme in Compressible Encryp...

引用

IEEE visual communications and image processing (VCIP)

作者： Ruifeng Li Masaaki Fujiyoshi Department of Computer Science Tokyo Metropolitan University Tokyo Japan

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

In recent years, the proliferation of cloud services, particularly social media, has spurred research on encryption-then-compression (EtC) systems for secure and efficient multi-media transmission. EtC systems compress encrypted images or provide compression-resilient encryption. To address the need for embedding authentication, copyright data, or tags to images in cloud services, this paper introduces a novel data hiding scheme for the EtC system. The EtC system which this paper focuses on converts an RGB color image to the YCbCr color image, followed by horizontally joining three color component images to form a grayscale image, and encrypts this grayscale image in non-overlapping blocks using block permutation, block rotation/inversion, and brightness inversion. The proposed data hiding scheme conceals data in unencrypted images and can extract it from encrypted images by manipulating diagonal pixel values within blocks. Sorting keys, generated from intra-block pixel value characteristics, ensure correct data sequence recovery. Moreover, the proposed scheme is reversible, allowing for the removal of embedded information, and uses different pixels within the same block for dual embeddings to increase payload. Compared to conventional schemes for the EtC system, the proposed scheme leverages all three visual encryption processes and considers the RGB-to-YCbCr conversion. Performance evaluation results confirm the effectiveness of the proposed scheme.

关键词： Performance evaluation visualization image coding image color analysis visual communication Social networking (online) Color Gray-scale Encryption Sorting

来源：评论

学校读者我要写书评

暂无评论

MAESR360: Masked autoencoder-based 360-degree video streaming via multi-scale feature fusion

MAESR360: Masked autoencoder-based 360-degree video streamin...

引用

IEEE visual communications and image processing (VCIP)

作者： Li Yu Zhiyu Pang Moncef Gabbouj School of Computer Science Nanjing University of Information Science & Technology Nanjing China Department of Computing Sciences Tampere University Tampere Finland

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

360-degree video streaming is becoming increasingly popular for its immersive experience. Traditional adaptive tile-based streaming methods allocate the bitrates according to view-port prediction, which effectively reduces required transmission bandwidth, but it will cause serious quality degradation when the viewport prediction is inaccurate. Thus, some researchers propose visual reconstruction and enhancement-based 360-degree video streaming framework, which can reconstructs the whole frame at very low bitrates. However, existing frameworks are built upon image-based visual reconstruction methods, which do not fully consider the characteristics of videos. In this paper, we propose a masked autoencoder-based, multi-scale optimized framework for 360-degree video streaming (MAESR360), which fully considers the temporal relevance of the video. We utilize spatio-temporal downsampling and high-ratio tube masking strategies to effectively reduce the amount of transmitted data. Additionally, we design a lightweight visual reconstruction model based on multi-scale feature fusion to recover the visual quality of video frames. The effectiveness of our proposed method is demonstrated through extensive experiments.

关键词： visualization visual communication Autoencoders Bit rate Superresolution Termination of employment Immersive experience Streaming media Reconstruction algorithms image reconstruction

来源：评论

学校读者我要写书评

暂无评论

Fast Adaptive Loop Filter Algorithm Based on the Optimization of Class Merging

Fast Adaptive Loop Filter Algorithm Based on the Optimizatio...

引用

IEEE visual communications and image processing (VCIP)

作者： Chengkang Huang Leilei Huang Chang Liu Shuocheng Wang Ke Xu Yibo Fan State Key Laboratory of Integrated Chips and Systems Fudan University China Institute of Microelectronic Circuits and Systems East China Normal University China Sanechips Technology Co. Chengdu China

ISBN: (数字)9798331529543

ISBN: (纸本)9798331529550

Adaptive loop filter (ALF) is one of the new tools adopted in the next generation video coding standard Versatile Video Coding (VVC). ALF leads to a performance improvement of 2%∼6% at the expense of high computational complexity and long processing time. Especially when encoding, ALF accounts 5%∼20% for total encoding runtime. To solve this problem, this paper proposes a fast algorithm for ALF by optimizing the process of class merging, which is an important step of rate-distortion optimization (RDO) in ALF. Experimental results indicate that compared to the VVC Test Model (VTM-22.0), this method can reduce the ALF encoding runtime on average 48.16%, 60.65%, 56.15% under all-intra, low-delay P and random access configurations, with only 0.15%, 0.31%, 0.19% increase in luma Bjontegaard Delta-Bit Rate (BD-BR).

关键词： Video coding Runtime image coding visual communication Merging Adaptive filters Rate-distortion Optimization Standards Next generation networking

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347页 << < 42 43 44 45 46 47 48 49 50 51 > >>

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：