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

1,643 篇 会议
23 篇 期刊文献

馆藏范围

1,666 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

739 篇 工学
- 534 篇 计算机科学与技术...
- 443 篇 信息与通信工程
- 196 篇 电气工程
- 186 篇 软件工程
- 57 篇 光学工程
- 35 篇 电子科学与技术（可...
- 32 篇 生物工程
- 10 篇 动力工程及工程热...
- 10 篇 化学工程与技术
- 9 篇 机械工程
- 8 篇 仪器科学与技术
- 7 篇 生物医学工程（可授...
- 6 篇 控制科学与工程
- 5 篇 网络空间安全
- 4 篇 安全科学与工程
- 3 篇 建筑学
- 3 篇 土木工程
531 篇 医学
- 530 篇 临床医学
- 3 篇 基础医学(可授医学...
- 3 篇 药学(可授医学、理...
- 3 篇 特种医学
151 篇 理学
- 104 篇 物理学
- 57 篇 数学
- 32 篇 生物学
- 20 篇 统计学（可授理学、...
- 7 篇 化学
- 4 篇 系统科学
33 篇 管理学
- 24 篇 管理科学与工程(可...
- 9 篇 图书情报与档案管...
9 篇 法学
- 8 篇 社会学
1 篇 军事学
1 篇 艺术学

主题

324 篇 visual communica...
295 篇 image coding
157 篇 training
153 篇 feature extracti...
131 篇 visualization
121 篇 image color anal...
116 篇 image reconstruc...
94 篇 video coding
94 篇 image processing
82 篇 encoding
80 篇 three-dimensiona...
80 篇 image segmentati...
76 篇 cameras
72 篇 estimation
67 篇 decoding
66 篇 image edge detec...
60 篇 deep learning
60 篇 image quality
59 篇 bit rate
57 篇 convolution

机构

43 篇 shanghai jiao to...
39 篇 institute of ima...
25 篇 school of electr...
21 篇 university of sc...
17 篇 tianjin univ sch...
16 篇 shanghai jiao to...
15 篇 beijing universi...
14 篇 peking univ inst...
14 篇 cas key laborato...
12 篇 institute of dig...
12 篇 institute of ima...
11 篇 university of el...
10 篇 univ sci & techn...
10 篇 univ sci & techn...
10 篇 school of inform...
10 篇 cooperat mediane...
9 篇 school of remote...
9 篇 shanghai jiao to...
9 篇 microsoft res as...
9 篇 xidian univ sch ...

作者

35 篇 zhai guangtao
32 篇 guangtao zhai
28 篇 song li
28 篇 sumei li
22 篇 li sumei
22 篇 yang xiaokang
20 篇 li li
20 篇 gao wen
19 篇 li song
18 篇 shan liu
17 篇 xie rong
17 篇 min xiongkuo
16 篇 xiongkuo min
16 篇 siwei ma
16 篇 dong liu
15 篇 xiong ruiqin
15 篇 zhenzhong chen
14 篇 ma siwei
14 篇 wen gao
13 篇 chen zhibo

语言

1,647 篇 英文
10 篇 中文
7 篇 土耳其文
1 篇 其他

检索条件"任意字段=Visual Communications and Image Processing, VCIP 2015"

共 1666 条记录，以下是21-30 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 Forensics Strikes Back: Defense Against Adversarial Patch

Image Forensics Strikes Back: Defense Against Adversarial Pa...

引用

2024 Conference on visual communications and image processing

作者： Kao, Ching-Chia Lu, Chun-Shien Yu, Chia-Mu Acad Sinica Inst Informat Sci IIS Taipei Taiwan Natl Taiwan Univ Taipei Taiwan Natl Yang Ming Chiao Tung Univ Hsinchu Taiwan

ISBN: (纸本)9798331529543;9798331529550

Traffic sign recognition plays a crucial role in self-driving cars, but unfortunately, it is vulnerable to adversarial patches (AP). Although AP can efficiently fool DNN-based models in previous studies, the connection between image forensics and AP detection still needs to be explored. From a high-level point of view, their goals are the same. That is to find tampered regions and prevent false positives in the meantime. A natural question arises: "Is achieving application-agnostic anomaly detection possible?" In this paper, we propose image Forensics Defense Against Adversarial Patch (IDAP), a framework to defend against adversarial patches via generalizable features learned from tampered images. In addition, we incorporate the Hausdorff erosion loss into our network model for joint training to complete the shape of a predicted mask. Extensive experimental comparisons on three datasets, including COCO, DFG, and APRICOT demonstrate that IDAP outperforms state-of-the-art AP detection methods.

关键词： Adversarial Patch AI Security image Forensics

来源：评论

学校读者我要写书评

暂无评论

Semantic Ensemble Loss and Latent Refinement for High-Fidelity Neural image Compression

Semantic Ensemble Loss and Latent Refinement for High-Fideli...

引用

2024 Conference on visual communications and image processing

作者： Li, Daxin Bai, Yuanchao Wang, Kai Jiang, Junjun Liu, Xianming Harbin Inst Technol Fac Comp Harbin Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Recent advancements in neural compression have surpassed traditional codecs in PSNR and MS-SSIM measurements. However, at low bit-rates, these methods can introduce visually displeasing artifacts, such as blurring, color shifting, and texture loss, thereby compromising perceptual quality of images. To address these issues, this study presents an enhanced neural compression method designed for optimal visual fidelity. We have trained our model with a sophisticated semantic ensemble loss, integrating Charbonnier loss, perceptual loss, style loss, and a non-binary adversarial loss, to enhance the perceptual quality of image reconstructions. Additionally, we have implemented a latent refinement process to generate content-aware latent codes. These codes adhere to bit-rate constraints, and prioritize bit allocation to regions of greater importance. Our empirical findings demonstrate that this approach significantly improves the statistical fidelity of neural image compression.

关键词： Generative image Compression Learned image Compression

来源：评论

学校读者我要写书评

暂无评论

Coarse-to-fine Transformer For Lossless 3D Medical image Compression

Coarse-to-fine Transformer For Lossless 3D Medical Image Com...

引用

2024 Conference on visual communications and image processing

作者： Yang, Xiaoxuan Lui, Guo Feng, Donghui Cheng, Zhengxue Yu, Guosheng Song, Li Shanghai Jiao Tong Univ Shanghai Peoples R China Alibaba Grp T Head Semicond Co Ltd Hangzhou Peoples R China

ISBN: (纸本)9798331529543;9798331529550

The rapid advancements in medical imaging have led to a growing demand for high-performance lossless compression of large 3D medical image datasets. Unlike natural images, medical images typically feature three-dimensional structures, and high bit-depth, necessitating specialized compression techniques. Based on a decoder-only transformer, we propose a learnable dual-decoder model for lossless compression of 3D medical images. Our approach packs voxels into patches, which are processed by a patch-level decoder to extract the patch feature. The voxels, along with the patch feature, are subsequently fed into a voxel-level decoder to model each voxel. This coarse-to-fine modeling strategy reduces the computational time for each voxel and enables long-range modeling dependencies. Experimental results demonstrate that our proposed model achieves state-of-the-art compression performance, with an approximately 15% improvement in compression performance over the traditional JP3D benchmark on various datasets.

关键词： Lossless image Compression Medical image Transformer

来源：评论

学校读者我要写书评

暂无评论

Light field depth estimation based on fusion of multi-scale semantic and geometric information

Light field depth estimation based on fusion of multi-scale ...

引用

2024 Conference on visual communications and image processing

作者： Tan, Feng Deng, Huiping Xiang, Sen Wu, Jin Wuhan Univ Sci & Technol Sch Informat Sci & Engn Wuhan Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Depth estimation of light field images is a crucial technique in various applications, including 3D reconstruction, autonomous driving, and object tracking. However, current deep-learning methods ignore the geometric information of the light field image and are limited to learning repetitive textures, which leads to inaccurate estimates of depth. The paper proposes a light field depth estimation network that fuses multi-scale semantic information with geometric information to address the problem of non-adaptation for repeated texture regions. The main focus of the network is the semantic and geometric information fusion (SGI) module, which can adaptively combine semantic and geometric information to improve the efficiency of cost aggregation. Furthermore, SGI module establishes a direct link between feature extraction and cost aggregation, providing feedback for feature extraction and guiding more efficient feature extraction. The experimental results from the optical field synthesis dataset HCI 4D demonstrate that the method has high accuracy and generalisation performance.

关键词： light field image Depth estimation Repeat texture area Semantic and geometric information fusion

来源：评论

学校读者我要写书评

暂无评论

ALICE: Adapt your Learnable image Compression modEl for variable bitrates

ALICE: Adapt your Learnable Image Compression modEl for vari...

引用

2024 Conference on visual communications and image processing

作者： Spadaro, Gabriele Ali, Muhammad Salman Presta, Alberto Pilo, Giommaria Bae, Sung-Ho Giraldo, Jhony H. Fiandrotti, Attilio Grangetto, Marco Tartaglione, Enzo Inst Polytech Paris Telecom Paris LTCI Paris France Univ Turin Turin Italy Kyung Hee Univ Yongin South Korea

ISBN: (纸本)9798331529543;9798331529550

When training a Learned image Compression model, the loss function is minimized such that the encoder and the decoder attain a target Rate-Distorsion trade-off. Therefore, a distinct model shall be trained and stored at the transmitter and receiver for each target rate, fostering the quest for efficient variable bitrate compression schemes. This paper proposes plugging Low-Rank Adapters into a transformer-based pre-trained LIC model and training them to meet different target rates. With our method, encoding an image at a variable rate is as simple as training the corresponding adapters and plugging them into the frozen pre-trained model. Our experiments show performance comparable with state-of-the-art fixed-rate LIC models at a fraction of the training and deployment cost. We publicly released the code at https://***/EIDOSLAB/ALICE.

关键词： image compression

来源：评论

学校读者我要写书评

暂无评论

Lookup Register-Tables with Interpolation for Effective image Transformation on x86/64 CPUs

Lookup Register-Tables with Interpolation for Effective Imag...

引用

2024 Conference on visual communications and image processing

作者： Kamei, Hirokazu Honda, Soichiro Hayashi, Kohei Maeda, Yoshihiro Fukushima, Norishige Nagoya Inst Technol Grad Sch Engn Nagoya Aichi Japan Shibaura Inst Technol Coll Engn Tokyo Japan

ISBN: (纸本)9798331529543;9798331529550

Lookup tables (LUTs) are commonly used to speed up image processing by handling complex mathematical functions like sine and exponential calculations. They are used in various applications such as camera image processing, high-dynamic range imaging, and edge-preserving filtering. However, due to the increasing gap between computing and input/output performance, LUTs are becoming less effective. Even though specific circuits like SIMD can improve LUT efficiency, they still need to bridge the performance gap fully. The gap makes it difficult to choose between direct numerical and LUT calculations. For this problem, a register-LUTs method with the nearest neighbor was proposed;however, it is limited for functions with narrow-range values approaching zero. In this paper, we propose a method for using register LUTs to process images efficiently over a wide range of values. Our contributions include proposing register-LUT with linear interpolation for efficient computation, using a smaller data type for further efficiency, and suggesting an efficient data retrieving method.

关键词： SIMD register-LUT interpolation x86/64 CPU image processing

来源：评论

学校读者我要写书评

暂无评论

FRIDAY: Mitigating Unintentional Facial Identity in Deepfake Detectors Guided by Facial Recognizers

FRIDAY: Mitigating Unintentional Facial Identity in Deepfake...

引用

2024 Conference on visual communications and image processing

作者： Kim, Younghun Kwon, Myung-Joon Lee, Wonjun Kim, Changick Korea Adv Inst Sci & Technol Grad Sch Green Growth & Sustainabil Daejeon South Korea Korea Adv Inst Sci & Technol Sch Elect Engn Daejeon South Korea

ISBN: (纸本)9798331529543;9798331529550

Previous Deepfake detection methods perform well within their training domains, but their effectiveness diminishes significantly with new synthesis techniques. Recent studies have revealed that detection models make decision boundaries based on facial identity instead of synthetic artifacts, leading to poor cross-domain performance. To address this issue, we propose FRIDAY, a novel training method that attenuates facial identity utilizing a face recognizer. To be specific, we first train a face recognizer using the same backbone as the Deepfake detector. We then freeze the recognizer and use it during the detector's training to mitigate facial identity information. This is achieved by feeding input images into both the recognizer and the detector, then minimizing the similarity of their feature embeddings using our Facial Identity Attenuating loss. This process encourages the detector to produce embeddings distinct from the recognizer, effectively attenuating facial identity. Comprehensive experiments demonstrate that our approach significantly improves detection performance on both in-domain and cross-domain datasets.

关键词： Deepfake Detection Unintentional Facial Identity Face Recognition image Forensics

来源：评论

学校读者我要写书评

暂无评论

Codec-agnostic Lenslet Video Coding with Smoothing Transform

Codec-agnostic Lenslet Video Coding with Smoothing Transform

引用

2024 Conference on visual communications and image processing

作者： Soetens, Eline Lafruit, Gauthier Teratani, Mehrdad Univ Libre Bruxelles Lab Image Synth & Anal Brussels Belgium

ISBN: (纸本)9798331529543;9798331529550

Plenoptic cameras are light field capturing devices able to acquire large amounts of angular and spatial information. The lenslet video produced by such cameras presents on each frame a distinctive hexagonal pattern of micro-images. Due to the particular structure of lenslet images, traditional video codecs perform poorly on lenslet video. Previous works have proposed a preprocessing scheme that cuts and realigns the micro-images on each lenslet frame. While effective, this method introduces high frequency components into the processed image. In this paper, we propose an additional step to the aforementioned scheme by applying an invertible smoothing transform. We evaluate the enhanced scheme on lenslet video sequences captured with single-focused and multi-focused plenoptic cameras. On average, the enhanced scheme achieves 9.85% bitrate reduction compared to the existing scheme.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

AsymLLIC: Asymmetric Lightweight Learned image Compression

AsymLLIC: Asymmetric Lightweight Learned Image Compression

引用

2024 Conference on visual communications and image processing

作者： Wang, Shen Cheng, Zhengxue Feng, Donghui Lu, Guo Song, Li Zhang, Wenjun Shanghai Jiao Tong Univ Dept Elect Engn Shanghai Peoples R China

ISBN: (纸本)9798331529543;9798331529550

Learned image compression (LIC) methods often employ symmetrical encoder and decoder architectures, evitably increasing decoding time. However, practical scenarios demand an asymmetric design, where the decoder requires low complexity to cater to diverse low-end devices, while the encoder can accommodate higher complexity to improve coding performance. In this paper, we propose an asymmetric lightweight learned image compression (AsymLLIC) architecture with a novel training scheme, enabling the gradual substitution of complex decoding modules with simpler ones. Building upon this approach, we conduct a comprehensive comparison of different decoder network structures to strike a better trade-off between complexity and compression performance. Experiment results validate the efficiency of our proposed method, which not only achieves comparable performance to VVC but also offers a lightweight decoder with only 51.47 GMACs computation and 19.65M parameters. Furthermore, this design methodology can be easily applied to any LIC models, enabling the practical deployment of LIC techniques.

关键词： Learned image compression neural network lightweight asymmetric

来源：评论

学校读者我要写书评

暂无评论

Variable Bitrate Models For Learned image Compression with Multi-gain units and Weighted Probability Assignment

Variable Bitrate Models For Learned Image Compression with M...

引用

2024 Conference on visual communications and image processing

作者： Wang, Ran Jiang, Wen Sun, Heming Katto, Jiro Waseda Univ Dept Comp Sci & Commun Engn Tokyo Japan Yokohama Natl Univ Fac Engn Yokohama Kanagawa Japan Waseda Univ Waseda Res Inst Sci & Engn Dept Comp Sci & Commun Engn Tokyo Japan

ISBN: (纸本)9798331529543;9798331529550

With the advancement of deep learning techniques, learned image compression (LIC) has surpassed traditional compression methods. However, these methods typically require training separate models to achieve optimal rate-distortion performance, leading to increased time and resource consumption. To tackle this challenge, we propose leveraging multi-gain and inverse multi-gain unit pairs to enable variable rate adaptation within a single model. Nevertheless, experiments have shown that rate-distortion performance may degrade at certain bitrates. Therefore, we introduce weighted probability assignment, where different selection probabilities are assigned during training based on lambda values, to increase the model's training frequency under specific bitrate conditions. To validate our approach, extensive experiments were conducted on Transformer-based and CNN-based models. The experimental results validate the efficiency of our proposed method.

关键词： Learned image compression variable rate multigain units weighted probability assignment

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167页 << < 1 2 3 4 5 6 7 8 9 10 > >>

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：