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

1,417 篇 会议
20 篇 期刊文献

馆藏范围

1,437 篇 电子文献
0 种 纸本馆藏

日期分布

学科分类号

873 篇 工学
- 592 篇 计算机科学与技术...
- 307 篇 软件工程
- 297 篇 电气工程
- 268 篇 信息与通信工程
- 82 篇 光学工程
- 57 篇 电子科学与技术（可...
- 44 篇 控制科学与工程
- 33 篇 生物医学工程（可授...
- 25 篇 测绘科学与技术
- 24 篇 仪器科学与技术
- 23 篇 机械工程
- 11 篇 生物工程
- 9 篇 材料科学与工程（可...
- 8 篇 航空宇航科学与技...
- 8 篇 网络空间安全
- 7 篇 动力工程及工程热...
- 7 篇 土木工程
381 篇 理学
- 251 篇 物理学
- 168 篇 数学
- 25 篇 统计学（可授理学、...
- 14 篇 生物学
- 11 篇 化学
- 10 篇 系统科学
229 篇 医学
- 221 篇 临床医学
- 23 篇 特种医学
- 11 篇 基础医学(可授医学...
- 9 篇 药学(可授医学、理...
47 篇 管理学
- 32 篇 管理科学与工程(可...
- 13 篇 图书情报与档案管...
8 篇 法学
- 7 篇 社会学
3 篇 农学
3 篇 艺术学
2 篇 经济学
2 篇 文学
1 篇 教育学
1 篇 历史学

主题

441 篇 image compressio...
400 篇 image coding
190 篇 video compressio...
140 篇 transform coding
106 篇 data compression
76 篇 discrete cosine ...
71 篇 image reconstruc...
70 篇 decoding
61 篇 image quality
58 篇 quantization
58 篇 wavelet transfor...
57 篇 bit rate
56 篇 compression
55 篇 point cloud comp...
54 篇 discrete wavelet...
50 篇 video coding
46 篇 three-dimensiona...
42 篇 pixel
42 篇 psnr
42 篇 image processing

机构

5 篇 institute of cir...
5 篇 national key lab...
4 篇 pengcheng labora...
4 篇 peng cheng lab p...
4 篇 center for signa...
3 篇 univ sci & techn...
3 篇 harbin inst tech...
3 篇 department of co...
3 篇 electronic commu...
3 篇 univ stuttgart r...
3 篇 department of el...
3 篇 wangxuan institu...
3 篇 ricoh california...
2 篇 university of sc...
2 篇 institute of inf...
2 篇 tit&s coll bhiwa...
2 篇 school of inform...
2 篇 chongqing commun...
2 篇 dipartimento di ...
2 篇 fraunhofer insti...

作者

5 篇 richter thomas
5 篇 schelkens peter
5 篇 ebrahimi touradj
5 篇 y. altunbasak
5 篇 valenzise giusep...
5 篇 kountchev roumen
4 篇 w. kinsner
4 篇 battiato s
4 篇 yang yang
4 篇 baronti s
4 篇 deforges olivier
4 篇 alparone l
4 篇 mancuso m
4 篇 kountcheva roumi...
4 篇 ebrahimi t
4 篇 aiazzi b
3 篇 abir jaafar huss...
3 篇 k. k. mahapatra
3 篇 chun-shien lu
3 篇 bao youneng

语言

1,393 篇 英文
30 篇 其他
13 篇 中文
2 篇 土耳其文

检索条件"任意字段=Conference on Still-Image Compression"

共 1437 条记录，以下是51-60 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：

UNIVERSAL EFFICIENT VARIABLE-RATE NEURAL image compression 47

UNIVERSAL EFFICIENT VARIABLE-RATE NEURAL IMAGE COMPRESSION

引用

47th IEEE International conference on Acoustics, Speech and Signal Processing (ICASSP)

作者： Yin, Shanzhi Li, Chao Bao, Youneng Liang, Yongsheng Meng, Fanyang Liu, Wei Harbin Inst Technol Shenzhen Peoples R China Peng Cheng Lab Shenzhen Peoples R China

ISBN: (纸本)9781665405409

Recently, Learning-based image compression has reached comparable performance with traditional image codecs(such as JPEG, BPG, WebP). However, computational complexity and rate flexibility are still two major challenges for its practical deployment. To tackle these problems, this paper proposes two universal modules named Energy-based Channel Gating(ECG) and Bit-rate Modulator(BM), which can be directly embedded into existing end-to-end image compression models. ECG uses dynamic pruning to reduce FLOPs for more than 50% in convolution layers, and a BM pair can modulate the latent representation to control the bit-rate in a channel-wise manner. By implementing these two modules, existing learning-based image codecs can obtain ability to output arbitrary bit-rate with a single model and reduced computation.

关键词： image compression dynamic pruning variable-rate

来源：评论

学校读者我要写书评

暂无评论

Group-aware Parameter-efficient Updating for Content-Adaptive Neural Video compression 24

Group-aware Parameter-efficient Updating for Content-Adaptiv...

引用

32nd ACM International conference on Multimedia, MM 2024

作者： Chen, Zhenghao Zhou, Luping Hu, Zhihao Xu, Dong The University of Newcastle Newcastle Australia The University of Sydney Sydney Australia Tencent AI Lab Shenzhen China The University of Hong Kong Hong Kong Hong Kong

ISBN: (纸本)9798400706868

Content-adaptive compression is crucial for enhancing the adaptability of the pre-trained neural codec for various contents. Though, its application in neural video compression (NVC) is still limited due to two main aspects: 1), video compression relies heavily on temporal redundancy, therefore updating just one or a few frames can lead to significant errors accumulating over time;2), NVC frameworks are generally complex, with many comprehensive components that are not trivial to update quickly during the encoding procedure. To address these challenges, we have developed a content-adaptive NVC technique called Group-aware Parameter-efficient Updating (GPU). Initially, to minimize error accumulation, we adopt a group-aware approach for updating encoder parameters. This involves adopting a patch-based Group of Pictures (GoP) updating strategy to segment a video into patch-based GoPs, which will be updated to facilitate a globally optimized domain-transferable solution. Subsequently, we introduce a parameter-efficient delta-tuning strategy, which is achieved by integrating several light-weight adapters into each encoding component by using both serial and parallel configuration. Such architecture-agnostic modules stimulate the components with large parameters, thereby reducing the updating cost during the encoding stage. We incorporate our GPU into the latest NVC framework and conduct extensive experiments, whose results showcase outstanding video compression efficiency across six video compression benchmarks and the adaptability of one medical volumetric image compression benchmark. © 2024 ACM.

关键词： Encoding (symbols)

来源：评论

学校读者我要写书评

暂无评论

One-Click Upgrade from 2D to 3D: Sandwiched RGB-D Video compression for Stereoscopic Teleconferencing

One-Click Upgrade from 2D to 3D: Sandwiched RGB-D Video Comp...

引用

IEEE/CVF conference on Computer Vision and Pattern Recognition (CVPR)

作者： Hu, Yueyu Guleryuz, Onur G. Chou, Philip A. Tang, Danhang Taylor, Jonathan Maxham, Rus Wang, Yao NYU Tandon Sch Engn Brooklyn NY 11201 USA Google LLC Mountain View CA USA

ISBN: (纸本)9798350365474

Stereoscopic video conferencing is still challenging due to the need to compress stereo RGB-D video in real-time. Though hardware implementations of standard video codecs such as H.264 / AVC and HEVC are widely available, they are not designed for stereoscopic videos and suffer from reduced quality and performance. Specific multiview or 3D extensions of these codecs are complex and lack efficient implementations. In this paper, we propose a new approach to upgrade a 2D video codec to support stereo RGB-D video compression, by wrapping it with a neural pre- and post-processor pair. The neural networks are end-to-end trained with an image codec proxy, and shown to work with a more sophisticated video codec. We also propose a geometry-aware loss function to improve rendering quality. We train the neural pre- and post-processors on a synthetic 4D people dataset, and evaluate it on both synthetic and real-captured stereo RGB-D videos. Experimental results show that the neural networks generalize well to unseen data and work out-of-box with various video codecs. Our approach saves about 30% bit-rate compared to a conventional video coding scheme and MV-HEVC at the same level of rendering quality from a novel view, without the need of a task-specific hardware upgrade.

关键词： Video conferencing

来源：评论

学校读者我要写书评

暂无评论

Collaborative Face Privacy Protection Method Based on Adversarial Examples in Social Networks 19th

Collaborative Face Privacy Protection Method Based on Advers...

引用

19th International conference on Advanced Intelligent Computing Technology and Applications (ICIC)

作者： Pan, Zhenxiong Sun, Junmei Li, Xiumei Zhang, Xin Bai, Huang Hangzhou Normal Univ Sch Informat Sci & Technol Hangzhou 311121 Peoples R China Key Lab Cryptog Zhejiang Prov Hangzhou 311121 Peoples R China

ISBN: (纸本)9789819947546;9789819947553

The face image de-identification method commonly used to protect personal privacy on social networks faces the problem of not being able to assure the usability of image sharing. Although the privacy protection method based on adversarial examples meets this requirement, there are still potential hidden problems of information leakage and the compression processing of images by social networks will weaken the privacy protection effect. In this paper, we propose a collaborative privacy protection method based on adversarial examples for photo sharing services on social networks, called CSP3Adv(Collaborative Social Platform Privacy Protection Adversarial Example). We use the perturbation transfer module, which avoids the information leakage caused by accessing to the original image. Moreover, we use the frequency restriction module to guarantees the privacy of users' face images after social network compression. The experimental results show that CSP3Adv achieves better privacy protection for various face recognition models and commercial API interfaces on different datasets.

关键词： Adversarial examples Face verification Privacy protection JPEG compression

来源：评论

学校读者我要写书评

暂无评论

Rethinking Decoders for Transformer-based Semantic Segmentation: A compression Perspective 38

Rethinking Decoders for Transformer-based Semantic Segmentat...

引用

38th conference on Neural Information Processing Systems, NeurIPS 2024

作者： Wen, Qishuai Li, Chun-Guang School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing100876 China

State-of-the-art methods for Transformer-based semantic segmentation typically adopt Transformer decoders that are used to extract additional embeddings from image embeddings via cross-attention, refine either or both types of embeddings via self-attention, and project image embeddings onto the additional embeddings via dot-product. Despite their remarkable success, these empirical designs still lack theoretical justifications or interpretations, thus hindering potentially principled improvements. In this paper, we argue that there are fundamental connections between semantic segmentation and compression, especially between the Transformer decoders and Principal Component Analysis (PCA). From such a perspective, we derive a white-box, fully attentional DEcoder for PrIncipled semantiC segemenTation (DEPICT), with the interpretations as follows: 1) the self-attention operator refines image embeddings to construct an ideal principal subspace that aligns with the supervision and retains most information;2) the cross-attention operator seeks to find a low-rank approximation of the refined image embeddings, which is expected to be a set of orthonormal bases of the principal subspace and corresponds to the predefined classes;3) the dot-product operation yields compact representation for image embeddings as segmentation masks. Experiments conducted on dataset ADE20K find that DEPICT consistently outperforms its black-box counterpart, Segmenter, and it is light weight and more robust. Our code and models are available at https://***/QishuaiWen/DEPICT. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High Efficient compression: Model compression Method Based on Channel Pruning and Knowledge Distillation

High Efficient Compression: Model Compression Method Based o...

引用

2023 Asia-Europe conference on Electronics, Data Processing and Informatics, ACEDPI 2023

作者： Lin, Junan Ye, Zekai Wang, Junhan Zhejiang Gongshang University College of Computer and Information Engineering Hangzhou China

ISBN: (纸本)9798350301151

With the development of neural network models in the field of deep learning image processing, more complex and higher performance neural network models can be used, but with it comes greater parameter quantities and computing power requirements. Although the model compression method has been updated in recent years, it still has problems such as inefficiency and reduced accuracy. Based on this, we propose a model compression method based on channel pruning and knowledge distillation, we sort and prune the L2 regularization weights of the convolutional layer filter containing a large number of calculations in the original model and prune it according to a certain proportion, and assist in restoring the accuracy by the knowledge distillation of the pruning model through the original model. Experimental results of the VGG16 model show that our pruning method reduced the parameters of the model by half and increased its processing speed to 2.7 times that of the original model, but the accuracy was reduced by about 10%. To solve this problem, we propose a knowledge distillation method to assist the training of the pruning model, so that the problem of model accuracy degradation has been improved and maintained at about 3.3%, to achieve a balanced state of model compression and accuracy reduction, thereby realizing the efficient compression of the model. © 2023 IEEE.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

TA2P: TASK-AWARE ADAPTIVE PRUNING METHOD FOR image CLASSIFICATION ON EDGE DEVICES 49

TA2P: TASK-AWARE ADAPTIVE PRUNING METHOD FOR IMAGE CLASSIFIC...

引用

49th IEEE International conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Wang, Yanting Li, Feng Zhang, Han Northwestern Polytech Univ Sch Software Xian Peoples R China Northwestern Polytech Univ Shenzhen Res & Dev Inst Shenzhen Peoples R China China Unicom Res Inst Beijing Peoples R China

ISBN: (纸本)9798350344868;9798350344851

Convolutional neural networks (CNNs) have been extensively used in image classification. However, it is still challenging to directly deploy them on edge devices because of high computation requirements. To solve this problem, many pruning schemes for neural networks have been proposed. However, these methods ignore the fact that most edge devices only need to handle some instead of the whole classes. If the classification of several classes is defined as one task, then tasklevel information could be utilized to further lighten CNNs. To this end, we propose such a task-aware adaptive model pruning method in this paper. Specifically, we first employ control gates to learn weights of each convolutional channel of each class, and then merge class-level control gates through linear combinations to obtain the pruned model for an adaptive task on edge devices. Experiments demonstrate that our proposed method could significantly reduce the number of parameters up to 33.3% and 13.5% on CIFAR-10 and CIFAR-100, while achieving almost the same accuracy compared with baseline methods.

关键词： Model compression channel pruning edge computing task aware

来源：评论

学校读者我要写书评

暂无评论

A Generative Adversarial Network for Video compression 4

A Generative Adversarial Network for Video Compression

引用

conference on Big Data IV - Learning, Analytics, and Applications

作者： Du, Pengli Liu, Ying Ling, Nam Liu, Lingzhi Ren, Yongxiong Hsu, Ming Kai Santa Clara Univ Santa Clara CA 95053 USA Kwai Inc Palo Alto CA 94306 USA

ISBN: (纸本)9781510650718;9781510650701

Video data has occupied people's daily professional and entertainment activities. It imposes a big pressure on the Internet bandwidth. Hence, it is important to develop effective video coding techniques to compress video data as much as possible and save the transmission bandwidth, while still providing visually pleasing decoded videos. In conventional video coding such as the high efficiency video coding (HEVC) and the versatile video coding (VVC), signal processing and information theory-based techniques are mainstream. In recent years, thanks to the advances in deep learning, a lot of deep learning-based approaches have emerged for image and video compression. In particular, the generative adversarial networks (GAN) have shown superior performance for image compression. The decoded images are usually sharper and present more details than pure convolutional neural network (CNN)-based image compression and are more consistent with human visual system (HVS). Nevertheless, most existing GAN-based methods are for still image compression, and truly little research investigates the potential of GAN for video compression. In this work, we propose a novel inter-frame video coding scheme that compresses both reference frames and target (residue) frames by GAN. Since residue signals contain less energy, the proposed method effectively reduces the bit rates. Meanwhile, since we adopt adversarial learning, the perceptual quality of decoded target frames is well-preserved. The effectiveness of our proposed algorithm is demonstrated by experimental studies on common test video sequences.

关键词： Deep learning generative adversarial network human visual system image compression motion compensation perceptual quality residue-frame coding video coding

来源：评论

学校读者我要写书评

暂无评论

Evolution of AVIF Encoder: Speed and Memory Optimizations 5

Evolution of AVIF Encoder: Speed and Memory Optimizations

引用

IEEE 5th International conference on Multimedia Information Processing and Retrieval (MIPR)

作者： Tulabandul, Ranjit Kumar Jayaprakash, Jayasanker Rao, Sanampudi Venkata Al, Cherma Raj An Gadgil, Neeraj Galligan, Frank Chang, Wan-Teh Ittiam Syst Pvt Ltd Consulate 11 Richmond Rd Bangalore 560025 Karnataka India Google LLC 1600 Amphitheatre Pkwy Mountain View CA 94043 USA

ISBN: (数字)9781665495486

ISBN: (纸本)9781665495486

The AVI image File Format (AVIF) is an open-source, royalty-free image compression standard that is aimed at providing higher compression gains. In recent years, there has been an exponential increase in the amount of image data captured, stored, rendered and transmitted by billions of users across the globe, via several web and mobile applications. It is important to make image encoders faster and memory-efficient to cater to a wide range of devices ensuring quality user experience. In this paper, we provide an overview of speed optimizations that were contributed to the libaom encoder. We describe methods to reduce the complexity of prediction mode and residual-transform search. Experiments indicate that on average, the slowest libavif encoder speed setting provides a BD-Rate (PSNR) gain of 39%, whereas the fastest libavif encoder speed setting provides a BD-Rate (PSNR) gain of 16% with a 48% speed-up over the best quality WebP encoder for still images.

关键词： AVIF libaom libavif WebP image compression

来源：评论

学校读者我要写书评

暂无评论

DEEP INCREMENTAL OPTICAL FLOW CODING FOR LEARNED VIDEO compression 29

DEEP INCREMENTAL OPTICAL FLOW CODING FOR LEARNED VIDEO COMPR...

引用

IEEE International conference on image Processing (ICIP)

作者： Chang, Chih-Peng Chen, Peng-Yu Ho, Yung-Han Peng, Wen-Hsiao Natl Yang Ming Chiao Tung Univ Dept Comp Sci Hsinchu Taiwan

ISBN: (数字)9781665496209

ISBN: (纸本)9781665496209

This work addresses motion coding in end-to-end learned video compression. The efficiency of motion coding is critical at low bit rates, at which a large portion of the bitstream signals motion information. Most end-to-end learned video codecs adopt an intra-coding approach to coding motion information as individual optical flow maps. Some recent studies introduce predictive motion coding to encode optical flow map residuals. still, motion coding remains an active research area for learned video compression. We present an incremental optical flow coding scheme. It first leverages an extrapolated flow together with the reference frame in estimating an incremental flow between the reference and the target frames for efficient motion coding. It then derives the final flow map for motion compensation by integrating the incremental and the extrapolated flows in a double-warping scheme. Experimental results on commonly used datasets show the superiority of our method over predictive motion coding and other advanced schemes.

关键词： Video Coding Motion Extrapolation Motion Coding Incremental Flow Double Warping

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144页 << < 2 3 4 5 6 7 8 9 10 11 > >>

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：