检索结果-内蒙古大学图书馆

Sequence of linear programming for transmission of fine-scalable coded content in bandwidth-limited environments

MULTIMEDIA SYSTEMS 2006年第5期11卷 455-466页

作者： Su, Xiao Wang, Tao San Jose State Univ Dept Comp Sci San Jose CA 95192 USA Synopsys Inc Mountain View CA 94043 USA

In this paper, we propose an optimal peer assignment algorithm on peer-to-peer networks. This algorithm is designed to maximize the quality of transmitting fine-scalable coded content by exploiting the embedding property of scalable coding. To be more realistic, we assume that the requesting peer has a delay constraint to display the content within a certain delay bound, and it also has limited incoming bandwidth. We first use a simple example to illustrate the peer assignment problem, and then formulate this problem as a linear programming problem, followed by a nonlinear programming problem. To efficiently solve the second nonlinear problem, we transform it into a sequence of linear programming problems. Finally, we apply our proposed algorithm to both image and video transmissions in bandwidth-limited environments. Extensive experiments have been carried out to evaluate the complexity and performance of our approach by comparing it with both nonlinear formulation and two heuristic schemes. The results have verified the superior performance of our proposed algorithm.

关键词： sequence of linear programming scalable coding content delivery peer-to-peer networks

来源：评论

学校读者我要写书评

暂无评论

ICMH-Net: Neural Image Compression Towards both Machine Vision and Human Vision 23

ICMH-Net: Neural Image Compression Towards both Machine Visi...

引用

31st ACM International Conference on Multimedia (MM)

作者： Liu, Lei Hu, Zhihao Chen, Zhenghao Xu, Dong Beihang Univ Beijing Peoples R China Univ Sydney Sydney NSW Australia Univ Hong Kong Hong Kong Peoples R China

ISBN: (纸本)9798400701085

Neural image compression has gained significant attention thanks to the remarkable success of deep neural networks. However, most existing neural image codecs focus solely on improving human vision perception. In this work, our objective is to enhance image compression methods for both human vision quality and machine vision tasks simultaneously. To achieve this, we introduce a novel approach to Partition, Transmit, Reconstruct, and Aggregate (PTRA) the latent representation of images to balance the optimizations for both aspects. By employing our method as a module in existing neural image codecs, we create a latent representation predictor that dynamically manages the bit-rate cost for machine vision tasks. To further improve the performance of auto-regressive-based coding techniques, we enhance our hyperprior network and predictor module with context modules, resulting in a reduction in bit-rate. The extensive experiments conducted on various machine vision benchmarks such as ILSVRC 2012, VOC 2007, VOC 2012, and COCO demonstrate the superiority of our newly proposed image compression framework. It outperforms existing neural image compression methods in multiple machine vision tasks including classification, segmentation, and detection, while maintaining high-quality image reconstruction for human vision.

关键词： image compression machine vision human vision scalable coding

来源：评论

学校读者我要写书评

暂无评论

Rate-distortion approach to databases: Storage and content-based retrieval

Rate-distortion approach to databases: Storage and content-b...

引用

IEEE International Symposium on Information Theory

作者： Tuncel, E Koulgi, P Rose, K Univ Calif Riverside Dept Elect Engn Riverside CA 92521 USA Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA Univ Calif Santa Barbara Dept Elect & Comp Engn Santa Barbara CA 93106 USA

ISBN: (纸本)0780375017

This paper investigates the relationship between rate-distortion theory and efficient content-based data retrieval from high-dimensional databases. We consider database design as the encoding of a data object sequence, and retrieval from the database as the decoding of the sequence using side information (i.e., the query) available only at the decoder. We show that, in this setting, the optimal asymptotic tradeoff between the search time R-s (bits per data object read from the storage device) and the expected search accuracy D-s (relevance of the retrieved data set) is given by the Wyner-Ziv solution with a side-information-dependent distortion measure. Moreover, the data indexing and retrieval problem is, in general, inseparable from the data compression problem. Data items selected by the search procedure, which can be stored in the disk with a limited total rate of R-r greater than or equal to R-s, need to be presented at a prescribed expected reconstruction quality D-r. This is, hence, a problem of scalable source coding or successive refinement, albeit with differing layer distortion measures to quantify search and reconstruction quality, respectively. We derive a single-letter characterization of all achievable quadruples {R-s, R-r, D-s, D-r}, and prove conditions for "successive refinability" without rate loss. Finally, we show that the special case D-s = D-r = 0 is nontrivial and of practical interest in this context, as it can impose "acceptable" search and reconstruction qualities for each individual data item and for the entire query space with high probability, in contradistinction with standard average distortion requirements. The region of achievable {R-s,R- R-r} is obtained by adapting Rimoldi's characterization to a new regular scalable coding problem.

关键词： approximate similarity searching content-based retrieval databases scalable coding successive refinability without rate loss Wyner-Ziv problem zero-one distortion measures

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-based Point Cloud Geometry coding with Resolution Scalability 22

Deep Learning-based Point Cloud Geometry Coding with Resolut...

引用

22nd IEEE International Workshop on Multimedia Signal Processing (MMSP)

作者： Guarda, Andre F. R. Rodrigues, Nuno M. M. Pereira, Fernando Inst Super Tecn Inst Telecomunicacoes Lisbon Portugal Inst Politecn Leiria Inst Telecomunicacoes ESTG Leiria Portugal

ISBN: (纸本)9781728193205

Point clouds are a 3D visual representation format that has recently become fundamentally important for immersive and interactive multimedia applications. Considering the high number of points of practically relevant point clouds, and their increasing market demand, efficient point cloud coding has become a vital research topic. In addition, scalability is an important feature for point cloud coding, especially for real-time applications, where the fast and rate efficient access to a decoded point cloud is important;however, this issue is still rather unexplored in the literature. In this context, this paper proposes a novel deep learning-based point cloud geometry coding solution with resolution scalability via interlaced sub-sampling. As additional layers are decoded, the number of points in the reconstructed point cloud increases as well as the overall quality. Experimental results show that the proposed scalable point cloud geometry coding solution outperforms the recent MPEG Geometry-based Point Cloud Compression standard which is much less scalable.

关键词： point cloud coding deep learning scalable coding resolution scalability interlaced sampling

来源：评论

学校读者我要写书评

暂无评论

EMBEDDED CELP WITH ADAPTIVE CODEBOOKS IN ENHANCEMENT LAYERS AND MULTI-LAYER GAIN OPTIMIZATION

EMBEDDED CELP WITH ADAPTIVE CODEBOOKS IN ENHANCEMENT LAYERS ...

引用

IEEE International Conference on Acoustics, Speech and Signal Processing

作者： Stachurski, Jacek Texas Instruments Inc DSP Solut R&D Ctr Dallas TX 75265 USA

ISBN: (纸本)9781424423538

The paper describes an embedded CELP coder in which an adaptive codebook is included in every enhancement layer and the lower-layer codebook gains are re-optimized in the higher layers to further improve speech quality. Each layer maintains its own filter memories to generate required target vectors, adds adaptive and fixed codebook contributions, and re-optimizes all codebook gains to improve coder performance (multi-layer gain optimization). The common elements across the embedded layers include the lower-layer adaptive and fixed codebook entries. The pitch-lag used in the core layer is also re-used in the enhancement layers to maintain time synchronization between layers. Estimation and encoding of selected lower-layer parameters may take into account their estimated impact on the higher layers. The described Embedded CELP coder has been implemented in the Embedded Variable Bit-Rate (EV-VBR) codec standardized by ITU-T as Recommendation G.718. The characterization test results of the G.718 Embedded CELP are summarized.

关键词： Speech coding Embedded coding scalable coding CELP

来源：评论

学校读者我要写书评

暂无评论

Dual-Layer Lossless coding for Infrared Video 33

Dual-Layer Lossless Coding for Infrared Video

引用

33rd IEEE International Conference on Visual Communications and Image Processing (IEEE VCIP)

作者： Hsiao, Hui-Shan Shih, Wen-Hsien Chiang, Jui-Chiu Lie, Wen-Nung Natl Chung Cheng Univ Dept Elect Engn Chiayi Taiwan Natl Chung Cheng Univ CIRAS Chiayi Taiwan

ISBN: (纸本)9781538644584

Conventional natural image/video is targeted for entertainment and some distortion is allowed for the decoded data. For infrared imagery, lossless coding is needed for some specified applications, where analysis over the content is always realized, such as military and medical applications. In this paper, we propose a bit-depth scalable coding scheme, where lossy compression is applied to the base layer while lossless compression is to the enhancement layer. Through the usage of deep residual learning, an improved inter-layer prediction is obtained. Experiment results show that the proposed scheme not only provides the flexibility by offering two kinds of content depending on the request, it also achieves up to 3.26% bitrate reduction compared to the single-layer lossless coding scheme.

关键词： Lossless coding scalable coding high bit-depth deep residual learning

来源：评论

学校读者我要写书评

暂无评论

Image coding based on Selective Super-Resolution Network 11

Image coding based on Selective Super-Resolution Network

引用

11th International Conference on Information and Communication Technology Convergence (ICTC) - Data, Network, and AI in the age of Untact (ICTC)

作者： Kim, Younhee Cho, Seunghyun Jeong, Se-Yoon Choi, Jin Soo Elect & Telecommun Res Inst Broadcasting & Media Res Lab Daejeon South Korea Kyungnam Univ Dept Informat & Commun Engn Changwon Si South Korea

ISBN: (纸本)9781728167589

This paper presents an image compression method using deep learning based super-resolution. Different from traditional image compression methods, we propose to select the super resolution network to enhance the perceptual quality. In the proposed method, the network selection map is generated by utilizing the semantic segmentation, image classification, and encoding distortion. Compared with traditional scalable image coding methods, more texture area are visually pleased even in the severe low bitrate encoding. For this reason, our method has the potential to result better compression ratio in terms of subjective image quality. Experimental results demonstrate the effectiveness of the proposed method. When compared with high efficiency video coding (HEVC), our method achieve the average of 43.42% bitrate saving at the same perceptual image quality.

关键词： image compression perceptual quality scalable coding super resolution

来源：评论

学校读者我要写书评

暂无评论

SPARSE SIGNAL MODELING IN A scalable CELP CODER

SPARSE SIGNAL MODELING IN A SCALABLE CELP CODER

引用

21st European Signal Processing Conference (EUSIPCO)

作者： Dymarski, Przemyslaw Romaniuk, Rafal Warsaw Univ Technol Inst Telecommun PL-00665 Warsaw Poland

ISBN: (纸本)9781479936878

This work presents a series of sparse signal modeling algorithms implemented in a variable rate CELP coder in order to compare their performances at a reasonable computational load. Multipulse excitation (MPE), Multi-Pulse Maximum Likelihood Quantization (MP-MLQ), Algebraic CELP (ACELP) and hybrid excitation schemes are analyzed under a common framework. New approaches are proposed, based on cyclic and parallel use of fast greedy algorithms. These algorithms yield a statistically significant reduction of signal approximation error at a controllable computational complexity. Main results were confirmed by comparing MOS values obtained with the PESQ algorithm

关键词： speech coding CELP scalable coding sparse approximation MP-MLQ ACELP

来源：评论

学校读者我要写书评

暂无评论

scalable FACIAL IMAGE COMPRESSION WITH DEEP FEATURE RECONSTRUCTION 26

SCALABLE FACIAL IMAGE COMPRESSION WITH DEEP FEATURE RECONSTR...

引用

26th IEEE International Conference on Image Processing (ICIP)

作者： Wang, Shurun Wang, Shiqi Zhang, Xinfeng Wang, Shanshe Ma, Siwei Gao, Wen Peking Univ Inst Digital Media Beijing Peoples R China City Univ Hong Kong Dept Comp Sci Hong Kong Peoples R China

ISBN: (纸本)9781538662496

In this paper, we propose a scalable image compression scheme, including the base layer for feature representation and enhancement layer for texture representation. More specifically, the base layer is designed as the deep learning feature for analysis purpose, and it can also be converted to the fine structure with deep feature reconstruction. The enhancement layer, which serves to compress the residuals between the input image and the signals generated from the base layer, aims to faithfully reconstruct the input texture. The proposed scheme can feasibly inherit the advantages of both compress-then-analyze and analyze-then-compress schemes in surveillance applications. The performance of this framework is validated with facial images, and the conducted experiments provide useful evidences to show that the proposed framework can achieve better rate-accuracy and rate-distortion performance over conventional image compression schemes.

关键词： Image compression deep learning feature feature reconstruction scalable coding

来源：评论

学校读者我要写书评

暂无评论

Low bit-rate subband image coding with matching pursuits

Low bit-rate subband image coding with matching pursuits

引用

Visual Communications and Image Processing 1998 Conference

作者： Rabiee, HR Safavian, SR Gardos, TR Mirani, AJ Intel Corp Media & Interconnect Technol Lab Hillsboro OR 97124 USA

ISBN: (纸本)0819427497

In this paper, a novel multiresolution algorithm for low bit-rate image compression is presented. High quality low bit-rate image compression is achieved by first decomposing the image into approximation and detail subimages with a shift-orthogonal multiresolution analysis. Then, at the coarsest resolution level, the coefficients of the transformation are encoded by an orthogonal matching pursuit algorithm with a wavelet packet dictionary. Our dictionary consists of convolutional splines of up to order two for the detail and approximation subbands. The intercorrelation between the various resolutions is then exploited by using the same bases from the dictionary to encode the coefficients of the finer resolution bands at the corresponding spatial locations. To further exploit the spatial correlation of the coefficients, the zero trees of wavelets (EZW) algorithm [I] was used to identify the potential zero trees. The coefficients of the presentation are then quantized and arithmetic encoded at each resolution, and packed into a scalable bit stream structure. Our new algorithm is highly bit-rate scalable, and performs better than the segmentation based matching pursuit [2,3] and EZW encoders at lower bit rates, based on subjective image quality and peak signal-to-noise ratio (PSNR).

关键词： image compression scalable coding multiresolution coding subband coding matching pursuit wavelet coding

来源：评论

学校读者我要写书评

暂无评论

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：

请选择收藏分类：

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

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：