Search For:

Displaying 1-15 out of 15 total
Reducing Blocking Artifacts in Compressed Images via Transform-Domain Non-local Coefficients Estimation
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Xinfeng Zhang,Ruiqin Xiong,Siwei Ma,Wen Gao
Issue Date:July 2012
pp. 836-841
Block transform coding using discrete cosine transform is the most popular approach for image compression. However, many annoying blocking artifacts are generated due to coarse quantization on transform coefficients independently. This paper proposes an ef...
 
Exploiting Image Local and Nonlocal Consistency for Mixed Gaussian-Impulse Noise Removal
Found in: 2012 IEEE International Conference on Multimedia and Expo (ICME)
By Jian Zhang,Ruiqin Xiong,Chen Zhao,Siwei Ma,Debin Zhao
Issue Date:July 2012
pp. 592-597
Most existing image denoising algorithms can only deal with a single type of noise, which violates the fact that the noisy observed images in practice are often suffered from more than one type of noise during the process of acquisition and transmission. I...
 
Compressed Sensing Recovery via Collaborative Sparsity
Found in: Data Compression Conference
By Jian Zhang,Debin Zhao,Chen Zhao,Ruiqin Xiong,Siwei Ma,Wen Gao
Issue Date:April 2012
pp. 287-296
Compressed Sensing (CS) has drawn quite an amount of attention as a joint sampling and compression approach. Its theory shows that a signal can be decoded from many fewer measurements than suggested by the Nyquist sampling theory, when the signal is sparse...
 
Transductive Regression with Local and Global Consistency for Image Super-Resolution
Found in: Data Compression Conference
By Xianming Liu, Debin Zhao, Ruiqin Xiong, Siwei Ma, Wen Gao, Huifang Sun
Issue Date:March 2011
pp. 173-182
In this paper, we propose a novel image super-resolution algorithm, referred to as interpolation based on transductive regression with local and global consistency (TRLGC). Our algorithm first constructs a set of local interpolation models which can predic...
 
Auto Regressive Model and Weighted Least Squares Based Packet Video Error Concealment
Found in: Data Compression Conference
By Yongbing Zhang, Xinguang Xiang, Siwei Ma, Debin Zhao, Wen Gao
Issue Date:March 2010
pp. 455-464
In this paper, auto regressive (AR) model is applied to error concealment for block-based packet video encoding. Each pixel within the corrupted block is restored as the weighted summation of corresponding pixels within the previous frame in a linear regre...
 
Error Resilient Dual Frame Motion Compensation with Uneven Quality Protection
Found in: Data Compression Conference
By Da Liu, Debin Zhao, Siwei Ma
Issue Date:March 2010
pp. 539
In this paper, an error resilient JU-DFMC is proposed for video transmission over error-prone channels. In the proposed error resilient JU-DFMC, a new error resilient prediction structure of DFMC is firstly presented. Then an end-to-end distortion model is...
 
Shape-Based Depth Map Coding
Found in: Intelligent Information Hiding and Multimedia Signal Processing, International Conference on
By Nan Zhang, Siwei Ma, Wen Gao
Issue Date:September 2009
pp. 316-319
Three-dimensional Television (3DTV) system based on Depth-Image-Based Rendering(DIBR) has won popular recognition of researchers. Since the depth information is closely related with the rendering of viewed pixels, the quality of coding has a direct impact ...
 
H.264/AVC-Based Depth Map Sequence Coding Using Improved Loop-filter
Found in: Intelligent Information Hiding and Multimedia Signal Processing, International Conference on
By Nan Zhang, Siwei Ma
Issue Date:September 2009
pp. 312-315
Research has been widely carried out on three dimensional television(3DTV) system using Depth-Image-Based Rendering (DIBR) techniques. The depth data is a kind of important 3D data, transmitted along with 2D texture data. At present, coding of depth map se...
 
Compression-Induced Rendering Distortion Analysis for Texture/Depth Rate Allocation in 3D Video Compression
Found in: Data Compression Conference
By Yanwei Liu, Siwei Ma, Qingming Huang, Debin Zhao, Wen Gao, Nan Zhang
Issue Date:March 2009
pp. 352-361
In 3D video applications, the virtual view is generally rendered by the compressed texture and depth. The texture and depth compression with different bit-rate overheads can lead to different virtual view rendering qualities. In this paper, we analyze the ...
 
Stereo Matching via Disparity Estimation and Surface Modeling
Found in: Computer Vision and Pattern Recognition, IEEE Computer Society Conference on
By Jong Dae Oh, Siwei Ma, C.-C. Jay Kuo
Issue Date:June 2007
pp. 1-8
Two new techniques are proposed to improve stereo matching performance in this work. First, to address the disparity discontinuity problem in occluded regions, we present a disparity estimation procedure, which consists of two steps; namely, a greedy dispa...
 
Decoder-Friendly Subpel MV Selection for H.264/AVC Video Encoding
Found in: Intelligent Information Hiding and Multimedia Signal Processing, International Conference on
By Qi Zhang, Yunyang Dai, Siwei Ma, C.-C. Jay Kuo
Issue Date:December 2006
pp. 655-658
A decoder-friendly subpel motion vector (MV) selection scheme for H.264/AVC video encoding is proposed in this work. First, the rate-distortion (RD) relationship with respect to subpel MVs is examined to shed light on the tradeoff of R-D performance degrad...
 
Fast H.264/AVC Inter-Mode Decision with RDC Optimization
Found in: Intelligent Information Hiding and Multimedia Signal Processing, International Conference on
By Yu Hu, Qing Li, Siwei Ma, C.-C. Jay Kuo
Issue Date:December 2006
pp. 511-516
A complexity-constrained inter-mode decision algorithm for H.264/AVC video coding is developed using a rate-distortioncomplexity (RDC) optimization framework in this work. The proposed algorithm consists of two main steps. At the first step, we use the num...
 
Joint Rate-Distortion-Complexity Optimization for H.264 Motion Search
Found in: Multimedia and Expo, IEEE International Conference on
By Yu Hu, Qing Li, Siwei Ma, C.-c. Kuo
Issue Date:July 2006
pp. 1949-1952
A joint rate-distortion-complexity H.264 motion search framework is proposed to balance the encoder's coding efficiency and complexity in an embedded system environment. Under our framework, the complexity of H.264 motion search is primarily measured by th...
 
Low-Complexity Adaptive Block-Size Transform Based on Extended Transforms
Found in: Multimedia and Expo, IEEE International Conference on
By Honggang Qi, Wen Gao, Siwei Ma, Debin Zhao, Xiangyang Ji
Issue Date:July 2006
pp. 129-132
In this paper, a low-complexity 8?8/4?4 Adaptive Block-size Transform (ABT) scheme is tentatively proposed for the Chinese Audio and Video coding Standard (AVS)1. In the proposed ABT scheme, an integer 8?8 transform is derived from the integer 4?4 transfor...
 
IEEE 1857 Standard Empowering Smart Video Surveillance Systems
Found in: IEEE Intelligent Systems
By Wen Gao,Yonghong Tian,Tiejun Huang,Siwei Ma,Xianguo Zhang
Issue Date:September 2013
pp. 1
IEEE 1857, Standard for Advanced Audio and Video Coding, was released as IEEE 1857-2013 in June 2013. Despite consisting of several different groups, the most significant feature of IEEE 1857-2013 is its surveillance groups, which can not only achieve at l...
 
 1