Z
Zhongbo Shi
Researcher at University of Science and Technology of China
Publications - 7
Citations - 178
Zhongbo Shi is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Data compression & Image compression. The author has an hindex of 5, co-authored 7 publications receiving 170 citations. Previous affiliations of Zhongbo Shi include Microsoft.
Papers
More filters
Journal ArticleDOI
Photo Album Compression for Cloud Storage Using Local Features
Zhongbo Shi,Xiaoyan Sun,Feng Wu +2 more
TL;DR: Experimental results show that the proposed feature-based coding scheme can be 10 times more efficient than individual JPEG compression and reduce redundancy between images using a block-based motion compensation, similar to video compression.
Proceedings ArticleDOI
Spatially Scalable Video Coding for HEVC
Zhongbo Shi,Xiaoyan Sun,Feng Wu +2 more
TL;DR: This work proposes a SSVC scheme to provide both single-loop and multi-loop solutions by enabling different inter-layer prediction mechanisms and employs an extra patch learning-based prediction mode named P-mode to further improve coding performance.
Proceedings ArticleDOI
Feature-based image set compression
Zhongbo Shi,Xiaoyan Sun,Feng Wu +2 more
TL;DR: This paper is the first to propose a generic image set compression scheme which removes the set redundancy based on local features in addition to luminance values, and utilizes a SIFT-based global transformation to enhance the correlation between two images.
Journal ArticleDOI
Spatially Scalable Video Coding For HEVC
Zhongbo Shi,Xiaoyan Sun,Feng Wu +2 more
TL;DR: An SSVC scheme to support both single-loop (SL) and multiloop (ML) solutions by enabling different interlayer prediction mechanisms by exploiting the interlayer redundancy based on the quadtree coding structure of HEVC is proposed.
Proceedings ArticleDOI
Multi-model prediction for image set compression
Zhongbo Shi,Xiaoyan Sun,Feng Wu +2 more
TL;DR: This paper proposes the first multi- model prediction (MoP) method for image set compression to significantly reduce inter image redundancy and enhances the correlation between images using feature-based geometric multi-model fitting.