scispace - formally typeset
Z

Zhibo Chen

Researcher at University of Science and Technology of China

Publications -  374
Citations -  6048

Zhibo Chen is an academic researcher from University of Science and Technology of China. The author has contributed to research in topics: Computer science & Image quality. The author has an hindex of 27, co-authored 344 publications receiving 3385 citations. Previous affiliations of Zhibo Chen include Sony Broadcast & Professional Research Laboratories & Microsoft.

Papers
More filters
Patent

Method for control delay in interactive multiple vision point video stream media service

TL;DR: In this article, a method for controlling relay in alternative multi-view-point video flow media service, which belongs to the technical field of multimedia data transmission, is proposed, which mainly comprises the following steps: firstly, carrying out the time synchronization between users and a server, wherein the server enables the users who watch the same viewpoint to build a view-point inner overlay network, all the viewpoint inner overlays together build an overlay network between the view-points, when the users watch multiviewpoint video programs, the equal overlay networks are added on the two
Patent

Method for adaptive entropy coding of tree structures

TL;DR: In this article, a method for encoding a bitstream comprises steps of defining at least a first and a second symbol group of binary symbols, with S1 being a subset of S2, determining within the bitstream first portions, second portions and third portions, wherein first portions have Th 1 or more consecutive S1 symbols and second portions had Th 2 or more successive S2 symbols, encoding the bit stream, wherein the values indicating the boundary positions between the first, second and third parts in the bit-stream are encoded using different codes.
Proceedings ArticleDOI

End-to-End Facial Image Compression with Integrated Semantic Distortion Metric

TL;DR: An End-to-End Facial Image Compression framework with a novel variable block size Regionally Adaptive Pooling (RAP) module whose parameters can be automatically optimized according to gradient feedback from an integrated semantic distortion metrics, including a successful exploration to apply Generative Adversarial Network as metric directly in image compression scheme.
Proceedings ArticleDOI

Seismic trace editing by applying machine learning

TL;DR: This study proposes a method based on machine learning to conduct seismic trace editing automatically and combines the techniques of Hough transform and Convolutional Neural Network for trace editing.
Patent

User terminal device, server device, system and method for assessing quality of media data

TL;DR: In this article, a user terminal device, a server device, and a system and a method for assessing quality of media data are described, which is used for extracting artefact features from the media data and for communicating the features to the server device which is then used for determining a quality score using the artefacts and an artefact/quality score database accessible by the server devices.