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
Proceedings ArticleDOI
Beyond Coding: Detection-driven Image Compression with Semantically Structured Bit-stream
TL;DR: This paper proposes a learning based Semantically Structured Coding (SSC) framework to generate SemanticallyStructured Bit-stream (SSB), where each part of bit-stream represents a certain object and can be directly used for aforementioned tasks.
Journal ArticleDOI
Sequential Gating Ensemble Network for Noise Robust Multiscale Face Restoration
TL;DR: Wang et al. as mentioned in this paper proposed a sequential gating ensemble network (SGEN) for multiscale robust face restoration. But, the SGEN network is not able to handle multiple scales of receptive field.
Patent
Method for encoding floating-point data, method for decoding floating-point data, and corresponding encoder and decoder
TL;DR: In this article, an algorithm for efficiently compressing floating-point data in 3D meshes is presented, where the exponent, sign and mantissa are separately compressed separately, and a reference pointing to the storage position is encoded.
Posted Content
Semantics-Aligned Representation Learning for Person Re-identification
TL;DR: Zhang et al. as discussed by the authors proposed a semantic alignment network (SAN) which consists of a base network as encoder and a decoder for reconstructing/regressing the densely semantics aligned full texture image.
Proceedings ArticleDOI
Learned Video Compression with Feature-level Residuals.
TL;DR: This paper presents an end-to-end video compression network for P-frame challenge on CLIC, and combines the advantages of both pixel-level and feature-level residual compression methods by model ensembling.