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
Relation-Aware Global Attention for Person Re-Identification
TL;DR: This work proposes an effective Relation-Aware Global Attention (RGA) module which captures the global structural information for better attention learning and proposes to stack the relations, i.e., its pairwise correlations/affinities with all the feature positions together to learn the attention with a shallow convolutional model.
Proceedings ArticleDOI
Style Normalization and Restitution for Generalizable Person Re-Identification
TL;DR: The aim of this paper is to design a generalizable person ReID framework which trains a model on source domains yet is able to generalize/perform well on target domains, and to enforce a dual causal loss constraint in SNR to encourage the separation of identity-relevant features and identity-irrelevant features.
Proceedings ArticleDOI
Densely Semantically Aligned Person Re-Identification
TL;DR: Zhang et al. as discussed by the authors proposed a two-stream network that consists of a main full image stream (MF-Stream) and a densely semantically-aligned guiding stream (DSAG-Stream).
Journal ArticleDOI
Fast integer-pel and fractional-pel motion estimation for H.264/AVC
TL;DR: A hybrid Unsymmetrical-cross Multi-hexagon-grid Search (UMHexagonS) algorithm is introduced, which well solves the false motion vector estimation problem because of the local-minimum and can save 30–50% computation compared with the Full Fractional-pel Search scheme.
Journal ArticleDOI
Light Field Spatial Super-Resolution Using Deep Efficient Spatial-Angular Separable Convolution
TL;DR: This paper proposes effective and efficient end-to-end convolutional neural network models for spatially super-resolving LF images with an hourglass shape, which allows feature extraction to be performed at the low-resolution level to save both the computational and memory costs.