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
Journal ArticleDOI
Task-Driven Semantic Coding via Reinforcement Learning
Xin Li,Jun Shi,Zhibo Chen +2 more
TL;DR: Zhang et al. as discussed by the authors implemented task-driven semantic coding by implementing semantic bit allocation based on reinforcement learning (RL) for video/image classification, detection and segmentation.
Proceedings ArticleDOI
No Reference Block Based Blur Detection
TL;DR: A No Reference Block-based Blur Detection (NR-BBD) algorithm is proposed, which calculates the local blur at the boundaries of Macro Blocks and then averages all of them to get the blur of the image.
Posted Content
Uncertainty-Aware Multi-Shot Knowledge Distillation for Image-Based Object Re-Identification.
TL;DR: This paper designs an Uncertainty-aware Multi-shot Teacher-Student (UMTS) Network that consists of a teacher network that learns the comprehensive features from multiple images of the same object, and a student network that takes a single image as input.
Posted Content
Style Normalization and Restitution for Domain Generalization and Adaptation
TL;DR: A novel Style Normalization and Restitution module (SNR) is designed to simultaneously ensure both high generalization and discrimination capability of the networks and enforce a dual causality loss constraint in the restitution step to encourage the better separation of task-relevant and task-irrelevant features.
Journal ArticleDOI
Stereoscopic Omnidirectional Image Quality Assessment Based on Predictive Coding Theory
TL;DR: This article proposes a stereoscopic omnidirectional image quality evaluator (SOIQE) to cope with the characteristics of 3D 360-degree images and is a parametric model without necessary of regression learning, which ensures its interpretability and generalization performance.