G
Guangming Shi
Researcher at Xidian University
Publications - 488
Citations - 14046
Guangming Shi is an academic researcher from Xidian University. The author has contributed to research in topics: Computer science & Sparse approximation. The author has an hindex of 41, co-authored 428 publications receiving 10591 citations. Previous affiliations of Guangming Shi include Chinese Ministry of Education.
Papers
More filters
Proceedings ArticleDOI
Joint Entropy Degradation Based Blind Image Quality Assessment
TL;DR: This work attempts to measure the image quality with its visual entropy degradation by measuring the degradations on the joint probability distributions of the joint entropy equation, and introduces a novel BIQA method.
Posted Content
Learning Hybrid Sparsity Prior for Image Restoration: Where Deep Learning Meets Sparse Coding
TL;DR: A novel framework of implementing hybrid structured sparse coding processes by deep convolutional neural networks and shows that the proposed hybrid image restoration method performs comparably with and often better than the current state-of-the-art techniques.
Proceedings ArticleDOI
Observation quality guaranteed layout of camera networks via sparse representation
Chang Wang,Fei Qi,Guangming Shi +2 more
TL;DR: An efficient near-optimal convex solution for layout guaranteeing satisfactory observation quality based on an anisotropic sensing model of camera based on the physical imaging process is proposed.
Proceedings ArticleDOI
No-reference image quality assessment with orientation selectivity mechanism
TL;DR: By analyzing the quality degradation on those patterns, a novel visual pattern degradation based NR IQA method is proposed and Experimental results on large databases demonstrate that the proposed method outperforms the existing NRIQA methods.
Journal ArticleDOI
A Feature-Enhanced Anchor-Free Network for UAV Vehicle Detection
TL;DR: A novel architecture for UAV vehicle detection is proposed that uses anchor-free mechanism to eliminate predefined anchors, and a multi-scale semantic enhancement block (MSEB) and an effective 49-layer backbone which is based on the DetNet59.