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
Super-Resolution Quality Assessment: Subjective Evaluation Database and Quality Index Based on Perceptual Structure Measurement
TL;DR: This work proposes a more accurate perception structure measurement and uses their similarity comparisons to evaluate the SR algorithms, demonstrating that the proposed method performs well consistent with the human visual perception.
Journal ArticleDOI
RFPruning: A retraining-free pruning method for accelerating convolutional neural networks
TL;DR: A two-stage Retraining-Free pruning method, named RFPruning, which embeds the rough screening of channels into training and fine-tunes the structures during pruning, to achieve both good performance and low time consumption is proposed.
Journal ArticleDOI
Edge-Based Perceptual Image Coding
TL;DR: A novel psychovisually motivated edge-based low-bit-rate image codec that offers a compact description of scale-invariant second-order statistics of natural images, the preservation of which is crucial to the perceptual quality of coded images.
Journal ArticleDOI
Single-Shot Dense Depth Sensing with Color Sequence Coded Fringe Pattern
TL;DR: Quantitative and qualitative experiments demonstrate that the proposed color sequence coded fringe depth sensing method generates a higher precision depth, as compared to a Kinect and larger resolution ToF (Time of Flight) camera.
Journal ArticleDOI
GMSS: Graph-Based Multi-Task Self-Supervised Learning for EEG Emotion Recognition
Yang Liu,Ji Chen,Fu Li,Boxun Fu,Hao Wu,Youshuo Ji,Yijing Zhou,Yi Niu,Guangming Shi,Wenming Zheng +9 more
TL;DR: Experiments on SEED, SEED-IV, and MPED datasets show that the proposed GMSS has remarkable advantages in learning more discriminative and general features for EEG emotional signals.