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
Posted Content
Deep Gaussian Scale Mixture Prior for Spectral Compressive Imaging
TL;DR: Wang et al. as mentioned in this paper proposed a novel hyperspectral image (HSI) reconstruction method based on the maximum a posterior (MAP) estimation framework using learned Gaussian Scale Mixture (GSM) prior.
Learning Primitive-aware Discriminative Representations for Few-shot Learning
TL;DR: Zhang et al. as discussed by the authors proposed a primitive mining and reasoning network (PMRN) to learn primitive-aware representations based on metric-based FSL model, which achieved state-of-the-art results on six standard benchmarks.
Proceedings ArticleDOI
Visual pattern degradation based image quality assessment
TL;DR: Inspired by the orientation selectivity mechanism in the primary visual cortex, a novel visual pattern is introduced to represent the structure of a local region and the proposed IQA method performs better than the existing IQA metrics.
Journal ArticleDOI
Correlation based universal image/video coding loss recovery
TL;DR: A novel and universal coding artifact reduction method is introduced that achieves about 0.8dB on average of PSNR improvement for JPEG, MPEG4, H.264/AVC, and HEVC compressed signals, respectively.
Journal ArticleDOI
Spatial-temporal network for fine-grained-level emotion EEG recognition
Youshuo Ji,Fu Li,Boxun Fu,Yang Li,Yijin Zhou,Yi Niu,Lijian Zhang,Yuanfang Chen,Guangming Shi +8 more
TL;DR: A corresponding fine-grained emotion EEG network (FG-emotionNet) for spatial-temporal feature extraction and the performance of the proposed method is superior to that of the representative methods in emotion recognition and similar structure methods with proposed method.