G
Guoqiang Zhong
Researcher at Ocean University of China
Publications - 117
Citations - 2347
Guoqiang Zhong is an academic researcher from Ocean University of China. The author has contributed to research in topics: Deep learning & Computer science. The author has an hindex of 19, co-authored 102 publications receiving 1164 citations. Previous affiliations of Guoqiang Zhong include École de technologie supérieure & Chinese Academy of Sciences.
Papers
More filters
Journal ArticleDOI
Generative adversarial networks with mixture of t-distributions noise for diverse image generation.
TL;DR: The experimental results and statistical comparisons demonstrate that tGANs perform significantly better than pixleCNN and related GAN-based models for diverse image generation.
Journal ArticleDOI
Tensor representation learning based image patch analysis for text identification and recognition
Guoqiang Zhong,Mohamed Cheriet +1 more
TL;DR: A novel framework for text identification and recognition, called TRL-IPA, which can be directly applied to gray level and color images, and recognition results on images of handwritten digits show its advantage over state-of-the-art vector and tensor representation based approaches.
Proceedings ArticleDOI
Stretching deep architectures for text recognition
TL;DR: A novel deep learning method based on “stretching” the projection matrices of stacked feature learning models, called SDA, which performs not only better than shallow featurelearning models, but also state-of-the-art deep learning models.
Journal ArticleDOI
Underwater image colour constancy based on DSNMF
TL;DR: Compared with state-of-the-art underwater image enhancement methods using no reference image quality assessment, the proposed DSNMF method outperforms current techniques in terms of its visual effect and IQA, but is also simpler to implement.
Book ChapterDOI
Visual Texture Perception with Feature Learning Models and Deep Architectures
TL;DR: This work proposes a set of deep architectures to learn compact representations of the texture perceptual features, and finds that 12 perceptual features are significant to describe the texture images with regard to the human perceptions.