L
Liqing Zhang
Researcher at Shanghai Jiao Tong University
Publications - 337
Citations - 10883
Liqing Zhang is an academic researcher from Shanghai Jiao Tong University. The author has contributed to research in topics: Computer science & Feature extraction. The author has an hindex of 37, co-authored 297 publications receiving 8886 citations. Previous affiliations of Liqing Zhang include South China University of Technology & National University of Singapore.
Papers
More filters
Book ChapterDOI
Moving object detecting system with phase discrepancy
TL;DR: This paper uses Canny-like salient area extraction algorithm to extract moving segments from motion saliency map, and uses graph based image segmentation algorithm to extend salient areas to bounding boxes.
Journal ArticleDOI
Computational model for perception of objects and motions
TL;DR: A visual perceptual model and computational mechanism for training the perceptual model that is able to perceive objects and their motions with a high accuracy and strong robustness against additive noise and Kullback-Leibler divergence is introduced.
Proceedings ArticleDOI
Non-blind image deconvolution using deep dual-pathway rectifier neural network
TL;DR: This paper proposes a pure learning approach to learn a mapping from a blurred patch to a clean patch directly with a deep dual-pathway rectifier neural network and empirically shows that the model works by efficiently detecting the blurry input patterns and then reconstructing the clean patch with the corresponding dictionary atoms.
Book ChapterDOI
A novel hierarchical model of attention: maximizing information acquisition
Yang Cao,Liqing Zhang +1 more
TL;DR: A novel attention model to produce saliency maps by generating information distributions on incoming images by automatically marks spots with large information amount as saliency, which ensures the system gains the maximum information acquisition through attending these spots.
Proceedings ArticleDOI
Few-shot Image Generation Using Discrete Content Representation
TL;DR: This work makes the first attempt to adapt few-shot image translation method to few- shot image generation task, and model the autoregressive distribution of discrete content map conditioned on style vector, which can alleviate the incompatibility between content map and style vector.