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
Proceedings Article
Depth Privileged Object Detection in Indoor Scenes via Deformation Hallucination.
TL;DR: Zhang et al. as mentioned in this paper employ the deformable convolution layer with augmented offsets as their deformation module and regard the offsets as geometric deformation, because the offsets enable flexibly sampling over the object and transforming to a canonical shape for ease of detection.
Journal ArticleDOI
BHONEM: Binary High-Order Network Embedding Methods for Networked-Guarantee Loans
TL;DR: A binary higher-order network embedding method to learn the low-dimensional representations of a guarantee network and shows that this method outperforms other start-of-the-art algorithms for both classification accuracy and robustness, especially in the guarantee network.
Book ChapterDOI
Independent residual analysis for temporally correlated signals
Liqing Zhang,Andrzej Cichocki +1 more
TL;DR: An improvement to the Probabilistic Neural Network (PNN) is presented that overcomes two weaknesses of the original model and shows good generalization capacity with similar or even slightly better results than other approaches.
Proceedings ArticleDOI
PPTLens: Create Digital Objects with Sketch Images
TL;DR: This work proposes a novel sketch image recognition framework, including an effective stroke extraction strategy and a novel offline sketch parsing algorithm, to implement the 'Image to Object' (I2O) scenario.
Journal ArticleDOI
Statistically Adaptive Image Denoising Based on Overcomplete Topographic Sparse Coding
TL;DR: This paper presents a novel image denoising framework using overcomplete topographic model that improves the previous work on the following aspects: multi-category based sparse coding, adaptive learning, local normalization, lasso shrinkage function, and subset selection.