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
A Hierarchial Model for Visual Perception
Bolei Zhou,Liqing Zhang +1 more
TL;DR: Analysis of the perceptual manifold reveals that scene images which share similar perceptual similarities stay nearby in the manifold space, and the dimensions of the space could describe the spatial layout of scenes, which are like the degree of naturalness, openness supervised trained in this model.
Journal ArticleDOI
10-Hydroxy-trans-2-decenoic Acid, a New Potential Feed Additive for Broiler Chickens to Improve Growth Performance
TL;DR: In this article , the authors explored the potential possibility of 10-hydroxy-trans-2-decenoic acid (10-HDA) use in feeding broiler chickens.
Book ChapterDOI
Perception of transformation-invariance in the visual pathway
Wenlu Yang,Liqing Zhang,Libo Ma +2 more
TL;DR: Comparisons with Bilinear Sparse Coding presented by Grimes and Rao and Topo-ICA by Hayvarinen show that the proposed perceptual model has some advantages such as simple to implement and more robust to transformation invariance.
Proceedings ArticleDOI
Computational Model for Rotation-Invariant Perception
Wenlu Yang,Liqing Zhang,Libo Ma +2 more
TL;DR: By using the correlation coefficients of two neural responses as the measure of rotation-invariance, this model can perform the task of perception of rotating angles and successfully perceive the relative angles of rotating patches.
Book ChapterDOI
Affine invariant topic model for generic object recognition
Zhenxiao Li,Liqing Zhang +1 more
TL;DR: This paper presents a novel topic model named Affine Invariant Topic Model (AITM) for generic object recognition that incorporates spatial structure into traditional LDA.