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
Object Recognition with Task Relevant Combined Local Features
Wenjun Zhu,Liqing Zhang +1 more
TL;DR: This paper improves traditional cortex-like hierarchical models of object recognition by introducing supervision during forming combined local features by analyzing why introducing supervision in this stage is necessary and explaining what can be extracted by some feature selection algorithms.
Proceedings ArticleDOI
Guess what you draw: interactive contour-based image retrieval on a million-scale database
TL;DR: A real-time image retrieval system which allows users to search target images whose objects are similar to the query in contour, regardless of their sizes and positions appearing in the images, which has better retrieval rate than existing systems and algorithms.
Proceedings Article
Higher-order PLS for classification of ERPs with application to BCIs
TL;DR: The higher-order PLS approach to find the latent variables related to the target labels and then make classification based on latent variables to effectively extract the underlying components from brain activities which correspond to the specific mental state is proposed.
Posted Content
Hard Pixel Mining for Depth Privileged Semantic Segmentation.
TL;DR: Zhang et al. as discussed by the authors leverage only the depth of training images as the privileged information to mine the hard pixels in semantic segmentation, in which depth information is only available for training images but not available for test images.
Proceedings ArticleDOI
Nonnegative Tensor PCA and Application to Speaker Recognition in Noise Environments
Qiang Wu,Liqing Zhang +1 more
TL;DR: A new approach called nonnegative tensor principal component analysis (NTPCA) with sparse constraint is proposed for speech feature extraction and can increase the recognition accuracy specifically in noise environments.