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
Posted Content
F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
TL;DR: A Fusing-and-Filling Generative Adversarial Network (F2GAN) is proposed to generate realistic and diverse images for a new category with only a few images to ensure the diversity of generated images by a mode seeking loss and an interpolation regression loss.
Journal ArticleDOI
Cardiology knowledge free ECG feature extraction using generalized tensor rank one discriminant analysis
Kai Huang,Liqing Zhang +1 more
TL;DR: This study introduced a generalized tensor rank one discriminant analysis (GTR1DA), which involves considering the distribution of the data points near the classification boundary to calculate better projection tensors and achieves greater classification accuracy than other vector- and tensor-based methods.
Journal ArticleDOI
Regularized tensor discriminant analysis for single trial EEG classification in BCI
Jie Li,Liqing Zhang +1 more
TL;DR: A regularized tensor discriminant analysis (RTDA) algorithm is proposed for a multi-way discriminative subspace extraction from tensor-represented EEG data, which improves the performance for EEG classification and is able to find the most significant channels for classification, and can be applied to channel selection in BCI.
Proceedings Article
Multilinear Subspace Regression: An Orthogonal Tensor Decomposition Approach
Qibin Zhao,Cesar F. Caiafa,Danilo P. Mandic,Liqing Zhang,Tonio Ball,Andreas Schulze-Bonhage,Andrzej Cichocki +6 more
TL;DR: The proposed multilinear subspace regression model based on so called latent variable decomposition is introduced and is shown to be suitable for the prediction of multidimensional dependent data from multiddimensional independent data.
Proceedings ArticleDOI
F2GAN: Fusing-and-Filling GAN for Few-shot Image Generation
TL;DR: In this article, a fusion generator is designed to fuse the high-level features of conditional images with random interpolation coefficients, and then fills in attended low-level details with non-local attention module to produce a new image.