X
Xiao-Tong Yuan
Researcher at Nanjing University of Information Science and Technology
Publications - 118
Citations - 4066
Xiao-Tong Yuan is an academic researcher from Nanjing University of Information Science and Technology. The author has contributed to research in topics: Sparse approximation & Thresholding. The author has an hindex of 29, co-authored 117 publications receiving 3374 citations. Previous affiliations of Xiao-Tong Yuan include Cornell University & Rutgers University.
Papers
More filters
Journal ArticleDOI
Visual Classification With Multitask Joint Sparse Representation
TL;DR: Two applications of the proposed multitask joint sparse representation model to combine the strength of multiple features and/or instances for recognition are investigated: fusing multiple kernel features for object categorization and robust face recognition in video with an ensemble of query images.
Proceedings ArticleDOI
Visual classification with multi-task joint sparse representation
Xiao-Tong Yuan,Shuicheng Yan +1 more
TL;DR: Experimental results on challenging real-world datasets show that the feature combination capability of the proposed algorithm is competitive to the state-of-the-art multiple kernel learning methods.
Journal Article
Truncated power method for sparse eigenvalue problems
Xiao-Tong Yuan,Tong Zhang +1 more
TL;DR: In this paper, the authors proposed a truncated power method that can approximately solve the underlying nonconvex optimization problem of sparse eigenvalue problem, which is to extract dominant (largest) sparse Eigenvectors with at most k non-zero components.
Journal ArticleDOI
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification
TL;DR: Wang et al. as discussed by the authors proposed a bidirectional-convolutional long short term memory (Bi-CLSTM) network to automatically learn the spectral-spatial features from hyperspectral images (HSIs).
Posted Content
Bidirectional-Convolutional LSTM Based Spectral-Spatial Feature Learning for Hyperspectral Image Classification
TL;DR: A novel deep learning framework named bidirectional-convolutional long short term memory (Bi-CLSTM) network to automatically learn the spectral-spatial features from hyperspectral images (HSIs) and can improve the classification performance by almost 1.5 % as compared to 3D-CNN.