T
Tieniu Tan
Researcher at Chinese Academy of Sciences
Publications - 727
Citations - 46303
Tieniu Tan is an academic researcher from Chinese Academy of Sciences. The author has contributed to research in topics: Feature extraction & Iris recognition. The author has an hindex of 96, co-authored 704 publications receiving 39487 citations. Previous affiliations of Tieniu Tan include Association for Computing Machinery & Center for Excellence in Education.
Papers
More filters
Book ChapterDOI
Multi-view gymnastic activity recognition with fused HMM
Ying Wang,Kaiqi Huang,Tieniu Tan +2 more
TL;DR: This paper uses multi-view features to recognize six kinds of gymnastic activities using shape-based features extracted from two orthogonal cameras in the form of R transform and a multi- view approach based on Fused HMM to combine different features for similar gymnastic activity recognition.
Book ChapterDOI
Fusion Based Blind Image Steganalysis by Boosting Feature Selection
TL;DR: Experimental results show that the fusion based approach increases the blind detection accuracy and also provides a good generality by identifying an untrained stego-algorithm.
Proceedings ArticleDOI
ReD-SFA: Relation Discovery Based Slow Feature Analysis for Trajectory Clustering
TL;DR: This paper proposed an approach, named Relation Discovery based Slow Feature Analysis (ReD-SFA), for feature learning and graph construction simultaneously, which can discover reliable intra-cluster relations with high precision, and competitive clustering performance can be achieved in comparison with state-of-the-art.
Journal ArticleDOI
Selective Wavelet Attention Learning for Single Image Deraining
TL;DR: Zhang et al. as discussed by the authors proposed a selective wavelet attention learning method to separate rain and background information in the embedding space, which can improve the accuracy of single image deraining.
Proceedings ArticleDOI
POD: Practical Object Detection With Scale-Sensitive Network
TL;DR: Wang et al. as discussed by the authors proposed a scale decomposition method that transfers the robust fractional scale into combinations of fixed integral scales for each convolution filter, which exploit the dilated convolution.