S
Stan Z. Li
Researcher at Westlake University
Publications - 625
Citations - 49737
Stan Z. Li is an academic researcher from Westlake University. The author has contributed to research in topics: Facial recognition system & Computer science. The author has an hindex of 97, co-authored 532 publications receiving 41793 citations. Previous affiliations of Stan Z. Li include Microsoft & Macau University of Science and Technology.
Papers
More filters
Proceedings ArticleDOI
A robust eye localization method for low quality face images
Dong Yi,Zhen Lei,Stan Z. Li +2 more
TL;DR: This work proposes a robust eye localization method for low quality face images to improve the eye detection rate and localization precision, and proposes a probabilistic cascade (P-Cascade) framework, in which the traditional cascade classifier is reformulate in a Probabilistic way.
Journal ArticleDOI
Eleven Routine Clinical Features Predict COVID-19 Severity Uncovered by Machine Learning of Longitudinal Measurements
Kai Zhou,Yaoting Sun,Lu Li,Zelin Zang,Jing Wang,Jun Li,Junbo Liang,Fangfei Zhang,Qiushi Zhang,Weigang Ge,Hao Chen,Xindong Sun,Liang Yue,Xiaomai Wu,Bo Shen,Jiaqin Xu,Hongguo Zhu,Shiyong Chen,Hai Yang,Shigao Huang,Minfei Peng,Dongqing Lv,Chao Zhang,Haihong Zhao,Luxiao Hong,Zhehan Zhou,Haixiao Chen,Xuejun Dong,Chunyu Tu,Minghui Li,Yi Zhu,Baofu Chen,Stan Z. Li,Tiannan Guo +33 more
TL;DR: A practical model for timely severity prediction for COVID-19 is presented, which is freely available at a webserver https://guomics.shinyapps.io/covidAI/.
Posted Content
Relational Learning for Joint Head and Human Detection
TL;DR: This work designs a head-body relationship discriminating module to perform relational learning between heads and human bodies, and leverage this learned relationship to regain the suppressed human detections and reduce head false positives.
Proceedings ArticleDOI
Color Models and Weighted Covariance Estimation for Person Re-identification
TL;DR: Experiments show that the proposed algorithm outperforms the state-of-the-art methods on two public benchmark datasets (VIPeR and PRID 450S) and demonstrates its feasibility and effectiveness.
Proceedings ArticleDOI
Multi-view face pose estimation based on supervised ISA learning
TL;DR: A supervised method is presented for more effective learning of view-subspace, assuming that view-labeled face examples are available and the models thus learned give more accurate pose estimation than those obtained with the unsupervised ISA.