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
Convex MRF potential functions
Stan Z. Li,Y.H. Huang,J.S. Fu +2 more
TL;DR: A general definition of convex potential functions is given for discontinuity-preserving MRF restoration models and an important guideline is derived for devising potential functions in MRF models to be adaptive to discontinuities.
Book ChapterDOI
Detecting Face with Densely Connected Face Proposal Network
TL;DR: This work proposes a novel face detector, dubbed the Densely Connected Face Proposal Network (DCFPN), with high performance as well as real-time speed on the CPU devices, and uses the dense anchor strategy and a fair L1 loss function to handle small faces well.
Proceedings ArticleDOI
A dynamic discharge structure for ultracapacitor application in the fuel cell UPS
TL;DR: A dynamic discharge structure model for ultracapacitor application in a 3 kW base station UPS has a better efficiency than the static discharge structure using a DC/DC converter to extend the duration.
Posted Content
Self-supervised on Graphs: Contrastive, Generative, or Predictive.
TL;DR: Self-supervised learning (SSL) is emerging as a new paradigm for extracting informative knowledge through well-designed pretext tasks without relying on manual labels as mentioned in this paper, however, precise annotations are generally very expensive and time-consuming.
Proceedings ArticleDOI
De-Mark GAN: Removing Dense Watermark with Generative Adversarial Network
TL;DR: Experimental results show that the verification benefits well from the recovered ID photos with high quality and the proposed De-mark GAN can achieve a competitive result in both image quality and verification.