S
Suping Wu
Researcher at Ningxia University
Publications - 12
Citations - 54
Suping Wu is an academic researcher from Ningxia University. The author has contributed to research in topics: Computer science & Engineering. The author has an hindex of 2, co-authored 6 publications receiving 28 citations.
Papers
More filters
Journal ArticleDOI
Similarity-Aware and Variational Deep Adversarial Learning for Robust Facial Age Estimation
TL;DR: A variational deep adversarial learning (VDAL) paradigm, which learns to encode each face sample in two factorized parts, i.e., the intra-class variance distribution and the intra -class invariant class center, which principally optimizes the variational confidence lower bound on the Variational factorized feature representation.
Journal ArticleDOI
Learning Reasoning-Decision Networks for Robust Face Alignment
TL;DR: Experimental results show that the proposed RDN consistently outperforms most state-of-the-art approaches on four widely-evaluated challenging datasets.
Book ChapterDOI
Learning Relational-Structural Networks for Robust Face Alignment
TL;DR: A relational-structural networks approach to learn both local and global feature representation for robust face alignment, which consistently outperforms the most state-of-the-art methods on widely evaluated challenging datasets.
Proceedings ArticleDOI
Learning Deformable Hourglass Networks (DHGN) for Unconstrained Face Alignment
TL;DR: This paper proposes a deformable hourglass networks (DHGN) approach to investigate the problem of face alignment, especially in such challenging cases when faces undergo large variations including severe poses, diverse expressions and partial occlusions in unconstrained environments.
Book ChapterDOI
Disentangled Representation Learning for Leaf Diseases Recognition
Xing Wang,Congcong Zhu,Suping Wu +2 more
TL;DR: A disentangled representation interactive network (DRIN), which disentangles the global features of each plant leaf and learns the discriminative representation of multiple sub-properties, including plant species, disease types and disease severity, is proposed.