Shiyang Lan

ORCID: 0000-0003-4362-1774
Publications
Citations
Views
---
Saved
---
About
Contact & Profiles
Research Areas
  • Advanced Image and Video Retrieval Techniques
  • Neural Networks and Applications
  • Domain Adaptation and Few-Shot Learning
  • Explainable Artificial Intelligence (XAI)
  • Face and Expression Recognition
  • Advanced Graph Neural Networks
  • Adversarial Robustness in Machine Learning
  • Human Pose and Action Recognition
  • Advanced Vision and Imaging
  • Graph Theory and Algorithms
  • Video Surveillance and Tracking Methods
  • Semantic Web and Ontologies

Fuzhou University
2023-2024

Existing representation learning approaches lie predominantly in designing models empirically without rigorous mathematical guidelines, neglecting interpretation terms of modeling. In this work, we propose an optimization-derived network that embraces both and extensibility. To ensure interpretability at the design level, adopt a transparent approach customizing from optimization perspective. This involves modularly stitching together components to meet specific requirements, enhancing...

10.1109/tmm.2024.3383295 article EN IEEE Transactions on Multimedia 2024-01-01

As researchers strive to narrow the gap between machine intelligence and human through development of artificial multimedia technologies, it is imperative that we recognize critical importance trustworthiness in open-world, which has become ubiquitous all aspects daily life for everyone. However, several challenges may create a crisis trust current open-world systems need be bridged: 1) Insufficient explanation predictive results; 2) Inadequate generalization learning models; 3) Poor...

10.1145/3581783.3612352 article EN 2023-10-26
Coming Soon ...