W
Wei Huang
Publications - 39
Citations - 112
Wei Huang is an academic researcher. The author has contributed to research in topics: Computer science & Chemistry. The author has an hindex of 5, co-authored 39 publications receiving 112 citations.
Papers
More filters
Proceedings Article
DSTAGNN: Dynamic Spatial-Temporal Aware Graph Neural Network for Traffic Flow Forecasting
TL;DR: A novel Dynamic Spatial-Temporal Aware Graph Neural Network (DSTAGNN) to model the complex spatial-temporal interaction in road network and design a novel graph neural network architecture that can not only represent dynamic spatial relevance among nodes with an improved multi-head attention mechanism, but also acquire the wide range of dynamic temporal dependency from multi-receptive field features via multi-scale gated convolution.
Journal ArticleDOI
Targeting regulated cell death (RCD) with small-molecule compounds in triple-negative breast cancer: a revisited perspective from molecular mechanisms to targeted therapies
TL;DR: In this paper , the authors focus on summarizing the molecular mechanisms of the above-mentioned seven major RCD subroutines related to triple negative breast cancer (TNBC) and the latest progress of small-molecule compounds targeting different RCD subsroutine.
Proceedings Article
Auto-scaling Vision Transformers without Training
TL;DR: As-ViT is proposed, an auto-scaling framework for ViTs without training, which automatically discovers and scales up ViTs in an efficient and principled manner and proposes a progressive tokenization strategy to train ViTs faster and cheaper.
Journal ArticleDOI
Deep learning image transmission through a multimode fiber based on a small training dataset.
TL;DR: An improved deep neural network incorporating attention mechanism and DSSIM loss function (AM_U_Net) is used to recover input images with speckles transmitted through a multimode fiber (MMF), demonstrating its significant application potential in medical imaging and secure communication.
Journal ArticleDOI
Learning to Model Pixel-Embedded Affinity for Homogeneous Instance Segmentation
TL;DR: This paper proposes a pixel-embedded affinity modeling method for homogeneous instance segmentation, which is able to preserve the semantic information of instances and improve the distinguishability of adjacent instances.