Search Results for author: Jinyu Xie

Found 2 papers, 0 papers with code

Bright Channel Prior Attention for Multispectral Pedestrian Detection

no code implementations22 May 2023 Chenhang Cui, Jinyu Xie, Yechenhao Yang

The method uses the V-channel of the HSV image of the thermal image as an attention map to trigger the unsupervised auto-encoder for visible light images, which gradually emphasizes pedestrian features across layers.

Image Enhancement object-detection +2

H2TF for Hyperspectral Image Denoising: Where Hierarchical Nonlinear Transform Meets Hierarchical Matrix Factorization

no code implementations21 Apr 2023 Jiayi Li, Jinyu Xie, YiSi Luo, XiLe Zhao, Jianli Wang

In the t-SVD, there are two key building blocks: (i) the low-rank enhanced transform and (ii) the accompanying low-rank characterization of transformed frontal slices.

Hyperspectral Image Denoising Image Denoising

Cannot find the paper you are looking for? You can Submit a new open access paper.