Výsledky vyhledávání - "Mingwen Shao"

Akademický článek

Enhancing Efficient Global Understanding Network With CSWin Transformer for Urban Scene Images Segmentation

Autor: Jie Zhang, Mingwen Shao, Yuanjian Qiao, Xiangyong Cao

Publikováno v: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, Vol 16, Pp 10230-10245 (2023)

The global context is crucial to the semantic segmentation task of remote sensing (RS) urban scene imagery since objects have large size variations, high similarity, and mutual occlusion. However, the existing methods for extracting global context in

Externí odkaz: https://doaj.org/article/9efa5adbf9de4d44b2df77a4ad559c23

Zobrazit plný text záznamu

Akademický článek

A Single-Stage Unsupervised Denoising Low-Illumination Enhancement Network Based on Swin-Transformer

Autor: Qian Zhang, Chengjie Zou, Mingwen Shao, Hong Liang

Publikováno v: IEEE Access, Vol 11, Pp 75696-75706 (2023)

Traditional low-light enhancement methods are often based on paired datasets for training. The training data is difficult to obtain and the resulting model has poor generalization. In unsupervised low-light enhancement networks, because paired data i

Externí odkaz: https://doaj.org/article/e4f61131dfae4cbb9c3927dd355ea7ea

Zobrazit plný text záznamu

Akademický článek

ESAMask: Real-Time Instance Segmentation Fused with Efficient Sparse Attention

Autor: Qian Zhang, Lu Chen, Mingwen Shao, Hong Liang, Jie Ren

Publikováno v: Sensors, Vol 23, Iss 14, p 6446 (2023)

Instance segmentation is a challenging task in computer vision, as it requires distinguishing objects and predicting dense areas. Currently, segmentation models based on complex designs and large parameters have achieved remarkable accuracy. However,

Externí odkaz: https://doaj.org/article/1ea7411141fc46868e56c0bbee264d8b

Zobrazit plný text záznamu

Plný text ve formátu HTML

Vyhledávací nástroje:

Upřesnit hledání