Výsledky vyhledávání - "Liu Weixiang"

Akademický článek

DESIGN AND ANALYSIS OF INERTIA VIBRATOR WITH ADJUSTABLE ECCENTRIC MASS

Autor: DUAN XinHao, QU PengZhe, LIU WeiXiang, ZHANG ChunHua, TAO Ying, LI PengYu

Publikováno v: Jixie qiangdu, Vol 40, Pp 160-164 (2018)

In order to make the exciting force adjustment of inertia vibrator during operation possible,and to meet the demand of particular vibrating machines,a kind of inertia vibrator is designed,it’s eccentric mass can be adjusted by pressure air. The des

Externí odkaz: https://doaj.org/article/1bdc1dde710c4f98906cd3f1f12a921a

Zobrazit plný text záznamu

Report

Perception Reinforcement Using Auxiliary Learning Feature Fusion: A Modified Yolov8 for Head Detection

Autor: Chen, Jiezhou, Wang, Guankun, Liu, Weixiang, Zhong, Xiaopin, Tian, Yibin, Wu, ZongZe

Head detection provides distribution information of pedestrian, which is crucial for scene statistical analysis, traffic management, and risk assessment and early warning. However, scene complexity and large-scale variation in the real world make acc

Externí odkaz: http://arxiv.org/abs/2310.09492

Zobrazit plný text záznamu

Report

Edge-aware Plug-and-play Scheme for Semantic Segmentation

Autor: Yi, Jianye, Zhong, Xiaopin, Liu, Weixiang, Zhu, Wenxuan, Wu, Zongze, Deng, Yuanlong

Semantic segmentation is a classic and fundamental computer vision problem dedicated to assigning each pixel with its corresponding class. Some recent methods introduce edge-based information for improving the segmentation performance. However these

Externí odkaz: http://arxiv.org/abs/2303.10307

Zobrazit plný text záznamu

Report

Mask Focal Loss: A unifying framework for dense crowd counting with canonical object detection networks

Autor: Zhong, Xiaopin, Wang, Guankun, Liu, Weixiang, Wu, Zongze, Deng, Yuanlong

As a fundamental computer vision task, crowd counting plays an important role in public safety. Currently, deep learning based head detection is a promising method for crowd counting. However, the highly concerned object detection networks cannot be

Externí odkaz: http://arxiv.org/abs/2212.11542

Zobrazit plný text záznamu

Report

Harmonizing output imbalance for defect segmentation on extremely-imbalanced photovoltaic module cells images

Autor: Yi, Jianye, Zhong, Xiaopin, Liu, Weixiang, Wu, Zongze, Deng, Yuanlong, Wu, Zhengguang

The continuous development of the photovoltaic (PV) industry has raised high requirements for the quality of monocrystalline of PV module cells. When learning to segment defect regions in PV module cell images, Tiny Hidden Cracks (THC) lead to extrem

Externí odkaz: http://arxiv.org/abs/2211.05295

Zobrazit plný text záznamu