Yunyang Xu

Yunyang Xu

Auto-generated profile, based on publicly available information

Yunyang Xu

School of Software, Shandong University, Jinan, China

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
23 September 2024 in Neural Networks
Verified
Journal Article
Closed access
ALAo Li
Ao Li
YLYing Li
Ying Li
YXYunyang Xu
Yunyang Xu
XLXuemei Li
Xuemei Li
CZCaiming Zhang
Caiming Zhang

16 January 2025 in Neural Networks
Verified
Journal Article
Closed access
GTGuangpo Tian
Guangpo Tian
YXYunyang Xu
Yunyang Xu
XMXiang Ma
Xiang Ma
XLXuemei Li
Xuemei Li
CZCaiming Zhang
Caiming Zhang

7 November 2023 in Information Sciences
Verified
Journal Article
Closed access
ZLZengyu Lei
Zengyu Lei
CZCaiming Zhang
Caiming Zhang
YXYunyang Xu
Yunyang Xu
XLXuemei Li
Xuemei Li

21 October 2022 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
YXYunyang Xu
Yunyang Xu
XGXifeng Gao
Xifeng Gao
CZCaiming Zhang
Caiming Zhang
JTJianchao Tan
Jianchao Tan
XLXuemei Li
Xuemei Li
Superpixel generation is increasingly an important area for computer vision tasks. While superpixels with highly regular shapes are preferred to make the subsequent processing easier, the accuracy of the superpixel boundaries is also necessary. Previous methods usually depend on a distance function considering both spatial and color coherency regularization on the whole image, which however is hard to balance between shape regularity and boundary adherence, especially when the desired number of superpixels is small. In addition, non-adaptive parameters and insufficient contour information also affect the performance of segmentation. To mitigate these problems, we propose a robust divide-and-conquer superpixel segmentation method, of which the core idea is that we apply a new contour information extraction and a pixel clustering to separate the input image into flat and non-flat regions, where the former targets shape regularity and the latter emphasizes boundary adherence, followed by an efficient hierarchical merging to clean up tiny and dangling superpixels. Our algorithm requires no additional parameter tuning except the desired number of superpixels since our internal parameters are self-adaptive to the image contents. Experimental results demonstrate that for public benchmark datasets, our algorithm consistently generates more regular superpixels with stronger boundary adherence than state-of-the-art methods while maintaining a competitive efficiency. We will release our code upon acceptance.

12 May 2025 in Medical Image Analysis
Verified
Journal Article
Closed access
LFLexin Fang
Lexin Fang
XLXuemei Li
Xuemei Li
YXYunyang Xu
Yunyang Xu
FZFan Zhang
Fan Zhang
CZCaiming Zhang
Caiming Zhang

5 December 2025 in Knowledge-Based Systems
Verified
Journal Article
Closed access
YXYunyang Xu
Yunyang Xu
LFLexin Fang
Lexin Fang
XLXuemei Li
Xuemei Li
CZCaiming Zhang
Caiming Zhang