Xusheng Li

Xusheng Li

Auto-generated profile, based on publicly available information

Xusheng Li

Chongqing University, Shapingba, Chongqing, China

Research Focus & Metrics

Academic Career Length

7Years (2020-Present)

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

Representative Publications

View All Publications
21 March 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
XLXusheng Li
Xusheng Li
CWChengliang Wang
Chengliang Wang
ZZZhuo Zeng
Zhuo Zeng

17 October 2022 in IET Image Processing
Verified
Journal Article
Open access
GLGuoqi Liu
Guoqi Liu
LBLu Bai
Lu Bai
JLJunlin Li
Junlin Li
XLXusheng Li
Xusheng Li
LRLinyuan Ru
Linyuan Ru
BCBaofang Chang
Baofang Chang
Convolution neural networks have been widely used in the field of computer vision, which effectively solve practical problems. However, the loss function with fixed parameters will affect the training efficiency and even lead to poor prediction accuracy. In particular, when there is a class imbalance in the data, the final result tends to favor the large‐class. In detection and recognition problems, the large‐class will dominate due to its quantitative advantage, and the features of few‐class can be not fully learned. In order to learn few‐class, batch nuclear‐norm maximization is introduced to the deep neural networks, and the mechanism of the adaptive composite loss function is established to increase the diversity of the network and thus improve the accuracy of prediction. The proposed loss function is added to the crowd counting, and verified on ShanghaiTech and UCF_CC_50 datasets. Experimental results show that the proposed loss function improves the prediction accuracy and convergence speed of deep neural networks.

31 March 2020 in IEEE Access
Verified
Journal Article
Open access
GLGuoqi Liu
Guoqi Liu
XLXusheng Li
Xusheng Li
BCBaofang Chang
Baofang Chang
YDYifei Dong
Yifei Dong
Superpixel is an essential tool for computer vision. In practice, classic superpixel algorithms do not exhibit good boundary adherence with fewer superpixels, which will greatly hamper further analysis. To remedy the defect, a superpixel boundary optimization framework is proposed in this paper. There are three steps in the framework. Firstly, based on the proposed information measure function, the undersegmented superpixels generated by classic superpixel algorithms are screened out. Secondly, with the two invariant centroids method, these under-segmented superpixels are re-segmented to improve the accuracy in boundary adherence. Finally, smaller superpixels are merged to maintain the same number with initial superpixels. Quantitative evaluations on the BSDS500 exhibit that the performance of the classic superpixel algorithms is improved by employing the framework, especially on the condition of fewer superpixels.

18 December 2025 in Information Sciences
Verified
Journal Article
Closed access
XLXusheng Li
Xusheng Li
CWChengliang Wang
Chengliang Wang
SWShumao Wang
Shumao Wang
JLJi Liu
Ji Liu
YLYonggang Luo
Yonggang Luo
JCJianbin Chen
Jianbin Chen