Lei Cai

Dr. Lei Cai

orcid

Research Focus & Metrics

Academic Career Length

3Years (2024-Present)

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

Representative Publications

View All Publications
15 January 2025 in Image and Vision Computing
Verified
Journal Article
Closed access
WBWang Bin
Wang Bin
YLYu Ying Liang
Yu Ying Liang
LCLei Cai
Lei Cai
HHHuakun Huang
Huakun Huang
HZHuanqiang Zeng
Huanqiang Zeng

23 October 2025 in Neural Networks
Verified
Journal Article
Closed access
FLFang Long
Fang Long
WSWenkang Su
Wenkang Su
ZLZixuan Li
Zixuan Li
LCLei Cai
Lei Cai
MLMingjie Li
Mingjie Li
XCXiaochun Cao
Xiaochun Cao

25 December 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
ZLZixuan Li
Zixuan Li
FLFang Long
Fang Long
WSWenkang Su
Wenkang Su
YWYuan-Gen Wang
Yuan-Gen Wang
QGQingxiao Guan
Qingxiao Guan
LCLei Cai
Lei Cai

18 June 2025 in Applied Sciences
Verified
Journal Article
Open access
PDF file
YSYifan Shi
Yifan Shi
HZHaixin Zeng
Haixin Zeng
XGXinrong Gong
Xinrong Gong
LCLei Cai
Lei Cai
WXWenjie Xiang
Wenjie Xiang
JZJianqing Zhu
Jianqing Zhu
Multi-source heterogeneous data has been widely adopted in developing artificial intelligence systems in recent years. In real-world scenarios, raw multi-source data are generally unlabeled and inherently contain multi-view noise and feature redundancy, leading to extensive research on unsupervised multi-view feature selection. However, existing approaches mainly utilize the local adjacency relationships and the L2,1-norm to guide the feature selection process, which may lead to instability in performance. To address these problems, this paper proposes a Consensus Guided Multi-view Unsupervised Feature Selection with Hybrid Regularization (CGMvFS). Specifically, CGMvFS integrates multiple view-specific basic partitions into a unified consensus matrix, which is constructed to guide the feature selection process by preserving comprehensive pairwise constraints across diverse views. A hybrid regularization strategy incorporating the L2,1-norm and the Frobenius norm is introduced into the feature selection objective function, which not only promotes feature sparsity but also effectively prevents overfitting, thereby improving the stability of the model. Extensive empirical evaluations demonstrate that CGMVFS outperforms state-of-the-art comparison approaches across diverse multi-view datasets.

8 April 2026 in Applied Sciences
Verified
Journal Article
Open access
PDF file
LCLei Cai
Lei Cai
ZJZheng Hui Jie
Zheng Hui Jie
FRFang Ruan
Fang Ruan
FCFeng Chen
Feng Chen
WXWenjie Xiang
Wenjie Xiang
YSYifan Shi
Yifan Shi
Pedestrian gender recognition plays an important role in pedestrian analysis and intelligent video applications, for example, in demographic statistics, soft biometric analysis, and context-aware person retrieval. However, it remains a challenging task owing to viewpoint variations, illumination changes, occlusions, and low image quality in real-world imagery. To address these issues, an effective adaptive decision fusion framework, termed the Decision Fusion Learning Network (DFLN), is proposed in this paper. The key novel aspect of DFLN is that it effectively explores both an appearance-centered view that emphasizes detailed texture and clothing information and a structure-centered view that captures rich contour and structural information for pedestrian gender recognition. To realize DFLN, a Parallel CNN Prediction Probability Learning Module (PCNNM) is first constructed to independently learn modality-specific probabilities from color image and edge maps. Subsequently, a learnable Decision Fusion Module (DFM) is designed to fuse the modality-specific probabilities and explore their complementary merits for realizing accurate pedestrian gender recognition. The DFM can be easily coupled with the PCNNM, forming an end-to-end decision fusion learning framework that simultaneously learns the feature representations and carries out adaptive decision fusion. Experiments on two pedestrian benchmark datasets, named PETA and PA-100K, show that DFLN achieves competitive or superior performance compared with several state-of-the-art pedestrian gender recognition methods. Extensive experimental analysis further confirms the effectiveness of the proposed decision fusion strategy and its favorable generalization ability under domain shift.

1 November 2026 in IEEE Transactions on Circuits and Systems for Video Technology
Verified
Journal Article
Closed access
RDRui Ding
Rui Ding
HZHuanqiang Zeng
Huanqiang Zeng
LCLei Cai
Lei Cai
JCJing Chen
Jing Chen
Junhui HouJunhui Hou
Junhui Hou
KMKai-Kuang Ma
Kai-Kuang Ma