Pei Liu

Pei Liu

Auto-generated profile, based on publicly available information

Pei Liu

The Hong Kong University of Science and Technology (Guangzhou), Guangzhou, China

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
27 October 2025
Verified
Conference Paper
Open access
PLPei Liu
Pei Liu
XLXin Liu
Xin Liu
RYRuoyu Yao
Ruoyu Yao
JLJunming Liu
Junming Liu
SMSiyuan Meng
Siyuan Meng
JMJun Ma
Jun Ma

18 December 2024 in Renewable Energy
Verified
Journal Article
Closed access
YLYiqun Li
Yiqun Li
ZPZiyuan Pu
Ziyuan Pu
PLPei Liu
Pei Liu
TQTao Qian
Tao Qian
QHQinran Hu
Qinran Hu
YWYinhai Wang
Yinhai Wang

25 February 2025 in Journal of Safety Research
Verified
Journal Article
Closed access
JCJunlan Chen
Junlan Chen
PLPei Liu
Pei Liu
SWShuo Wang
Shuo Wang
Nan ZhengNan Zheng
Nan Zheng
XGXiucheng Guo
Xiucheng Guo

16 July 2025 in Communications in Transportation Research
Verified
Journal Article
Open access
YZYifan Zhuang
Yifan Zhuang
PLPei Liu
Pei Liu
HYHao Yang
Hao Yang
KZKai Zhang
Kai Zhang
YWYinhai Wang
Yinhai Wang
ZPZiyuan Pu
Ziyuan Pu

29 December 2025
Verified
Book Chapter
Open access
PDF file
NZNanfang Zheng
Nanfang Zheng
PLPei Liu
Pei Liu
YJYufei Ji
Yufei Ji
YLYiqun Li
Yiqun Li
YZYifan Zhuang
Yifan Zhuang
Ziyuan PuZiyuan Pu
Ziyuan Pu
Numerous approaches for ego-vehicle 3D perception tasks have arisen as a result of the advancement of AI-assisted driving, but there has been little research on roadside perception. The roadside perspective is worthwhile to develop since it offers a global picture and a wider sensory range. While cameras offer semantic information, LiDAR offers exact 3-D spatial data. In 3D detection, these two modalities work well together. Nevertheless, since both the extraction and fusion process is not sufficiently accurate, additional camera data fails to enhance accuracy in certain tests. Kolmogorov-Arnold Networks (KANs), which are more appropriate for high-dimensional, complicated data, have recently been suggested as alternatives to MLPs. Kaninfradet3D, which improves the feature extraction along with fusion modules, is proposed in this study. KAN Layers were used to enhance the encoder and fuser modules of the model. Cross-attention was used to improve feature fusion, and visually comparisons showed that camera features had better merged. This solved the issue of unusually concentrated camera characteristics, which had a detrimental influence on fusion. Our method surpasses the benchmark by +1.40 mAP in the infrastructure portion of the TUMTraf V2X Cooperative Perception Dataset and by +9.87 mAP and +10.64 mAP in both perspectives of the TUMTraf Intersection Dataset. The results highlight the potential of employing KANs in roadside perception challenges by demonstrating that Kaninfradet3D can successfully fuse features.