Sijie Wang

Sijie Wang

Auto-generated profile, based on publicly available information

Sijie Wang

School of Electrical and Electronic Engineering, Nanyang Technological University, Singapore

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
8 January 2024 in IEEE Transactions on Geoscience and Remote Sensing
Verified
Journal Article
Closed access
RSRui She
Rui She
QKQiyu Kang
Qiyu Kang
SWSijie Wang
Sijie Wang
WTWee Peng Tay
Wee Peng Tay
KZKai Zhao
Kai Zhao
AHAndreas Hartmannsgruber
Andreas Hartmannsgruber
Point cloud registration is a fundamental technique in 3-D computer vision with applications in graphics, autonomous driving, and robotics. However, registration tasks under challenging conditions, under which noise or perturbations are prevalent, can be difficult. We propose a robust point cloud registration approach that leverages graph neural partial differential equations (PDEs) and heat kernel signatures. Our method first uses graph neural PDE modules to extract high-dimensional features from point clouds by aggregating information from the 3-D point neighborhood, thereby enhancing the robustness of the feature representations. Then, we incorporate heat kernel signatures into an attention mechanism to efficiently obtain corresponding keypoints. Finally, a singular value decomposition (SVD) module with learnable weights is used to predict the transformation between two point clouds. Empirical experiments on a 3-D point cloud dataset demonstrate that our approach not only achieves state-of-the-art performance for point cloud registration but also exhibits better robustness to additive noise or 3-D shape perturbations.

3 October 2024 in IEEE Transactions on Intelligent Transportation Systems
Verified
Journal Article
Closed access
SWSijie Wang
Sijie Wang
QKQiyu Kang
Qiyu Kang
RSRui She
Rui She
KZKai Zhao
Kai Zhao
YSYang Song
Yang Song
WTWee Peng Tay
Wee Peng Tay
Place recognition plays a crucial role in the fields of robotics and computer vision, finding applications in areas such as autonomous driving, mapping, and localization. Place recognition identifies a place using query sensor data and a known database. One of the main challenges is to develop a model that can deliver accurate results while being robust to environmental variations. We propose two multi-modal place recognition models, namely PRFusion and PRFusion++. PRFusion utilizes global fusion with manifold metric attention, enabling effective interaction between features without requiring camera-LiDAR extrinsic calibrations. In contrast, PRFusion++ assumes the availability of extrinsic calibrations and leverages pixel-point correspondences to enhance feature learning on local windows. Additionally, both models incorporate neural diffusion layers, which enable reliable operation even in challenging environments. We verify the state-of-the-art performance of both models on three large-scale benchmarks. Notably, they outperform existing models by a substantial margin of $+$ 3.0 AR@1 on the demanding Boreas dataset. Furthermore, we conduct ablation studies to validate the effectiveness of our proposed methods.

1 July 2026 in IEEE Transactions on Pattern Analysis and Machine Intelligence
Verified
Journal Article
Closed access
RSRui She
Rui She
SWSijie Wang
Sijie Wang
QKQiyu Kang
Qiyu Kang
KZKai Zhao
Kai Zhao
TGTianyu Geng
Tianyu Geng
WTWee Peng Tay
Wee Peng Tay
Personalized federated learning (PFL) plays a pivotal role in ensuring efficient privacy preservation and secure collaborative learning. However, PFL faces significant challenges due to data heterogeneity and device diversity. To enhance personalization and robustness in PFL, we propose a novel model called FedNODE, which leverages hierarchical embeddings. FedNODE incorporates personalized, pseudo-generic, and fusion embeddings to facilitate hierarchical information representation. We utilize a hypernetwork based on neural ordinary differential equations (ODEs) within the server to generate backbone parameters for different clients, enabling the creation of personalized embeddings. Additionally, we introduce a pseudo-generic embedding based on a learnable vector to balance personalized and generic information. A neural ODE-based network follows the backbone module for each client, integrating personalized and pseudo-generic embeddings. To validate the efficacy of FedNODE, we conduct extensive evaluations across various classification datasets, encompassing diverse statistically heterogeneous settings and noisy scenarios. The results demonstrate that FedNODE achieves state-of-the-art performance.

21 August 2026 in Applied Energy
Verified
Journal Article
Closed access
JRJunhao Ren
Junhao Ren
HGHonglin Gao
Honglin Gao
SWSijie Wang
Sijie Wang
LZLan Zhao
Lan Zhao
QKQiyu Kang
Qiyu Kang
GXGaoxi Xiao
Gaoxi Xiao