Biography

Siheng Chen 陈思衡 is a tenure-track associate professor of Shanghai Jiao Tong University and co-PI at Shanghai AI laboratory. He received his doctorate from Carnegie Mellon University. His research interests include graph machine learning and collective intelligence. Dr. Chen’s work on sampling theory of graph data received the 2018 IEEE Signal Processing Society Young Author Best Paper Award. His co-authored paper on structural health monitoring received ASME SHM/NDE 2020 Best Journal Paper Runner-Up Award and another paper on 3D point cloud processing received the Best Student Paper Award at 2018 IEEE Global Conference on Signal and Information Processing. His technique on joint perception and prediction was applied on all the UBER’s autonomous cars. Dr. Chen also contributed to the project of scene-aware interaction, winning MERL President’s Award. He also serves as the associate editor of IEEE Transactions on Signal and Information Processing over Networks.

Join us:

We are actively hiring! We are looking for motivated postdocs, interns, PhD/master/undergraduate students. If you are interested in working with us, please feel free to drop me an email!

Interests
  • Graph machine learning
  • Multi-agent learning
  • Collaborative perception
  • Federated learning
Education

  • Ph.D in Electrical and Computer Engineering

    Carnegie Mellon University

  • Master of Science in Machine Learning

    Carnegie Mellon University

  • Bachelor of Science in Electronic Engineering

    Beijing Institute of Technology

Recent News

All news»

[Sep. 2023] Two papers are accepted by NeurIPS 2023

[Jul. 2023] Three papers are accepted by the International Conference on Computer Vision (ICCV)

[Jun. 2023] Collaborative Uncertainty Benefits Multi-Agent Multi-Modal Trajectory Forecasting is accepted by Transactions on Pattern Analysis and Machine Intelligence

[Apr. 2023] Two papers are accepted by The International Conference on Machine Learning (ICML)

[Apr. 2023] CoCa3D is reported by 机器之心

[Mar. 2023] Four papers are accepted by The Conference on Computer Vision and Pattern Recognition (CVPR)

[Jan. 2023] Robust collaborative 3D object detection in presence of pose errors is accepted to 2023 IEEE International Conference on Robotics and Automation (ICRA)

[Jan. 2023] Aerial Monocular 3D Object Detection is accepted to IEEE Robotics and Automation Letters

[Dec. 2022] Discriminative Radial Domain Adaptation is accepted to IEEE Transactions on Image Processing

[Nov. 2022] One paper is accepted to IEEE Transactions on Knowledge and Data Engineering

Recent Publications

Quickly discover relevant content by filtering publications.
Yifan Lu, Quanhao Li, Baoan Liu, Mehrdad Dianat, Chen Feng, Siheng Chen, Yanfeng Wang (2023). Robust Collaborative 3D Object Detection in Presence of Pose Errors. arXiv preprint arXiv:2211.07214.

Cite

Yue Hu, Shaoheng Fang, Weidi Xie, Siheng Chen (2023). Aerial monocular 3d object detection. arXiv preprint arXiv:2208.03974.

Cite

Zenan Huang, Jun Wen, Siheng Chen, Linchao Zhu, Nenggan Zheng (2023). Discriminative Radial Domain Adaptation. IEEE Transactions on Image Processing.

Cite DOI

Rui Ye, Mingkai Xu, Jianyu Wang, Chenxin Xu, Siheng Chen, Yanfeng Wang (2023). FedDisco: Federated Learning with Discrepancy-Aware Collaboration. CoRR.

Cite DOI URL

Ming Jin, Yu Zheng, Yuan-Fang Li, Siheng Chen, Bin Yang, Shirui Pan (2022). Multivariate Time Series Forecasting with Dynamic Graph Neural ODEs. IEEE Transactions on Knowledge and Data Engineering.

Cite

Yiqi Zhong, Zhenyang Ni, Siheng Chen, Ulrich Neumann (2022). Aware of the history: Trajectory forecasting with the local behavior data. European Conference on Computer Vision (ECCV).

Cite

See all publications

Projects

*
All Deep Learning Other
CoAlign: Robust Collaborative 3D Object Detection in Presence of Pose Errors
[ ICRA 2023 ]
CoAlign, a novel hybrid collaboration framework that is robust to unknown pose errors.
Yifan Lu, Quanhao Li, Baoan Liu, Mehrdad Dianati, Chen Feng, Siheng Chen, Yanfeng Wang
PDF Code
CoAlign: Robust Collaborative 3D Object Detection in Presence of Pose Errors
GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning
[ CVPR 2022 ]
GroupNet, a multiscale hypergraph neural network, which is novel in terms of both interaction capturing and representation learning.
Chenxin Xu, Maosen Li, Zhenyang Ni, Ya Zhang, Siheng Chen
PDF Code Talk Zhihu
GroupNet: Multiscale Hypergraph Neural Networks for Trajectory Prediction with Relational Reasoning
Remember Intentions: Retrospective-Memory-based Trajectory Prediction
[ CVPR 2022 ]
MemoNet, an instance-based approach that predicts the movement intentions of agents by looking for similar scenarios in the training data.
Chenxin Xu, Weibo Mao, Wenjun Zhang, Siheng Chen
PDF Code Zhihu
Remember Intentions: Retrospective-Memory-based Trajectory Prediction

Contact

  • sihengc@sjtu.edu.cn
  • 800 Dongchuan Road, Shanghai, 200240
  • Enter SEIEE Building 5 and take the stairs to Office 303A on Floor 3