Siheng Chen

Siheng Chen is an associate professor at Shanghai Jiao Tong University. Before that, he was a research scientist at Mitsubishi Electric Research Laboratories (MERL) and an autonomy engineer at Uber Advanced Technologies Group, working on the perception and prediction systems of self-driving cars. Before joining an industry, he was a postdoctoral research associate at Carnegie Mellon University. He received the doctorate in Electrical and Computer Engineering from Carnegie Mellon University in 2016, where he also received two masters degrees in Electrical and Computer Engineering and Machine Learning, respectively. He received his bachelor's degree in Electronics Engineering in 2011 from Beijing Institute of Technology, China. His paper "Discrete signal processing on graphs: Sampling theory" won the 2018 IEEE Signal Processing Society Young Author Best Paper Award. His coauthored paper received the Best Student Paper Award at IEEE GlobalSIP 2018.

His research mainly focuses on graph-structured data science, whose goal is to develeop theories and algorithms to analyze large-scale data associated with complex and irregular structures. His research is conducted from three aspects: theory (graph signal processing), algorithms (graph neural networks), and applications (autonomous systems, human behavior analysis, 3D point cloud processing, and smart infrastructure). Please see more information in his CV and Google Scholar page.

My research interests broadly include signal processing, machine learning and data mining. My current research mainly focuses on data science with graphs, whose goal is to develeop theories and algorithms to analyze large-scale data associated with complex and irregular structures.

Graph Signal Processing

Graph signal processing is a theoretical framework that generalizes classical discrete signal processing from regular domains, such as lines and rectangular lattices, to arbitrary, irregular domains commonly represented by graphs. Different from network science, signal processing on graphs focuses on the interplay between the graph structure and the corresponding signals. The goal of this research is to build a theoretical foundation from the perspective of signal processing to handle practical data analysis tasks.

The current work focuses on understanding and formulating such a framework for signal sampling and recovery on graphs.

Graph Neural Networks

The input data fed into deep learning systems is usually associated with regular structures. For example, speech signals and natural language have an underlying 1D sequential structure; images have an underlying 2D lattice structure. To take advantage of this regularly structured data, deep learning uses a series of basic operations defined for the regular domain, such as traditional convolution and uniform pooling; however, not all data is contained in regular structures. In urban science, traffic information is associated with road networks; in neuroscience, brain activity is associated with brain connectivity networks; in social sciences, users profile information is associated with social networks. New operations are needed to activate deep learning for irregular data. We design novel graph-based differential operators that handle data associated with irregular structures and also allow end-to-end training. The applications include 3D-skeleton-based action understadning, 3D point cloud learning and social network analysis.

3D Point Cloud Processing and Learning

Over the past few decades, signal processing and machine learning tools have been widely generalized from 1D time series to 2D images because of the growth of imaging technologies and huge public demands. Recently, we are experiencing a transition from 2D images to 3D data. Twenty years from now, autonomous driving and virtual/augmented reality might be a part of everyone’s daily life. The success of both fields heavily relies on a similar, but new data structure, 3D point clouds. 3D points are irregularly sampled from the surfaces of objects; each point precisely records a position on a surface. The traditional data structures, such as 1D time series and 2D image, naturally have compact discrete representations on a regular grid; however, 3D point clouds are sparsely and irregularly scattered in a 3D continuous space, which cannot be handled by traditional signal processing and machine learning tools. To solve this irregular-data-structure issue, we can introduce a 3D spatial graph to capture the overall shape of scattered 3D points. This 3D spatial graph, which is constructed by connecting neighboring 3D points, can be considered as a warped version of a regular grid. We then can apply techniques developed from data science with graphs to solve many challenges on 3D point cloud, such as 3D data compression, 3D object detection and 3D instance segmentation.

Smart Infrastructure

We explore an indirect measurement approach for bridge structural health monitoring that collects sensed information from the dynamic responses of many vehicles travelling over a bridge and then makes extensive use of advanced signal processing techniques to determine information about the state of the bridge.

Journal

  1. S. Chen, Y. C. Eldar, and L. Zhao,“Graph unrolling networks: Interpretable neural networks for graph signal denoising”, IEEE Transactions on Signal Processing, submitted
  2. V. Ioannidis, S. Chen, and G. Giannakis,“Efficient and stable graph scattering transforms via pruning”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
  3. M. Li, S. Chen, X. Chen, Y. Zhang, Y. Wang, and Q. Tian,“Symbiotic graph neural networks for 3D skeleton-based human action recognition and motion prediction”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
  4. X. Chen, S. Chen, H. Zheng, J. Yao, K. Cui, Y. Zhang, and I. W. Tsang,“Node attribute generation on graphs”, IEEE Transactions on Pattern Analysis and Machine Intelligence, 2020
  5. S. Chen, B. Liu, C. Feng, C. Vallespi-Gonzalez, and C. Wellington, “3D point cloud processing and learning for autonomous driving””, IEEE Signal Processing Magazine, Special Issue on Autonomous Driving, 2020.
  6. J-Z. Peng, S. Chen, N. Aubry, Z. Chen, W-T. Wu, “Time-variant prediction of flow over an airfoil using deep neural network ”, Physics of Fluids 32 (12), 2020
  7. J-Z. Peng, S. Chen, N. Aubry, Z. Chen, W-T. Wu, “Unsteady reduced-order model of flow over cylinders based on convolutional and deconvolutional neural network structure”, Physics of Fluids 32 (12), 2020
  8. J. Liu,S. Chen, M. Berges, J. Bielak, J. H Garrett, J. Kovačević, and H. Y. Noh, “Damage diagnosis algorithms for indirect structural health monitoring of bridges”, Mechanical Systems and Signal Processing, 2019
  9. J. Liu,S. Chen, George Lederman, David Kramer, H. Y. Noh, J. Bielak, J. H Garrett, J.~Kova\v{c}evi\’c, and M. Berges, “Dynamic responses of two passenger trains with the corresponding GPS positions, environmental conditions and weekly maintenance schedules in Pittsburgh’s light rail network”, Nature Scientific Data, 2019
  10. S. Chen, C. Duan, Y. Yang, D. Li, C. Feng and D. Tian, “FoldingNet++: Deep unsupervised learning of 3D point clouds via graph topology inference and filtering”, IEEE Trans. Image Process., 2020.
  11. S. Chen, D. Tian, C. Feng, A. Vetro and J. Kovačević, “Fast resampling of 3D point clouds via graphs”, IEEE Trans. Signal Process., 2018.
  12. Y. Yang, S. Chen, M. Maddah-Ali, P. Grover, S. Kar and J. Kovačević, “Fast temporal path localization on graphs via multiscale Viterbi decoding”, IEEE Trans. Signal Process., 2018.
  13. S. Chen, Y. Yang, S. Zong, A. Singh, and J. Kovačević, “Detecting localized categorical attributes on graphs”, IEEE Trans. Signal Process., 2017.
  14. G. Lederman, S. Chen, J. H. Garrett, J. Kovačević, H. Y. Noh, and J. Bielak, “ A data fusion approach for track monitoring from multiple in-service trains”. J. Mech. Syst. Signal Process., 2017.
  15. G. Lederman, S. Chen, J. H. Garrett, J. Kovačević, H. Y. Noh, and J. Bielak, “ Track monitoring from the dynamic response of a passing train: a sparse approach”, J. Mech. Syst. Signal Process., 2016.
  16. G. Lederman, S. Chen, J. H. Garrett, J. Kovačević, H. Y. Noh, and J. Bielak, “ Rail-monitoring from the dymanic response of an operational train”, J. Mech. Syst. Signal Process., 2016.
  17. S. Chen, R. Varma, A. Singh, and J. Kovačević, “Signal recovery on graphs: Fundamental limits of sampling strategies”, IEEE Trans. Signal and Inform. Process. over Networks, sp. iss. Inference and Learning over Networks, 2016.
  18. S. Chen, R. Varma, A. Sandryhaila, and J. Kovačević, “Discrete signal processing on graphs: Sampling Theory”, IEEE Trans. Signal Process., 2015.
  19. S. Chen, A. Sandryhaila, J. M. F. Moura, and J. Kovačević, “Signal recovery on graphs: Variation minimization”, IEEE Trans. Signal Process., 2015.
  20. S. Chen, F. Cerda, P. Rizzo, J. Bielak, J. H. Garrett, and J. Kovačević, “Semi-supervised multiresolution classification using adaptive graph filtering with application to indirect bridge structural health monitoring”, IEEE Trans. Signal Process., 2014.
  21. F. Cerda, S. Chen, J. Bielak, J. H. Garrett, P. Rizzo, and J. Kovačević, “Indirect structural health monitoring of a simplified laboratory-scale bridge model ”, Int. J. Smart Struct. Syst., sp. iss. Challenge on bridge health monitoring utilizing vehicle-induced vibrations, 2014.

Conference

  1. S. Chen, Y. C. Eldar, “Graph signal denoising via unrolling networks“, In Proc. IEEE Int. Conf. Acoust., Speech Signal Process, 2021. 
  2. S. Chen, Y. C. Eldar, “Time-varing graph signal inpainting via unrolling networks“, In Proc. IEEE Int. Conf. Acoust., Speech Signal Process, 2021.  
  3. C. Xu, S. Chen*, M. Li, Y. Zhang*, “Invariant Teacher and Equivariant Student for Unsupervised 3D Human Pose Estimation“, AAAI 2021, accepted.
  4. C Pan, S. Chen, A Ortega, “Spatio-temporal graph scattering transform“, ICLR 2021.
  5. M Li, S Chen, Y Zhang, IW Tsang, “Graph cross networks with vertex infomax pooling“, Neural Information Processing Systems (NeurIPS) 2020.
  6. P. Wu, S. Chen, and D. Metaxas,”MotionNet: Joint perception and motion prediction for autonomous driving based on BEV maps”, In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR). 2020.
  7. M. Li, S. Chen, Y. Zhang, and Y. Wang,“Dynamic multiscale graph neural networks for category-agnostic 3D skeleton-based motion prediction”, In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2020, Oral.
  8. Y. Hu, S. Chen,Y. Zhang, and Y. Wang,“Collaborative motion prediction via neural message passing”, In Proc. IEEE Conf. on Computer Vision and Pattern Recognition (CVPR) 2020, Oral.
  9. J. Liu, B. Chen, S. Chen, M. Berges, J. Bielak, H. Noh,“Damage-sensitive and domain-invariant feature extraction for vehicle-vibration-based bridge health monitoring”, In Proc. IEEE Int. Conf. Acoust., Speech Signal Process. 2020.
  10. S. Chen, N. Zhang, and H. Sun,“Collaborative localization based on traffic landmarks for autonomous driving”, International Symposium on Circuits and Systems (ISCAS), 2020.
  11. V. Ioannidis, S. Chen, and G. Giannakis,“Pruned graph scattering transforms”, International Conference on Learning Representations (ICLR), 2020.
  12. S. Chen, S. Niu, T. Lan and B. Liu, “PCT: Large-scale 3D point cloud representations via graph inception networks with applications to autonomous driving”, In Proc. IEEE Int. Conf. on Image Process., Taipei, Taiwan, Sep. 2019.
  13. M. Li, S. Chen, X. Chen, Y. Zhang, Y. Wang and Q. Tian, “Actional-structural graph convolutional networks for 3D skeleton-based action recognition”, In Proc. IEEE Computer Vision and Pattern Recognition, Long Beach, CA, June 2019. [code]
  14. Y. Hu, S. Chen, X. Chen, Y. Zhang and X. Gu “Neural message passing for visual relationship detection”, ICML Workshop (Learning and Reasoning with Graph-Structured Representations), June. 2019.[code]
  15. C. Duan, S. Chen and J. Kovačević, “3D point cloud denoising via deep-neural-network based local surface estimation”, In Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Brighton, UK, May 2019. [code]
  16. C. Duan, S. Chen and J. Kovačević, “Weighted multiple-projection: 3D point cloud denoising with tangent planes”, In Proc. IEEE Glob. Conf. Signal Information Process., Anaheim, California, Nov. 2018. [code]
  17. S. Niu*, S. Chen*, H. Guo, C. Targonski, M. C. Smith and J. Kovačević, “Generalized value iteration networks: Life beyond lattices”, In Proc. AAAI., New Orleans, Feb. 2018. [code]
  18. S. Chen, D. Tian, C. Feng, A. Vetro and J. Kovačević, “Contour-enhanced resampling of 3d point clouds via graphs”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., New Orleans, 2017.
  19. Y. Yang, S. Chen, M. Ali Maddah-Ali, P. Grover, S. Kar and J. Kovačević, “Fast path localization on graphs via multiscale Viterbi decoding”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., New Orleans, 2017.
  20. R. Varma, S. Chen and J. Kovačević, “Graph topology recovery for regular and irregular graphs”, In IEEE CAMSAP, Curacao, Netherlands Antilles, Dec. 2017.
  21. S. Chen, Y. Yang, A. Singh, and J. Kovačević, “Signal detection on graphs: Bernoulli noise model”, In Proc. IEEE Glob. Conf. Signal Information Process., Washington, DC, Dec. 2016.
  22. S. Chen, Y. Yang, C. Faloutsos, and J. Kovačević, “Monitoring Manhattan’s traffic at 5 intersections?”, In Proc. IEEE Glob. Conf. Signal Information Process., Washington, DC, Dec. 2016.
  23. S. Chen, R. Varma, A. Singh and J. Kovačević, “A statistical perspective of sampling scores for linear regression”, Proc. IEEE International Symposium on Information Theory, Barcelona, Spain, 2016.
  24. S. Chen, R. Varma, A. Singh and J. Kovačević, “Representations of piecewise smooth signals on graphs”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Shanghai, China, 2016.
  25. R. Varma, S. Chen and J. Kovačević, “Spectrum-blind signal recovery on graphs”, IEEE CAMSAP, Cancun, Mexico, 2015.
  26. T. Ji, S. Chen, R. Varma and J. Kovačević, “Efficient route planning of autonomous vehicles based on graph signal recovery”, Allerton 2015.
  27. S. Chen, R. Varma, A. Singh and J. Kovačević, “Signal recovery on graphs: Random versus experimentally designed sampling”, SampTA 2015, Washington, D.C., May, 2015.
  28. S. Chen, A. Sandryhaila, and J. Kovačević, “Sampling theory for graph signals”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Brisbane,Australia, April, 2015.
  29. S. Chen, A. Sandryhaila, and J. Kovačević, “Distributed algorithm for graph signal inpainting”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Brisbane,Australia, April, 2015.
  30. S. Bittner, S. Chen, and J. Kovačević, “ Fast algorithm for neural network reconstruction”, Proc. IEEE Int. Symposium on Biomedical Imaging., Brooklyn, NY, April, 2015.
  31. S. Chen, A. Sandryhaila, J. M. F. Moura, and J. Kovačević, “Signal denoising on graphs via graph filtering,”, Proc. IEEE Glob. Conf. Signal Information Process., Atlanta, GA, Dec, 2014
  32. S. Chen, A. Sandryhaila, G. Lederman, Z. Wang, J. M. F. Moura, P. Rizzo, J. Bielak, J. H. Garrett, and J. Kovačević, “Signal inpainting on graphs via total variation minimization”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Florence, Italy, May 2014.
  33. G. Lederman, Z. Wang, S. Chen, T. Tang, F. Cerda, J. Bielak, J. H. Garrett, J. Kovačević, H. Noh, and P. Rizzo, “Damage quantification and localization algorithms for indirect SHM of bridges”, Proc. Int. Conf. Bridge Maint., Safety Manag., Shanghai, China, July 2014.
  34. S. Chen, A. Sandryhaila, J. M. F. Moura, and J. Kovačević, “Adaptive graph filtering: Multiresolution classification on graphs”, Proc. IEEE Glob. Conf. Signal Information Process., Austin, TX, Dec. 2013.
  35. S. Chen, F. Cerda, J. Guo, J. B. Harley, Q. Shi, P. Rizzo, J. Bielak, J. H. Garrett and J. Kovačević, “Multiresolution classification with semi-supervised learning for indirect bridge structure health monitoring”, Proc. IEEE Int. Conf. Acoust., Speech Signal Process., Vancouver, Canada, May 2013.
  36. Z. Wang, S. Chen, G. Lederman, F. Cerda, J. Bielak, J. H. Garrett, P. Rizzo and J. Kovačević, “Comparison of sparse representation and Fourier discriminant methods: Damage location classification in indirect lab-scale bridge structural health monitoring”, Proc. Structures Congr., Pittsburgh, PA, May 2013.
  37. F. Cerda, J. H. Garrett, J. Bielak, P. Rizzo, J. A. Barrera, Z. Zhang, S. Chen, M. T. McCann, and J. Kovačević, “Indirect structural health monitoring in bridges: Scale experiments”, Proc. Int. Conf. Bridge Maint., Safety Manag., Lago di Como, Italy, July 2012.

Thesis

  1. S. Chen, “Data science with graphs: A signal processing perspective”, Ph.D Thesis in ECE, 2016.
  2. S. Chen, “Adaptive sampling for urban traffic monitoring”, Master Thesis in MLD, 2016.

Preprint

  1. S. Chen, S. Niu, L. Akoglu, J. Kovačević and C. Faloutsos, “Fast, Warped Graph Embedding: Unifying Framework and One-Click Algorithm ”. [code]
  2. S. Chen, Y. Yang, J. M. F. Moura, and J. Kovačević, “Localization, decomposition and dictionary learning of piecewise-constant signals on graphs”.
  3. S. Chen, R. Varma, A. Singh, and J. Kovačević, “Signal representations on graphs: Tools and applications”.
  4. S. Chen, Q. Gao, C. Li, J. Kovačević and C. Faloutsos “ZoomRank: Bridging PageRank and HITS”.


303A, Cooperative Medianet Innovation Center, Building 5

School of Electronic Information and Electrical Engineering, Shanghai Jiao Tong University

800 Dongchuan Road, Minhang District, Shanghai 200240, China


Email: sihengc[AT]sjtu[DOT]edu[DOT]cn

 

 

MediaBrain陈思衡老师 招【2022与2023级】直博/直硕生啦! 

陈老师年初刚刚回国,是未来媒体网络协同创新中心的长聘轨副教授,2019年国家重大人才工程青年项目入选者!
陈老师在CMU获得博士学位,博士后完成后,在Uber Advanced Technologies Group、三菱电机实验室MERL担任Research Scientist,至今在TPAMI、TIP、NeurIPS(oral)、CVPR (oral)、AAAI (oral)、ICLR上发表了50余篇论文,Google Scholar引用2000余次,获得过IEEE信号处理协会最佳年轻作者论文奖!学界+业界影响力Max!

陈老师与海外各高校包括(CMU、Oxford、…)以及国内外各企业(Uber、滴滴、…)都有着很强的connection,可以推荐你到世界顶尖的平台学习交流!

如果你数学与编程功底扎实,踏实好学,对计算机视觉与机器学习有一定的了解;
如果你想做【一流的学术】工作、在国际顶级期刊和会议发表【高水平 & 有学术影响力】的论文;
如果你对图信号处理、图神经网络、无人系统等领域感兴趣,想要探索计算机视觉、机器学习和自动驾驶的问题;
如果对科研有热情,希望能够加入一个积极向上、开放包容、有激情有理想地探索科学的、顶级的科研氛围与团队;
那么欢迎你加入我们!

加入我们,你会接受系统的科研工作练习,陈老师与学长学姐带你快速适应科研节奏,参与到我们正在开展的工作中,有机会在一年做出优质的科研工作并发表顶会论文!

请有意向的同学发送简历至:sihengc[AT]sjtu[DOT]edu[DOT]cn

也欢迎朋友们帮忙转发,期待大家共同进步!