portrait

Wenbin He

Research Scientist at Bosch

Mail LinkedIn GitHub Google Scholar ResearchGate

News

  • 01/2020. Our paper on visual analytics for deep reinforcement learning models has been accepted by PacificVis 2020.

  • 07/2019. Our paper on deep learning based parameter space exploration of ensemble simulations won IEEE VIS 2019 Best Paper Award.

  • 10/2018. Our paper on kernel density estimation of surfaces has been accepted by IEEE TVCG.

  • 10/2018. Our paper on parallel reduction won IEEE LDAV 2018 Best Paper Honorable Mention Award.

  • 10/2018. I'm going to present our paper on parallel reduction in IEEE LDAV 2018.

About

Wenbin He (何文彬) is a research scientist at Bosch. He received his Ph.D. degree from the Department of Computer Science and Engineering at The Ohio State University, advised by Prof. Han-Wei Shen. Before that, he received his B.Eng. degree in Software Engineering from Beijing Institute of Technology in 2012.

Research Interests

Broadly speaking, Wenbin He's research interests include data analysis and visualization, computer graphics, machine learning, and high performance computing. More specifically, his research mainly focuses on large-scale scientific data visualization, ensemble simulation data visualization, uncertainty quantification and visualization, and visual computing with machine learning.

Current Research Projects

  • Machine learning for data analysis and visualization

  • Visual analytics on machine learning models

Work Experience

bosch-logo

Bosch

Research Scientist

Mar 2020 – Present

Human Machine Interaction, Visual Computing

osu-logo

The Ohio State University

Graduate Research Associate

May 2013 – December 2016, May 2017 - December 2019

Worked on exploration and analysis of ensemble datasets with statistical and deep learning models

Graduate Teaching Associate

January 2017 - May 2017

Teaching associate for CSE 5542 Real-Time Rendering and CSE 5544 Introduction to Data Visualization

merl-logo

Mitsubishi Electric Research Laboratories

Summer Intern

May 2019 – July 2019

Worked on developing visual analytics techniques to interpret and diagnose deep reinforcement learning models for robot control tasks, especially focusing on studying transfer failures from simulations to real robots

argonne-logo

Argonne National Laboratory

Research Aide

May 2016 – August 2016

Worked on developing parallel reduction techniques to visualize and analyze extreme-scale datasets on supercomputers

Research Aide

May 2015 – July 2015

Worked on analyzing and visualizing the finite-time Lyapunov exponents and Lagrangian coherent structures of uncertain unsteady flows using statistical models

Publications

  • Wenbin He, Teng-Yok Lee, Jeroen van Baar, Kent Wittenburg, and Han-Wei Shen
    DynamicsExplorer: Visual Analytics for Robot Control Tasks involving Dynamics and LSTM-based Control Policies
    In Proceedings of 2020 IEEE Pacific Visualization Symposium, 2020. (Accepted)
    | DOI | PDF | Video |

  • Wenbin He, Junpeng Wang, Hanqi Guo, Ko-Chih Wang, Han-Wei Shen, Mukund Raj, Youssef S. G. Nashed, and Tom Peterka
    InSituNet: Deep Image Synthesis for Parameter Space Exploration of Ensemble Simulations
    IEEE Transactions on Visualization and Computer Graphics (SciVis 2019), vol. 26, no. 1, pp. 23-33, 2020. Best Paper Award
    | DOI | PDF | Video | GitHub |

  • Wenbin He, Hanqi Guo, Han-Wei Shen, and Tom Peterka
    eFESTA: Ensemble Feature Exploration with Surface Density Estimates
    IEEE Transactions on Visualization and Computer Graphics, vol. 26, no. 4, pp. 1716-1731, 2020.
    | DOI | PDF | Video | GitHub |

  • Hanqi Guo, Wenbin He, Sangmin Seo, Han-Wei Shen, Emil Mihai Constantinescu, Chunhui Liu, and Tom Peterka
    Extreme-Scale Stochastic Particle Tracing for Uncertain Unsteady Flow Visualization and Analysis
    IEEE Transactions on Visualization and Computer Graphics, vol. 25, no. 9, pp. 2710-2724, 2019.
    | DOI | PDF |

  • Wenbin He, Hanqi Guo, Tom Peterka, Sheng Di, Franck Cappello, and Han-Wei Shen
    Parallel Partial Reduction for Large-Scale Data Analysis and Visualization
    In Proceedings of 2018 IEEE Symposium on Large Data Analysis and Visualization, pp. 45-55, 2018. Best Paper Honorable Mention
    | DOI | PDF |

  • Wenbin He, Xiaotong Liu, Han-Wei Shen, Scott M. Collis, and Jonathan J. Helmus
    Range Likelihood Tree: A Compact and Effective Representation for Visual Exploration of Uncertain Data Sets
    In Proceedings of 2017 IEEE Pacific Visualization Symposium, pp. 151–160, 2017.
    | DOI | PDF | Video |

  • Hanqi Guo, Wenbin He, Tom Peterka, Han-Wei Shen, Scott M. Collis, and Jonathan J. Helmus
    Finite-Time Lyapunov Exponents and Lagrangian Coherent Structures in Uncertain Unsteady Flows
    IEEE Transactions on Visualization and Computer Graphics (PacificVis 2016), vol. 22, no. 6, pp. 1672–1682, 2016.
    | DOI | PDF |

  • Wenbin He, Chun-Ming Chen, Xiaotong Liu, and Han-Wei Shen
    A Bayesian Approach for Probabilistic Streamline Computation in Uncertain Flows
    In Proceedings of 2016 IEEE Pacific Visualization Symposium, Visualization Notes, pp. 214–218, 2016.
    | DOI | PDF |

  • Ayan Biswas, David Thompson, Wenbin He, Qi Deng, Chun-Ming Chen, Han-Wei Shen, Raghu Machiraju, and Anand Rangarajan
    An Uncertainty-Driven Approach to Vortex Analysis Using Oracle Consensus and Spatial Proximity
    In Proceedings of 2015 IEEE Pacific Visualization Symposium, pp. 223–230, 2015.
    | DOI | PDF |

Services

Reviewer

  • IEEE Transactions on Visualization and Computer Graphics (TVCG), 2020

  • Journal of Visualization (JOV), 2017

  • IEEE VIS, 2018, 2019

  • EG/VGTC Conference on Visualization (EuroVis), 2018, 2020

  • IEEE Pacific Visualization Symposium (PacificVis), 2020

  • China Visualization and Visual Analytics Conference (ChinaVis), 2018, 2019

© Copyright 2018-2020 Wenbin He - All Rights Reserved