He Wang

He Wang is an Associate Professor at University College London

  • HOME
  • Publications
  • Research
  • Funding
  • Group
  • About

Research Interest

My current research interest lies in Computer Graphics, Computer Animation, Computer Vision, Machine Learning and Robotics. It generally falls into, but is not limited to, the following topics:
Deep Learning and Partial Differential Equations Partial Differential Equations (PDEs) are used in an extremely wide range of fields in computer science and engineering, ranging from critical domains such as solid mechanics and fluid dynamics, to entertainments/education such as visual effects, computer graphics, animation and virtual reality. One key fundamental aspect to such research is a well-balanced trade-off between accuracy and speed. We look into how to leverage Deep Learning to help solving PDEs and physical simulations in general. Examples can be found here.
Robustness of Deep Learning Deep learning has been the 'go to' solution nowadays. But its vulnerability to adversarial attacks has a wide implication in many applications fields regarding the robustness of their deep learning models. Why are deep learning models vulnerable to such attacks and how to make them robust is the key question here. Examples can be found here.
Crowd Simulation and Evaluation. Whenever you see massive battle scenes in movies or games these days, it is almost for sure generated by crowd simulation. Beyond entertainment, crowd simulation is also widely used in design, urban planning, logistics, etc. where collective behaviours of humans matter. To simulate crowds, we need to understand people's behaviour patterns ranging from navigation skills to socio-psychological factors. My primary research interest is to learn these patterns from data which involves simulation and evaluation. Technical-wise, I leverage the knowledge from the four fields mentioned. Examples can be found here, here and here.
Motion Planning, Analysis and Synthesis. We humans have amazing motion planning skills which are very difficult to be encoded by current algorithms, especially when it involves interactions with the environment. Think putting on clothes for example. The complexity of this motion planning problem goes up exponentially when the environment just gets mildly complex. My research interest in this area is to find good representations (topological, geometric, etc.) to enable algorithms to find solutions easily. Examples can be found here, here and here.
Scene Analysis. In today's renaissance of Virtual Reality, the urge of understanding the virtual world is as much desired as the the understanding of the real world. My research interest in this area is to leverage geometric and topological knowledge to describe the virtual world so that alrogrithms can be designed for applications such as virtual agents, design, search, etc. Examples can be found here and here.
Other topics. I am also in general intersted in other graphics topics (geometric processing, visualization, physical simulation), machine learning (non-parametric Bayesian models, Deep Learning, Reinforcement Learning), and computer vision(crowd analysis, tracking).

Media Coverage

2022/12, I gave a talk (in Chinese) about robust human activity recognition in a webinar, invited by GAMES Webinar.
2021/10, Our SIGGRAPH 2021 paper, High-order Differentiable Autoencoder for Nonlinear Model Reduction, has been covered by Two Minute Papers in an video, and Edge Analytics Inc in an article.
2021/10, Our ICCV 2021 paper, Unsupervised Image Generation with Infinite Generative Adversarial Networks, has been covered by Computer Graphics and Geometric Computing in an article (in Chinese).
2021/06, Our CVPR 2021 paper, BASAR: BASAR:Black-box Attack on Skeletal Action Recognition, has been covered by BAAIHub in an article and VALSE 2021 (#89 poster) (in Chinese).
2020/04, Dr David McKee, founder and CTO of Slingshot Simulations, interviewed me on Personal Digital Twins: Microscopic Simulation at the Individual Level.
2020/03, TechXplore published an article to cover our paper 'Human-like Planning for Reaching in Cluttered Environments', in International Conference on Robotics and Automation 2020.

Invited Keynotes, Panels and Talks

2025/09, Keynote, Bridging Physics and AI: Learning Pedestrian Dynamics from Video Data, Pedestrian and Evacuation Dynamics 2025, Czech Republic
2025/03, Talk, Bridging Physics and AI: Learning Pedestrian Dynamics from Video Data, University of Bristol, UK
2025/03, Talk, When Physics Meets AI: Modelling High-Density Crowds with Deep Learning, University of Surrey, UK
2024/06, Talk, Physics-based Machine Learning or/and Machine-learning based Physics, Southeast University, China
2023/11, Keynote, AI for Fast Digital Content Creation for Animation and Beyond, BFX, UK
2023/02, Talk, Crowd Behaviour: a spectrum of black-box and white-box perspectives, Bentley, UK
2022/12, Talk, The Universal Vulnerability of Human Action Recognition Classifiers and Potential Solutions, GAMES webinar, online.
2022/06, Talk, Animation for Graphics and Beyond, University College London, UK.
2022/03, Talk, The Universal Vulnerability of Human Action Recognition Classifiers and Potential Solutions, University of Durham, UK.
2022/03, Panel, Personal Digital Twin workshop, The European Commission’s Joint Research Centre.
2022/02, Talk, Machine Learning for Crowd Behaviour Understanding in Public Spaces, RAILS workshop, Shift2Rail.
2020/09, Talk, Machine Learning for Fun and Beyond, Numerical Analysis Group, Ltd, UK.
2018/07, Talk, Computer Animation for Serious Applications, University of Bath, UK.
2018/06, Talk, Virtual Reality for Cost-effective Human Perception Evaluation of Urban Green Space, Newton UK-China Workshop, Xi'an, China.
2017/11, Talk, Crowd:A Living Creature to Simulate and Manage, University of Sheffield, UK.
2016/11, Talk, Non-parametric Clustering on Crowd Analysis, Loughbrough University, UK.
2013/11, Talk, Motion Planning in New Spaces, INRIA, Renees, France.
2013/09, Talk, Manipulating Deformable Objects, University of Bristol, UK.
2012/06, Talk, A New Deforming Coordinate System, Zhejiang University, China.

Professional Service

Journal Editorial

Associate Editor, Computer Graphics Forum, Wiley.
Guest Editors, Sensors, MDPI. (1, 2)

Conference Committee

Programme Chair, ACM SIGGRAPH / Eurographics Symposium on Computer Animation 2024, Montreal, Canada.
Workshop Chair, Parallel CFD International Conference 2024, Bonn, Germany.
Poster Chair, ACM SIGGRAPH Motion, Interaction and Games 2019, Newcastle Upon Tyne, UK.
Publicity Chair, British Machine Vision Conference 2018, Newcastle Upon Tyne, UK.
PC member (Technical Paper Committee, Courses Programme Committee), Siggraph Asia (2025).
PC member, AAAI Conference on Artificial Intelligence (AAAI) (2024, 2023, 2022).
PC member, Eurographics (2024, 2021, 2020).
PC member, Pacific Graphics (2022, 2020, 2019).
PC member, ACM SIGGRAPH / Eurographics Symposium on Computer Animation (2024, 2022).
PC member, International Conference on Computer Animation and Social Agents (2023, 2022, 2021).
PC member, Pedestrian and Evacuation Dynamics (2025).
PC member, Computer Graphics International (2023).
PC member, The ACM Symposium on Virtual Reality Software and Technology (2014).
PC member, The Computational Visual Media Conference (2024, 2023, 2022).
PC member, ACM SIGGRAPH Conference on Motion, Interaction and Games (2023, 2022, 2021, 2020, 2019, 2018, 2017, 2016, 2011).
PC member, International Conference on Robot Systems and Applications (ICRSA) (2020).
PC member, IEEE International Conference on Artificial Intelligence and Virtual Reality (2022, 2021, 2020, 2018).
PC member, International Conference on Virtual Reality and Visualization (2021).

Review Service

Journals

IEEE Transactions on Pattern Analysis and Machine Intelligence
ACM Transactions on Graphics
Journal of the American Statistical Association
IEEE Transactions on Visualization and Computer Graphics
IEEE Transactions on Multimedia
IEEE Transactions on Neural Networks and Learning Systems
IEEE Transactions on Intelligent Transportation Systems
Computer Graphics Forum
IEEE Transactions on Cybernetics
Computer & Graphics
Computer Animation and Virtual World
The Visual Computer
Arts
International Journal of Distributed Sensor Networks
Engineering with Computers
Autonomous Agents and Multi-Agent Systems

Conferences

ACM SIGGRAPH
ACM SIGGRAPH ASIA
The Conference on Computer Vision and Pattern Recognition (CVPR)
The Annual Conference on Neural Information Processing Systems (Neurips)
International Conference on Learning Representation (ICLR)
The International Conference on Robotics and Automation (ICRA)
The International Conference on Computer Vision (ICCV)
The Association for the Advancement of Artificial Intelligence (AAAI)
ACM Multimedia
The IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
Eurographics
IEEE International Conference on Control and Automation
The British Machine Vision Conference (BMVC)
Pacific Graphics
Computer Graphics International
ACM SIGGRAPH Conference on Motion, Interaction and Games (MIG)
International Conference on Graphics Graphics and Application
The ACM Symposium on Virtual Reality Software and Technology (VRST)

Copyright since 2016 He Wang