He Wang

He Wang is an Associate Professor at University College London

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

Abstract

Action recognition has been heavily employed in many applications such as autonomous vehicles, surveillance, etc, where its robustness is a primary concern. With the recent uprising of adversarial attack which automatically and strategically look to computing data pertubation in order to fool well-trained classifiers, this project looks into the vulnerability of existing classifiers against adversarial attack and how to improve their resistence and robustness.

Resources

  1. Yunfeng Diao, Baiqi Wu, Ruixuan Zhang, Ajian Liu, Xingxing Wei, Meng Wang, He Wang.  TASAR: Transfer-based Attack on Skeletal Action Recognition.   The International Conference on Learning Representations (ICLR). 2025 Conference
     Paper   Code   BibTex
    @inproceedings{diao2025tasar,
      author = {Yunfeng Diao and Baiqi Wu and Ruixuan Zhang and Ajian Liu and Xingxing Wei and Meng Wang and He Wang},
      title = {TASAR: Transfer-based Attack on Skeletal Action Recognition},
      booktitle = {The International Conference on Learning Representations (ICLR)},
      year = {2025}
    }

  2. Yunfeng Diao*, He Wang*, Tianjia Shao, Yongliang Yang, Kun Zhou, David Hogg, Meng Wang.  Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack.   Pattern Recognition. 2024 Journal
     Paper   BibTex
    @article{diao2022understanding,
      author = {Yunfeng Diao* and He Wang* and Tianjia Shao and Yongliang Yang and Kun Zhou and David Hogg and Meng Wang},
      title = {Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack},
      journal = {Pattern Recognition},
      pages = {110564},
      year = {2024}
    }

  3. He Wang, Yunfeng Diao.  Post-train Black-box Defense via Bayesian Boundary Correction.   arxiv. 2024 Preprint
     Paper   BibTex
    @misc{wang2023defending,
      author = {He Wang and Yunfeng Diao},
      title = {Post-train Black-box Defense via Bayesian Boundary Correction},
      series = {arxiv},
      year = {2024}
    }

  4. Zhengzhi Lu, He Wang, Ziyi Chang, Guoan Yang, Hubert PH Shum.  Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient.   The Internaitional Conference on Computer Vision (ICCV). 2023 Conference
     Paper   Supplement   Video   Code   BibTex
    @inproceedings{lu2023hard,
      author = {Zhengzhi Lu and He Wang and Ziyi Chang and Guoan Yang and Hubert PH Shum},
      title = {Hard No-Box Adversarial Attack on Skeleton-Based Human Action Recognition with Skeleton-Motion-Informed Gradient},
      booktitle = {The Internaitional Conference on Computer Vision (ICCV)},
      year = {2023}
    }

  5. He Wang, Yunfeng Diao, Zichang Tan, Guodong Guo.  Defending Black-box Skeleton-based Human Activity Classifiers.   The AAAI Conference on Artificial Intelligence (AAAI). 2023 Conference
     Paper   Video   Code   BibTex
    @inproceedings{wang2023defending_1,
      author = {He Wang and Yunfeng Diao and Zichang Tan and Guodong Guo},
      title = {Defending Black-box Skeleton-based Human Activity Classifiers},
      booktitle = {The AAAI Conference on Artificial Intelligence (AAAI)},
      year = {2023}
    }

  6. Yufeng Diao, Tianjia Shao, Yongliang Yang, Kun Zhou, He Wang.  BASAR: Black-box attack on skeletal action recognition.   The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 Conference
     Paper   Supplement   Video   Code   Errata   BibTex
    @inproceedings{diao2021basar,
      author = {Yufeng Diao and Tianjia Shao and Yongliang Yang and Kun Zhou and He Wang},
      title = {BASAR: Black-box attack on skeletal action recognition},
      booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      pages = {7597--7607},
      year = {2021}
    }

  7. He Wang, Feixiang He, Zhexi Peng, Tianjia Shao, Yongliang Yang, Kun Zhou, David Hogg.  Understanding the robustness of skeleton-based action recognition under adversarial attack.   The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 2021 Conference
     Paper   Supplement   Video   Code   BibTex
    @inproceedings{wang2021understanding,
      author = {He Wang and Feixiang He and Zhexi Peng and Tianjia Shao and Yongliang Yang and Kun Zhou and David Hogg},
      title = {Understanding the robustness of skeleton-based action recognition under adversarial attack},
      booktitle = {The IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
      pages = {14656--14665},
      year = {2021}
    }

Acknowledgement

This project has received funding from the European Union’s Horizon 2020 research and innovation programme under grant agreement No 899739 CrowdDNA, EPSRC (EP/R031193/1), NSF China (No. 61772462, No. U1736217), RCUK grant CAMERA (EP/M023281/1, EP/T014865/1) and the 100 Talents Program of Zhejiang University.

Copyright since 2016 He Wang