Skeletal motions have been heavily replied upon for human activity recognition (HAR). Recently, a universal vulnerability of skeleton-based HAR has been identified across a variety of classifiers and data, calling for mitigation. To this end, we propose the first black-box defense method for skeleton-based HAR to our best knowledge. Our method is featured by full Bayesian treatments of the clean data, the adversaries and the classifier, leading to (1) a new Bayesian Energy-based formulation of robust discriminative classifiers, (2) a new adversary sampling scheme based on natural motion manifolds, and (3) a new post-train Bayesian strategy for black-box defense. We name our framework Bayesian Energy-based Adversarial Training or BEAT. BEAT is straightforward but elegant, which turns vulnerable black-box classifiers into robust ones without sacrificing accuracy. It demonstrates surprising and universal effectiveness across a wide range of skeletal HAR classifiers and datasets, under various attacks. Code is available at https://github.com/realcrane/RobustActionRecogniser.
Understanding the Vulnerability of Skeleton-based Human Activity Recognition via Black-box Attack
School of Computer Science and Information Engineering, Hefei University of Technology(合肥工业大学计算机与信息工程学院);University College London(伦敦大学学院);Zhejiang University(浙江大学);University of Bath(巴斯大学);School of Computing, University of Leeds(利兹大学计算学院)
Skeleton-Guided Sparse Anchors for Rotated Instance Segmentation in Cell Microscopy
Aier Institute of Digital Ophthalmology and Visual Science(爱尔数字眼科学与视觉科学研究所);Changsha Aier Eye Hospital(长沙爱尔眼科医院);Shanghai Jiao Tong University(上海交通大学);Nanyang Technological University(南洋理工大学);Obstetrics and Gynecology Hospital, Institute of Reproduction and Development, Fudan University(复旦大学附属妇产科医院 生殖与发育研究院)
Dormant: Defending against Pose-driven Human Image Animation
Institute of Information Engineering, Chinese Academy of Sciences(中国科学院信息工程研究所);School of Cyber Security, University of Chinese Academy of Sciences(中国科学院大学网络空间安全学院);Nanyang Technological University(南洋理工大学)
Neurosymbolic Framework for Concept-Driven Logical Reasoning in Skeleton-Based Human Action Recognition
Department of ECSE, Faculty of Engineering, Monash University, Australia(莫纳什大学工程学院电子与计算机工程系,澳大利亚);AIM for Health Lab, Faculty of Information Technology, Monash University, Australia(莫纳什大学信息科技学院健康人工智能实验室,澳大利亚);Department of DSAI, Faculty of Information Technology, Monash University, Australia(莫纳什大学信息科技学院数据科学与人工智能系,澳大利亚)
FuSSI-Net: Fusion of Spatio-temporal Skeletons for Intention Prediction Network
Chalmers University of Technology(查尔姆斯理工大学);Volvo Cars Technology USA(沃尔沃汽车美国技术公司);Volvo Car Corporation(沃尔沃汽车公司);University of California, Berkeley(加州大学伯克利分校)