SkeletonVis: Interactive Visualization for Understanding Adversarial Attacks on Human Action Recognition Models
Georgia Institute of Technology（佐治亚理工学院）；Intel（英特尔）
英文摘要：
Skeleton-based human action recognition technologies are increasingly used in video based applications, such as home robotics, healthcare on aging population, and surveillance. However, such models are vulnerable to adversarial attacks, raising serious concerns for their use in safety-critical applications. To develop an effective defense against attacks, it is essential to understand how such attacks mislead the pose detection models into making incorrect predictions. We present SkeletonVis, the first interactive system that visualizes how the attacks work on the models to enhance human understanding of attacks.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
