PRIVACY-PRESERVING ACTION RECOGNITION

As the amount of data shared on the network increases, these data pose a threat to our privacy. This paper focuses on the privacy-preserving issues of action recognition for humans. Generally, the face is considered the most identifiable visual cue for a human. However, removing face information is not enough for many privacy-preserving scenes. Thus, we replace the human body with his poses and explore the pose presentation in the action recognition task. In privacy scenes, many human actions could not access in advance. To recognize these unseen actions, we study the zero-shot action recognition in the strict condition of privacy preservation. Specifically, we propose to use \emph{unified actor score} (UAS) to enhance the action recognition accuracy. The experimental results show that UAS outperforms most of the state-of-the-art methods in standard datasets without sacrificing privacy.