STPrivacy: Spatio-temporal privacy-preserving action recognition

• Main Authors: LI, Ming, XU, Xiangyu, FAN, Hehe, ZHOU, Pan, LIU, Jun, LIU, Jia-Wei, LI, Jiahe, KEPPO, Jussi, SHOU, Mike Zheng, YAN, Shuicheng
• Format: text
• Language: English
• Published: Institutional Knowledge at Singapore Management University 2023
• Subjects: Privacy; Data privacy; Computer vision; Benchmark testing; Transformers; Information filtering; Task analysis; Graphics and Human Computer Interfaces
• Online Access: https://ink.library.smu.edu.sg/sis_research/8985; https://ink.library.smu.edu.sg/context/sis_research/article/9988/viewcontent/2023_ICCV_STPrivacy.pdf
• Institution: Singapore Management University

Existing methods of privacy-preserving action recognition (PPAR) mainly focus on frame-level (spatial) privacy removal through 2D CNNs. Unfortunately, they have two major drawbacks. First, they may compromise temporal dynamics in input videos, which are critical for accurate action recognition. Seco...