Ashish Patel 🇮🇳’s Post

𝗗𝗮𝘆-𝟰𝟲𝟮 𝗖𝗼𝗺𝗽𝘂𝘁𝗲𝗿 𝗩𝗶𝘀𝗶𝗼𝗻 𝗟𝗲𝗮𝗿𝗻𝗶𝗻𝗴 SPAct: Self-supervised Privacy Preservation for Action Recognition by Ishan Rajendrakumar Dave, Chen Chen, Mubarak Shah, Center for Research in Computer Vision, University of Central Florida, Orlando, USA Follow me for a similar post: Ashish Patel ------------------------------------------------------------------- 𝗜𝗻𝘁𝗲𝗿𝗲𝘀𝘁𝗶𝗻𝗴 𝗙𝗮𝗰𝘁𝘀 : 🔸 This paper is published CVPR2022. 🔸 Github: https://lnkd.in/gAdvRzZK ------------------------------------------------------------------- 𝗜𝗠𝗣𝗢𝗥𝗧𝗔𝗡𝗖𝗘 ➡️ Visual private information leakage is an emerging key issue for the fast growing applications of video understanding like activity recognition. ➡️ Existing approaches for mitigating privacy leakage in action recognition require privacy labels along with the action labels from the video dataset. ➡️ However, annotating frames of video dataset for privacy labels is not feasible. Recent developments of self-supervised learning (SSL) have unleashed the untapped potential of the unlabeled data. ➡️ For the first time, we present a novel training framework which removes privacy information from input video in a self-supervised manner without requiring privacy labels. ➡️ Our training framework consists of three main components: anonymization function, self-supervised privacy removal branch, and action recognition branch. ➡️ We train our framework using a minimax optimization strategy to minimize the action recognition cost function and maximize the privacy cost function through a contrastive self-supervised loss. ➡️ Employing existing protocols of known-action and privacy attributes, our framework achieves a competitive action-privacy trade-off to the existing state-of-the-art supervised methods. ➡️ In addition, we introduce a new protocol to evaluate the generalization of learned the anonymization function to novel-action and privacy attributes and show that our self-supervised framework outperforms existing supervised methods. #computervision #artificialintelligence #technology