Selective, Interpretable, and Motion Consistent Privacy Attribute Obfuscation for Action Recognition
This work addresses privacy concerns for individuals in public imagery, offering a more flexible and interpretable solution for action recognition, though it is incremental in improving existing obfuscation techniques.
The paper tackled the problem of preserving privacy in action recognition by addressing issues of global obfuscation and lack of interpretability, resulting in a method that outperforms alternatives on three datasets without requiring retraining.
Concerns for the privacy of individuals captured in public imagery have led to privacy-preserving action recognition. Existing approaches often suffer from issues arising through obfuscation being applied globally and a lack of interpretability. Global obfuscation hides privacy sensitive regions, but also contextual regions important for action recognition. Lack of interpretability erodes trust in these new technologies. We highlight the limitations of current paradigms and propose a solution: Human selected privacy templates that yield interpretability by design, an obfuscation scheme that selectively hides attributes and also induces temporal consistency, which is important in action recognition. Our approach is architecture agnostic and directly modifies input imagery, while existing approaches generally require architecture training. Our approach offers more flexibility, as no retraining is required, and outperforms alternatives on three widely used datasets.