The paper shows that adding a pixel-distance penalty with a tunable threshold to a privacy anonymizer preserves action recognition accuracy while keeping privacy leakage roughly stable across settings.
Spact: Self-supervised privacy preservation for action recog- nition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Balancing Privacy and Action Performance: A Penalty-Driven Approach to Image Anonymization
The paper shows that adding a pixel-distance penalty with a tunable threshold to a privacy anonymizer preserves action recognition accuracy while keeping privacy leakage roughly stable across settings.