LatentStealth is a latent-space optimization method that produces imperceptible yet effective adversarial attacks on expressive human pose and shape estimation models using few output queries.
Hybrik: A hybrid analytical-neural inverse kinematics solution for 3d human pose and shape estimation,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
LatentStealth: Unnoticeable and Efficient Adversarial Attacks on Expressive Human Pose and Shape Estimation
LatentStealth is a latent-space optimization method that produces imperceptible yet effective adversarial attacks on expressive human pose and shape estimation models using few output queries.