AI Paper Atlas

Research map / Video / Action recognition

Towards Privacy-Preserving Visual Recognition via Adversarial Training: A Pilot Study

Zhenyu Wu, Zhangyang Wang, Zhaowen Wang, Hailin Jin

ECCV 2018 · Video › Action recognition · approach: Disentangled action recognition · 161 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add budget model restarting to the budget model ensemble (ablation)adversarial degradation training · SBU Kinect Interactionaction vs privacy trade-offImproved
increase number of budget models M in the ensemble (ablation)Method 3 · SBU Kinect Interactionaction vs privacy trade-offImproved
learned adversarial degradation instead of naive downsamplingprivacy-preserving action recognition · SBU Kinect Interactionaction vs privacy trade-offImproved
crop out faces from RGB framesraw RGB frames · SBU Kinect Interactionidentity privacyNo clear effect
crop out whole actor bodiesraw RGB frames · SBU Kinect Interactionaction accuracy and privacyHurt
add ensemble and restarting to adversarial training (ablation)degradation f_d · UCF-101/VISPR-17 and VISPR-7action accuracy vs C-MAP privacy trade-offImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy