AI Paper Atlas

Research map / Video / Action recognition

Privacy-Preserving Action Recognition via Motion Difference Quantization

Sudhakar Kumawat, Hajime Nagahara

ECCV 2022 · Video › Action recognition · approach: Disentangled action recognition · 22 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
replace Wu et al UNet encoder with BDQBDQ · encoder complexityFLOPs: 166.4G -> 120.4MImproved
add Quantization to Difference module (ablation)BDQ · SBU actor-pair privacyprivacy accuracyImproved
add Blur to Difference+Quantization (ablation)BDQ · SBU actor-pair privacyprivacy accuracyImproved
use Difference alone (ablation)BDQ · SBU action recognitionaction accuracyImproved
increase adversarial weight alpha from 0 (ablation)BDQ · SBUprivacy accuracyImproved
add BDQ encoder to 3D CNN action recognition3D ResNeXt-101 · SBUaction accuracy: 85.1Hurt

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