AI Paper Atlas

Research map / Adversarial robustness and security / Certified and empirical robustness

Learning Discriminative Video Representations Using Adversarial Perturbations

Jue Wang, Anoop Cherian

ECCV 2018 · Adversarial robustness and security › Certified and empirical robustness · approach: Robust overfitting and regularization · 26 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 average pooling with discriminative subspace poolingtwo-stream ResNet-152 · HMDB-51 split-1accuracy: 63.8% -> 72.5%Improved
replace max pooling with discriminative subspace poolingtwo-stream ResNet-152 · HMDB-51 split-1accuracy: 60.6% -> 72.5%Improved
replace average pooling with discriminative subspace poolingRes-TCN skeleton features · NTU-RGBD cross-subjectaccuracy: 74.3% -> 81.6%Improved
replace average pooling with discriminative subspace poolingInception-ResNet-v2 · YUP++ movingaccuracy: 76.5% -> 88.3%Improved
use universal adversarial perturbation noise instead of Gaussian noise as negative bag (ablation)DSP · HMDB-51 split-1accuracy: 69.8% -> 70.8%Improved
increase number of hyperplanes from one to six (ablation)DSP · HMDB-51 split-1accuracy: about 3% accuracy gainImproved
increase number of hyperplanes from six to fifteen (ablation)DSP · HMDB-51 split-1accuracy: drops around 0.5%No clear effect
add temporal ordering constraints (ablation)DSP · HMDB-51 split-1accuracyImproved
increase UAP fooling rate from 0.1 to 0.9 (ablation)DSP · HMDB-51 split-1accuracyImproved
apply DSP on I3D features instead of average poolingTS I3D · HMDB-51accuracy: 80.9% -> 81.5%Improved
apply DSP instead of average pooling on I3D, long sequencesI3D · HMDB-51 split-1 (260+ frames)accuracy: 77.3 -> 82.6Improved
apply DSP instead of average pooling on I3D, short sequencesI3D · HMDB-51 split-1 (1+ frames)accuracy: 80.8 -> 81.6Improved

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