AI Paper Atlas

Research map / Video / Video segmentation and tracking

Self-Supervised Sparse Representation for Video Anomaly Detection

Jhih-Ciang Wu, He-Yen Hsieh, Ding-Jie Chen, Chiou-Shann Fuh, Tyng-Luh Liu

ECCV 2022 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 167 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 de-Normal module with averaged normal feature (ablation)S3R baseline · UCF-Crime (weakly-supervised)AUC: 83.42 -> 84.19Improved
add de-Normal module with averaged normal feature (ablation)S3R baseline · ShanghaiTech (weakly-supervised)AUC: 96.97 -> 97.28Improved
use learned task-specific dictionary DT instead of averaged feature (ablation)S3R · UCF-Crime (weakly-supervised)AUC: 84.19 -> 85.99Improved
use task-specific DT instead of universal DU for reconstruction (ablation)S3R · UCF-Crime (weakly-supervised)AUC: 85.00 -> 85.99Improved
use task-specific DT instead of universal DU (ablation)S3R · ShanghaiTech (weakly-supervised)AUC: 97.47 -> 97.48No clear effect
use universal dictionary DU for pseudo anomaly generationS3R · UCF-Crime (one-class)AUC: 77.15 -> 79.58Improved
use universal dictionary DU for pseudo anomaly generationS3R · ShanghaiTech (one-class)AUC: 79.89 -> 80.47Improved
replace 25% anomaly and 25% normal snippets vs 25% anomaly only (ablation)S3R · ShanghaiTech (one-class), pseudo snippet ratioAUC: 79.59 -> 80.47Improved
use 12.5% anomaly ratio instead of 25% (ablation)S3R · ShanghaiTech (one-class), pseudo snippet ratioAUC: 80.47 -> 60.43Hurt
set en-Normal channel reduction to 25% instead of 50% (ablation)S3R · ShanghaiTech (one-class), en-Normal channel reductionAUC: 70.38 -> 80.47Improved
set de-Normal MLP reduction to 6.25% instead of 25% (ablation)S3R · ShanghaiTech (one-class), de-Normal channel reductionAUC: 66.14 -> 80.47Improved
S3R vs best prior one-class method on UCF-CrimeS3R · UCF-Crime (one-class)AUC: 72.70 -> 77.15Improved

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