AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Background-Agnostic Framework with Adversarial Training for Abnormal Event Detection in Video

Mariana-Iuliana Georgescu, Radu Tudor Ionescu, Fahad Shahbaz Khan, Marius Popescu, Mubarak A. Shah

TPAMI 2021 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 206 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 adversarial training with pseudo-abnormal examples and segmentation (this work vs earlier version)background-agnostic framework · Avenuemicro AUC (%): about 5% higher micro AUC than the preliminary methodImproved
this work vs preliminary versionframework · ShanghaiTechmicro AUC (%): 4% margin micro, 4.4% macroImproved
this work vs preliminary versionframework · ShanghaiTechRBDC (%): more than 20%Improved
train on ShanghaiTech instead of Avenue (cross-domain)framework · Avenuemicro AUC (%): 92.3 -> 83.6Hurt
train on Avenue instead of ShanghaiTech (cross-domain)framework · ShanghaiTechTBDC (%): 78.79 -> 63.89Hurt
train on Avenue instead of UCSD Ped2framework · UCSD Ped2macro AUC (%): 99.7 -> 97.2Hurt
train on Avenue instead of Subway Exitframework · Subway ExitTBDC (%): 67.96 -> 63.93Hurt
combine Avenue and UCSD Ped2 as source data setsframework · Subway Exitframe AUC new labels (%): 92.4 -> 92.3No clear effect
use new frame labels instead of old labelsframework · Subway Entranceframe AUC (%): 87.6 -> 92.2Improved
use reconstructions instead of absolute differences as classifier input (ablation)binary classifiers · preliminary experimentsaccuracyHurt
use pseudo-abnormal adversarial decoder (adversarial training) (ablation)auto-encoders · Avenue test video 03frame AUC (%): 93.25 -> 98.83Improved
this work vs Ionescu et al. on Subway Exit (new labels)framework · Subway Exitframe AUC (%): 0.9% higherImproved

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