AI Paper Atlas

Research map / Video / Video segmentation and tracking

UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection

CVPR 2022 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 183 citations (OpenAlex)

Check your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (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 UBnormal training anomalies to the pseudo-abnormal pool (ablation)Georgescu anomaly detector · UBnormal testmicro AUC: 59.3 -> 61.3Helped
Fine-tune the pre-trained model on UBnormal (ablation)Sultani · UBnormal testmicro AUC: 49.5 -> 50.3Helped
Use 1/8 or 1/4 rather than 1/32 video sample rate (ablation)TimeSformer · UBnormal testmicro AUC: 68.5 -> 64.1; 68.5 -> 61.9Hurt
Add the UBnormal normal-versus-abnormal proxy task T5 (ablation)Georgescu multi-task detector · Avenue and ShanghaiTechmicro AUC: Avenue: 91.5 -> 91.9; ShanghaiTech: 82.4 -> 83.0Helped
Translate UBnormal objects with CycleGAN in addition to T5 (ablation)Georgescu multi-task detector · Avenue and ShanghaiTechmicro AUC: Avenue: 91.9 -> 93.0; ShanghaiTech: 83.0 -> 83.7Helped

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