AI Paper Atlas

Research map / Video / Video segmentation and tracking

EVAL: Explainable Video Anomaly Localization

Ashish Singh, Michael J. Jones, Erik G. Learned-Miller

CVPR 2023 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 39 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
Use EVAL instead of the strongest listed baselinevideo anomaly localization · CUHK AvenueRBDC AUC: 65.99 -> 68.2Improved
Use EVAL instead of the strongest listed baselinevideo anomaly localization · CUHK AvenueTBDC AUC: 89.28 -> 87.56Hurt
Use EVAL instead of the strongest listed baselinevideo anomaly localization · CUHK AvenueFrame AUC: 92.9 -> 86.02Hurt
Use EVAL instead of the strongest listed baselinevideo anomaly localization · ShanghaiTechRBDC AUC: 45.45 -> 59.21Improved
Use EVAL instead of the strongest listed baselinevideo anomaly localization · ShanghaiTechTBDC AUC: 84.50 -> 89.44Improved
Use EVAL instead of the strongest listed baselinevideo anomaly localization · ShanghaiTechFrame AUC: 90.02 -> 76.63Hurt
Use EVAL instead of the strongest listed baselinevideo anomaly localization · Street SceneRBDC AUC: 21.0 -> 24.26Improved
Use EVAL instead of the strongest listed baselinevideo anomaly localization · Street SceneTBDC AUC: 53.0 -> 64.5Improved
Combine appearance and motion features instead of using either alone (ablation)EVAL · UCSD Ped1, UCSD Ped2, CUHK Avenue, Street SceneRBDC and TBDC AUCMixed
Replace EVAL appearance embeddings with ImageNet pre-classification features (ablation)EVAL · UCSD Ped1RBDC AUC: 29.6 -> 25.148Hurt
Replace EVAL appearance embeddings with ImageNet pre-classification features (ablation)EVAL · UCSD Ped1TBDC AUC: 64.8 -> 44.63Hurt
Replace EVAL appearance embeddings with ImageNet pre-classification features (ablation)EVAL · UCSD Ped2RBDC AUC: 77.7 -> 64.67Hurt

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