AI Paper Atlas

Research map / Video / Video segmentation and tracking

A New Comprehensive Benchmark for Semi-Supervised Video Anomaly Detection and Anticipation

Congqi Cao, Yue Lu, Peng Wang, Yanning Zhang

CVPR 2023 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 58 citations (OpenAlex)

Read the paper

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 scene-conditioned VAE (γ=1) instead of setting γ=0 (ablation)Ours · NWPU CampusAUC (%): 65.8 -> 68.2Improved
Add scene-conditioned VAE (γ=1) instead of setting γ=0 (ablation)Ours · ShanghaiTech-sdAUC (%): 70.4 -> 82.7Improved
Add backward prediction to forward prediction (ablation)Ours for anomaly anticipation · NWPU Campus, anticipation times 0.5s to 3.0sAUC (%): 65.2 -> 65.8; 64.6 -> 65.3; 64.2 -> 64.9; 63.6 -> 64.6; 63.1 -> 64.2; 62.5 -> 64.0Improved
Use the proposed method rather than the strongest listed baselineOurs · ShanghaiTechAUC (%): 78.2 -> 79.2Improved
Use the proposed method rather than the strongest listed baselineOurs · CUHK AvenueAUC (%): 91.1 -> 86.8Hurt
Use the proposed method rather than the strongest listed baselineOurs · IITB CorridorAUC (%): 73.5 -> 73.6Improved
Use the proposed method rather than the strongest listed baselineOurs · NWPU CampusAUC (%): 64.5 -> 68.2Improved
Extend the anticipation timeOurs (f+b) · NWPU CampusAUC (%): 65.8 -> 64.0Hurt

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