AI Paper Atlas

Research map / Video / Video segmentation and tracking

Weakly-Supervised Video Anomaly Detection With Robust Temporal Feature Magnitude Learning

Yu Tian, Guansong Pang, Yuanhong Chen, Rajvinder Singh, Johan W. Verjans, Gustavo Carneiro

ICCV 2021 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 662 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 feature magnitude learning (FM) to the MIL baseline (ablation)MIL baseline · ShanghaiTechAUC: 85.96 -> 92.99Improved
add feature magnitude learning (FM) to the MIL baseline (ablation)MIL baseline · UCF-CrimeAUC: 77.39 -> 81.28Improved
add pyramid of dilated convolutions (PDC) (ablation)MIL baseline · ShanghaiTechAUC: 85.96 -> 89.21Improved
add temporal self-attention (TSA) (ablation)MIL baseline · ShanghaiTechAUC: 85.96 -> 91.73Improved
add PDC (ablation)MIL baseline · UCF-CrimeAUC: 77.39 -> 79.32Improved
add TSA (ablation)MIL baseline · UCF-CrimeAUC: 77.39 -> 78.96Improved
add TSA alongside PDC (ablation)MIL baseline with PDC · ShanghaiTechAUC: 89.21 -> 92.32Improved
add PDC and TSA to the FM model (full RTFM) (ablation)MIL baseline with FM · ShanghaiTechAUC: 92.99 -> 97.21Improved
add PDC and TSA to the FM model (full RTFM) (ablation)MIL baseline with FM · UCF-CrimeAUC: 81.28 -> 84.30Improved
add FM to the PDC+TSA model (ablation)MTN with MIL · UCF-CrimeAUC: 82.12 -> 84.30Improved
replace Sultani MIL with RTFM (I3D features) (ablation)Sultani et al. · UCF-CrimeAUC: 77.92 -> 84.30Improved
reduce abnormal training videos from 63 to 25 and use RTFM instead of MIL (ablation)RTFM vs Sultani · ShanghaiTechAUC: about 3% higher using 25 vs 63 videosImproved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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