AI Paper Atlas

Research map / Video / Video segmentation and tracking

CLAWS: Clustering Assisted Weakly Supervised Learning with Normalcy Suppression for Anomalous Event Detection

Muhammad Zaigham Zaheer, Arif Mahmood, Marcella Astrid, Seung-Ik Lee

ECCV 2020 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 202 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 random batch selection (RBS) to the backbone (ablation)BBN · UCF-Crimeframe-level AUC (%): 69.50 -> 75.95Improved
add random batch selection (RBS) to the backbone (ablation)BBN · ShanghaiTechframe-level AUC (%): 67.50 -> 79.64Improved
add normalcy suppression modules (NSM) to BBN+RBS (ablation)BBN + RBS · ShanghaiTechframe-level AUC (%): 79.64 -> 87.76Improved
add both NSMs to BBN+RBS (ablation)BBN + RBS · UCF-Crimeframe-level AUC (%): 75.95 -> 80.94Improved
add NSM-1 to BBN+RBS (ablation)BBN + RBS · UCF-Crimeframe-level AUC (%): 75.95 -> 78.60Improved
add NSM-2 on top of NSM-1 (ablation)BBN + RBS + NSM-1 · UCF-Crimeframe-level AUC (%): 78.60 -> 80.94Improved
add sparsity and temporal consistency losses (ablation)BBN + RBS + NSM · UCF-Crimeframe-level AUC (%): 80.94 -> 81.53Improved
add clustering distance loss (ablation)CLAWS Net w/o clustering loss · UCF-Crimeframe-level AUC (%): 81.53 -> 83.03Improved
keep RBS in the full model (removing it lowers AUC) (ablation)CLAWS Net · UCF-Crimeframe-level AUC (%): 80.23 -> 83.03Improved
keep NSM-1 in the full model (ablation)CLAWS Net · UCF-Crimeframe-level AUC (%): 77.39 -> 83.03Improved
keep NSM-2 in the full model (ablation)CLAWS Net · UCF-Crimeframe-level AUC (%): 79.78 -> 83.03Improved
keep both NSMs in the full model (ablation)CLAWS Net · UCF-Crimeframe-level AUC (%): 76.81 -> 83.03Improved

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