AI Paper Atlas

Research map / Video / Video segmentation and tracking

Sequential keypoint density estimator: an overlooked baseline of skeleton-based video anomaly detection

Anja Delić, Matej Grcic, Siniša Šegvić

ICCV 2025 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 9 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
learn diagonal covariance instead of fixed identity (ablation)SeeKer · UBnormal (full)AUROC: 61.4 -> 77.9Improved
learn diagonal covariance instead of fixed identity (ablation)SeeKer · ShanghaiTech (full)AUROC: 74.1 -> 85.5Improved
learned full covariance instead of diagonal (ablation)SeeKer · ShanghaiTech (full)AUROC: 85.5 -> 84.3No clear effect
keypoint-level instead of skeleton-level factorization (ablation)SeeKer · UBnormal (full)AUROC: 75.0 -> 77.9Improved
keypoint-level instead of skeleton-level factorization (ablation)SeeKer · ShanghaiTech (full)AUROC: 79.0 -> 85.5Improved
weight keypoint log-densities by detector confidence (ablation)SeeKer · UBnormal (full)AUROC: 76.8 -> 77.9Improved
weight keypoint log-densities by detector confidence (ablation)SeeKer · ShanghaiTech (full)AUROC: 83.7 -> 85.5Improved
train only on skeletons with confidence at least 0.4 plus weighting (ablation)SeeKer · UBnormal (full)AUROC: 75.5 -> 77.9Improved
add Gaussian smoothing (ablation)SeeKer · UBnormal (full)AUROC: 76.8 -> 77.9Improved
add Gaussian smoothing (ablation)SeeKer · ShanghaiTech (full)AUROC: 83.4 -> 85.5Improved
add Gaussian smoothing (ablation)STG-NF · UBnormal (full)AUROC: 68.2 -> 71.8Improved
masked fully connected model instead of transformer decoder (ablation)SeeKer · UBnormal (full)AUROC: 71.1 -> 77.9Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 0 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