AI Paper Atlas

Research map / Video / Video segmentation and tracking

Autoregressive Denoising Score Matching is a Good Video Anomaly Detector

Hanwen Zhang, Congqi Cao, Qinyi Lv, Lingtong Min, Yanning Zhang

ICCV 2025 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 8 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 autoregressive denoising score matching to plain DSM (ablation)NCST · ShanghaiTechAUC macro (%): 78.5 -> 84.1Improved
add scene condition embedding (ablation)ADSM · ShanghaiTechAUC macro (%): 84.1 -> 86.3Improved
add key frame motion weighting (ablation)ADSM · ShanghaiTechAUC macro (%): 84.1 -> 87.7Improved
aggregate PSNR visual difference between denoised and original data (ablation)ADSM · ShanghaiTechAUC macro (%): 84.1 -> 89.9Improved
combine scene, motion and appearance components (ablation)ADSM · ShanghaiTechAUC macro (%): 89.9 -> 93.2Improved
apply ADSM in pretrained VAE latent space instead of original pixel space (ablation)ADSM · ShanghaiTechAUC macro (%): 93.2 -> 87.5Hurt
apply ADSM in latent space on NWPU Campus (ablation)ADSM · NWPU CampusAUC macro (%): 78.1 -> 73.2Hurt
use ADSM instead of other likelihood-based methods (MSMA, MULDE)Likelihood-based VAD · ShanghaiTechAUC macro (%): 90.4 -> 93.2Improved
use ADSM versus skeleton-based STG-NF on micro AUCVAD methods · ShanghaiTechAUC micro (%): 85.9 -> 84.5Hurt

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