AI Paper Atlas

Research map / Video / Video segmentation and tracking

Feature Prediction Diffusion Model for Video Anomaly Detection

Cheng Yan, Shiyu Zhang, Yang Liu, Guansong Pang, Wenjun Wang

ICCV 2023 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 102 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 the two diffusion modules over a plain auto-encoder (ablation)FPDM · UCF-Crimeframe-level AUC: 53.1% -> 74.7%Improved
add refinement module to prediction module (ablation)FPDM · ShanghaiTechframe-level AUC: 77.3% -> 78.6%Improved
add prediction module to refinement module (ablation)FPDM · UCF-Crimeframe-level AUC: 72.5% -> 74.7%Improved
pre-train auto-encoder before optimizing FPDM (ablation)FPDM · ShanghaiTechframe-level AUC: 78.6% -> 78.6%No clear effect
decode features back to images before computing anomaly score (ablation)FPDM · ShanghaiTechframe-level AUC: 78.6% -> 78.3%Hurt
train prediction and refinement modules separately instead of jointly (ablation)FPDM · ShanghaiTechframe-level AUC: 70.8% -> 78.6%Improved
add joint fine-tuning after separate training (ablation)FPDM · ShanghaiTechframe-level AUC: 78.6% -> 78.2%Hurt
increase neighbor frames in prediction module from 0 to 12 (ablation)FPDM · ShanghaiTech scene 3AUC: 73.8 -> 81.7Improved
increase neighbor frames from 0 to 12 (ablation)FPDM · ShanghaiTech scene 11 (appearance anomalies)AUC: 96.3 -> 96.6No clear effect
use FPDM with image features versus object-detection or 3D feature methodsFPDM · ShanghaiTechframe-level AUC: 78.6% vs 84.3% (SSL)Hurt

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