AI Paper Atlas

Research map / Video / Video segmentation and tracking

A Hybrid Video Anomaly Detection Framework via Memory-Augmented Flow Reconstruction and Flow-Guided Frame Prediction

Zhian Liu, Yongwei Nie, Chengjiang Long, Qing Zhang, Guiqing Li

ICCV 2021 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 395 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 frame prediction to flow reconstruction (ablation)HF2-VAD · UCSD Ped2AUROC (%): 98.8 -> 99.3Improved
add frame prediction to flow reconstruction (ablation)HF2-VAD · CUHK AvenueAUROC (%): 86.8 -> 91.1Improved
add frame prediction to flow reconstruction (ablation)HF2-VAD · ShanghaiTechAUROC (%): 73.1 -> 76.2Improved
add flow reconstruction to frame prediction (ablation)HF2-VAD · UCSD Ped2AUROC (%): 94.5 -> 99.3Improved
add flow reconstruction to frame prediction (ablation)HF2-VAD · CUHK AvenueAUROC (%): 90.2 -> 91.1Improved
add flow reconstruction to frame prediction (ablation)HF2-VAD · ShanghaiTechAUROC (%): 76.0 -> 76.2Improved
use ML-MemAE-SC with 3 memories instead of MemAE (ablation)Flow reconstruction · UCSD Ped2AUROC (%): 96.27 -> 98.81Improved
use CVAE with flow condition instead of VAE for prediction (ablation)Frame prediction · UCSD Ped2AUROC (%): 89.96 -> 94.48Improved
combine ML-MemAE-SC (3 memories) with CVAE instead of reconstruction only (ablation)Flow reconstruction · UCSD Ped2AUROC (%): 98.81 -> 99.31Improved
combine ML-MemAE-SC (3 memories) with CVAE instead of prediction only (ablation)CVAE prediction · UCSD Ped2AUROC (%): 94.48 -> 99.31Improved
feed all four reconstructed flows to CVAE instead of one (ablation)HF2-VAD · UCSD Ped2AUROC (%): 98.70 -> 99.31Improved
use deterministic posterior-mean sampling instead of stochastic sampling at test time (ablation)CVAE · UCSD Ped2AUROC (%): 99.3078 vs 99.3065 to 99.3089No clear effect

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