AI Paper Atlas

Research map / Video / Video segmentation and tracking

Video Anomaly Detection by Solving Decoupled Spatio-Temporal Jigsaw Puzzles

Guodong Wang, Yunhong Wang, Jie Qin, Dongming Zhang, Xiuguo Bao, Di Huang

ECCV 2022 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 130 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
use multi-label position prediction instead of multi-class permutation classification (same 5040/5040 permutations) (ablation)jigsaw VAD · ShanghaiTech CampusAUROC %: 78.5 -> 82.0Improved
use multi-label instead of multi-class (same 5040/5040 permutations) (ablation)jigsaw VAD · CUHK AvenueAUROC %: 87.5 -> 89.5Improved
increase permutations from 504/504 to 5040/5040 (ablation)multi-label jigsaw · ShanghaiTech CampusAUROC %: 79.7 -> 82.0Improved
use full spatial permutations (362880) instead of 5040 (ablation)multi-label jigsaw · CUHK AvenueAUROC %: 89.5 -> 92.2Improved
use full spatial permutations (362880) instead of 5040 (ablation)multi-label jigsaw · ShanghaiTech CampusAUROC %: 82.0 -> 83.2Improved
increase patches from n^2=4 to n^2=9 (l=7) (ablation)jigsaw VAD · ShanghaiTech CampusAUROC %: 80.2 -> 83.2Improved
increase patches from n^2=9 to n^2=16 (l=9) (ablation)jigsaw VAD · ShanghaiTech CampusAUROC %: 84.3 -> 80.4Hurt
increase frames from l=7 to l=9 (n^2=9) (ablation)jigsaw VAD · ShanghaiTech CampusAUROC %: 83.2 -> 84.3Improved
increase frames from l=7 to l=9 (n^2=9) (ablation)jigsaw VAD · CUHK AvenueAUROC %: 92.2 -> 89.2Hurt
add spatial puzzle to temporal-only training (ablation)jigsaw VAD · ShanghaiTech CampusAUROC %: 78.6 -> 82.7Improved
test with both temporal and spatial solvers instead of temporal only (ablation)jigsaw VAD · ShanghaiTech CampusAUROC %: 82.7 -> 84.3Improved
replace rotation/arrow-of-time pretexts with spatio-temporal jigsaw (ablation)pretext task · ShanghaiTech CampusAUROC %: 72.9 -> 84.3Improved

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