AI Paper Atlas

Research map / Video / Video segmentation and tracking

Training-free Detection of Generated Videos via Spatial-Temporal Likelihoods

Omer Ben Hayun, Roy Betser, Meir Yossef Levi, Levi Kassel, Guy Gilboa

CVPR 2026 · Video › Video segmentation and tracking · approach: Weakly supervised video anomaly detection · 5 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 balanced real/synthetic test sets instead of unbalanced (D3 with DinoV3, downsampled real)D3 evaluation · GenVideomean AP: 0.83 -> 0.74Hurt
duplicate real-video frames 3->8 FPS instead of downsampling (D3 with DinoV3, balanced)D3 evaluation · GenVideomean AP: 0.74 -> 0.94Hurt
use X-CLIP16 instead of DinoV3 as D3 embedderD3 · GenVideo (downsample, balanced)mean AP: 0.74 -> 0.78Improved
apply l2 normalization to temporal differences (ablation)STALL temporal features · VATEX calibration set (AD normality test)normal features (%): 0.0% -> 98.4%Improved
add whitening to l2-normalized temporal differences (ablation)STALL temporal features · VATEX calibration set (AD normality test)normal features (%): 98.4% -> 99.6%Improved
add whitening to raw frame embeddings (ablation)STALL spatial features · VATEX calibration set (AD normality test)normal features (%): 96.3% -> 98.2%Improved
estimate temporal whitening from one random frame difference per video instead of all differences (ablation)STALL · GenVideo/VideoFeedback/ComGenVidaverage AUC: 0.8110 -> 0.8105No clear effect
raise temporal derivative order D from 1 to 4 (ablation)STALL · three benchmarksAUCNo clear effect
insert a flash frame (black or white) into real videosSTALL temporal likelihood · MSR-VTT (400 real videos)temporal scoreHurt
reverse or shuffle frame orderSTALL temporal likelihood · MSR-VTT (400 real videos)temporal scoreNo clear effect
vary frame rate in {2, 4, 8, 12, 24} FPS at inferenceSTALL · GenVideo 24 FPS subsetdetection performanceNo clear effect
change calibration set from VATEX to DiDeMo (ablation)STALL · VideoFeedbackaverage AUC: 0.82 -> 0.86Improved

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