AI Paper Atlas

Research map / Video / Video generation

SWIFT: Sliding Window Reconstruction for Few-Shot Training-Free Generated Video Attribution

Chao Wang, Zijin Yang, Yaofei Wang, Yuang Qi, Weiming Zhang, Nenghai Yu, Kejiang Chen

CVPR 2026 · Video › Video generation · approach: Autoregressive long video generation · 0 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 temporal sliding-window reconstruction (SWIFT) instead of AEDRvideo attribution · S-Video avgaccuracy: 73.6% -> 94.0%Improved
use SWIFT instead of AEDR on LTX targetLTX-Video attribution vs EA / Real · S-Video LTXaccuracy: 97.1% -> 94.5% (EA); 95.6% -> 92.2% (Real)Mixed
use MSE instead of PSNR/SSIM as loss metric (ablation)SWIFT · Wan2.1accuracy: 47.8% (PSNR) -> 98.4% (MSE)Improved
use MSE instead of MAE (ablation)SWIFT · Wan2.1accuracy: 97.8% -> 98.4%Improved
use W0/W3 corrupted window instead of W0/W1 (ablation)SWIFT on HYV · HYV window selectionaccuracy: 82.3% -> 90.7%Improved
use W0/W3 instead of intuitive W0/W7 (ablation)SWIFT on LTX · LTX window selectionaccuracy: 78.6% -> 85.3%Improved
increase threshold sample size from 0 (tau=1) to 200 (ablation)SWIFT KDE threshold · avg over 5 modelsavg accuracy: 85.1% -> 94.0%Improved
fixed threshold tau=1 (zero-shot) (ablation)SWIFT · per modelaccuracy: HYV 90.1%, EA 89.3%, Wan2.2 98.4% vs Wan2.1 81.7%, LTX 66.1%Mixed
change KDE kernel or bandwidth rule (ablation)SWIFT · EAavg accuracy: 97.80% -> 97.40%No clear effect
shorten video to 25% of frames (ablation)SWIFT · Wan2.2accuracy: 98.0% -> 94.1%Hurt
apply post-processing (flip, noise, crop, compression) to test videos (ablation)SWIFT · EAaccuracy: 97.8% -> 52.0% (Flip), 60.3% (Noise)Hurt
use windowed reconstruction instead of full-video double reconstructionSWIFT vs AEDR · runtimeruntime: 227s -> 218s (HYV); 31s -> 21s (EA)Improved

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