AI Paper Atlas

Research map / Detection and segmentation / Open-set and few-shot detection

Robust Sequential DeepFake Detection

Rui Shao, Tianxing Wu, Ziwei Liu

IJCV 2025 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 27 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 auto-regressive mechanism (ablation)SeqFakeFormer (ResNet-50) · Seq-DeepFake components manipulationAdap-Acc: 52.66 -> 55.30Improved
add SECA (ablation)SeqFakeFormer (ResNet-50) · Seq-DeepFake components manipulationAdap-Acc: 54.64 -> 55.30Improved
add SECA (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake attributes manipulationAdap-Acc: 46.56 -> 48.32Improved
add auto-regressive mechanism without SECA (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake attributes manipulationFixed-Acc: 66.98 -> 66.70No clear effect
add ISM and ISC image-sequence reasoning modules (ablation)SeqFakeFormer++ (ResNet-50) · Seq-DeepFake-P componentsAdap-Acc: 44.34 -> 45.35Improved
add ISM and ISC image-sequence reasoning modules (ablation)SeqFakeFormer++ (ResNet-34) · Seq-DeepFake-P componentsFixed-Acc: 63.51 -> 65.23Improved
add ISM and ISC (ablation)SeqFakeFormer++ (ResNet-50) · Seq-DeepFake-P attributesAdap-Acc: 45.43 -> 47.30Improved
add ISC only (ablation)SeqFakeFormer++ (ResNet-50) · Seq-DeepFake-P componentsFixed-Acc: 65.19 -> 65.22No clear effect
treat as sequence prediction instead of multi-label classification (SeqFakeFormer vs DRN, MA, TS)SeqFakeFormer (ResNet-50) · Seq-DeepFake components manipulationAdap-Acc: 53.89 -> 55.30Improved
perturbations applied to data (Seq-DeepFake-P vs Seq-DeepFake)SeqFakeFormer (ResNet-50) · components manipulationAdap-Acc: 55.30 -> 44.34Hurt
use SeqFakeFormer++ instead of SeqFakeFormer on perturbed dataSeqFakeFormer (ResNet-50) · Seq-DeepFake-P attributesAdap-Acc: 45.43 -> 47.30Improved
use SeqFakeFormer instead of DETRDETR (ResNet-50) · Seq-DeepFake components manipulationAdap-Acc: 49.84 -> 55.30Improved

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