AI Paper Atlas

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

Detecting and Recovering Sequential DeepFake Manipulation

Rui Shao, Tianxing Wu, Ziwei Liu

ECCV 2022 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 57 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 decoding (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake (facial components)Adaptive-Acc: 51.71 -> 54.80Improved
add SECA with auto-regressive decoding (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake (facial components)Adaptive-Acc: 53.84 -> 54.80Improved
add SECA without auto-regressive decoding (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake (facial components)Adaptive-Acc: 52.19 -> 51.71Hurt
add SECA without auto-regressive decoding (ablation)SeqFakeFormer (ResNet-50) · Seq-DeepFake (facial components)Fixed-Acc: 71.22 -> 70.99Hurt
add SECA (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake (facial attributes)Adaptive-Acc: 46.56 -> 48.32Improved
add auto-regressive decoding (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake (facial attributes)Adaptive-Acc: 47.22 -> 48.32Improved
add auto-regressive decoding alone (no SECA) (ablation)SeqFakeFormer (ResNet-34) · Seq-DeepFake (facial attributes)Fixed-Acc: 66.98 -> 66.70Hurt
replace Multi-Cls with SeqFakeFormerMulti-Cls (ResNet-50) · Seq-DeepFake (facial components)Adaptive-Acc: 50.57 -> 55.30Improved
replace Multi-Cls with SeqFakeFormerMulti-Cls (ResNet-50) · Seq-DeepFake (facial attributes)Adaptive-Acc: 46.00 -> 49.63Improved
replace DETR with SeqFakeFormerDETR (ResNet-34) · Seq-DeepFake (facial attributes)Fixed-Acc: 67.93 -> 67.99No clear effect
replace Two-Stream deepfake detector with SeqFakeFormerTwo-Stream · Seq-DeepFake (facial components)Adaptive-Acc: 53.89 -> 55.30Improved
evaluate with adaptive length instead of fixed lengthSeqFakeFormer (ResNet-50) · Seq-DeepFake (facial components)accuracy: 72.65 -> 55.30Hurt

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