AI Paper Atlas

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

All in One: Unifying Deepfake Detection, Tampering Localization, and Source Tracing with a Robust Landmark-Identity Watermark

Junjiang Wu, Liejun Wang, Zhiqing Guo

CVPR 2026 · Detection and segmentation › Open-set and few-shot detection · approach: Industrial anomaly detection · 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
add landmark regression loss (lambda_L) (ablation)LIDMark (FHD) · CelebA-HQ 128x128 common distortionsAED: 342.39 -> 1.17Improved
add landmark regression loss (lambda_L) (ablation)LIDMark (FHD) · CelebA-HQ 128x128 deepfake manipulationsAED: 359.98 -> 1.58Improved
add landmark regression loss (lambda_L) (ablation)LIDMark (FHD) · CelebA-HQ 256x256 common distortionsAED: 540.91 -> 3.06Improved
add landmark regression loss (lambda_L) (ablation)LIDMark (FHD) · CelebA-HQ 128x128 deepfake manipulationsBER: 0.14% -> 3.33%Hurt
add identifier loss (lambda_ID) (ablation)LIDMark (FHD) · CelebA-HQ 128x128 common distortionsBER: 0.42% -> 0.27%Improved
add identifier loss (lambda_ID) (ablation)LIDMark (FHD) · CelebA-HQ 128x128 deepfake manipulationsBER: 0.49% -> 3.33%Hurt
add identifier loss (lambda_ID) (ablation)LIDMark (FHD) · CelebA-HQ 128x128 common distortionsAED: 2.31 -> 1.17Improved
add identifier loss (lambda_ID) (ablation)LIDMark (FHD) · CelebA-HQ 128x128PSNR: 47.31 -> 40.22Hurt
add landmark regression loss (lambda_L) (ablation)LIDMark (FHD) · CelebA-HQ 128x128PSNR: 42.12 -> 40.22Hurt
expand identifier payload from 16-D to 32-D (168-D total) (ablation)LIDMark (FHD) · CelebA-HQ 256x256PSNR: 44.31 -> 42.36Hurt
expand identifier payload from 16-D to 32-D (168-D total) (ablation)LIDMark (FHD) · CelebA-HQ 256x256 deepfake manipulationsAED: 4.01 -> 3.01Improved
expand identifier payload from 16-D to 32-D (168-D total) (ablation)LIDMark (FHD) · CelebA-HQ 256x256 deepfake manipulationsBER: 2.55% -> 3.26%Hurt

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