Research map / Video / Video segmentation and tracking
Spatial-Temporal Forgery Trace based Forgery Image Identification
Yilin Wang, Zunlei Feng, Jiachi Wang, Hengrui Lou, Binjia Zhou, Jie Lei, Mingli Song, Yijun Bei
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 changed | Where | Measured | Effect |
|---|---|---|---|
| add temporal prior correlation module (ablation) | STFT · DALL·E 3 (DeepFaceGen) | AUC: 86.28 -> 92.02 | Improved |
| add spatial correlation module (ablation) | STFT · DALL·E 3 (DeepFaceGen) | AUC: 79.71 -> 92.02 | Improved |
| add frequency-enhanced attention module (ablation) | STFT · DALL·E 3 (DeepFaceGen) | AUC: 89.75 -> 92.02 | Improved |
| use 20 diffusion sampling steps instead of 10, 15, 25 or 30 (ablation) | STFT · GenImage / DeepFaceGen | accuracy: best at 20 steps | Improved |
| use 3x8x8 latent resolution instead of lower (3x4x4) or higher (ablation) | STFT · GenImage / DeepFaceGen | accuracy: best at 3 × 8 × 8 | Improved |
| STFT versus DRCT on cross-subset generalization | STFT · GenImage (cross-subset) | accuracy: Midjourney 89.3 -> 92.3; BigGAN 84.0 -> 85.6 | Improved |
| STFT versus DIRE/DRCT on non-face images | STFT · LSUN Cat/Horse/Bedroom | AUC: 74.48 -> 90.32 (Cat, vs DRCT) | Improved |
Closest papers by meaning
- STD-FD: Spatio-Temporal Distribution Fitting Deviation for AIGC Forgery Identification (ICML 2025 · similarity 0.91)
- Generalizing Deepfake Video Detection with Plug-and-Play: Video-Level Blending and Spatiotemporal Adapter Tuning (CVPR 2025 · similarity 0.88)
- Learning Discriminative Noise Guidance for Image Forgery Detection and Localization (AAAI 2024 · similarity 0.87)
- Exposing the Deception: Uncovering More Forgery Clues for Deepfake Detection (AAAI 2024 · similarity 0.86)
- Face Forgery Video Detection via Temporal Forgery Cue Unraveling (CVPR 2025 · similarity 0.86)
- On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection (NeurIPS 2024 · similarity 0.85)
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.
