Research map / Video / Video segmentation and tracking
Face Forensics in the Wild
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Use the discriminative attention model instead of I3D | Face forgery detection · FFIW-10K test | AUC (%): 69.5 -> 70.9 | Helped |
| Train the proposed model on FFIW-10K rather than FF++ | Face forgery classification · DFDC Preview test | AUC (%): 72.8 -> 74.1 | Helped |
| Train the proposed model on FFIW-10K rather than FF++ | Face forgery classification · Celeb-DF test | AUC (%): 75.3 -> 78.3 | Helped |
| Train the proposed model on FFIW-10K rather than FF++ | Face forgery classification · FF++ test | AUC (%): 99.5 -> 99.3 | Hurt |
| Replace multi-temporal-scale instance aggregation with max-pooling (ablation) | Ours · FFIW-10K test | AUC (%): 70.9 -> 66.2 | Hurt |
| Replace multi-temporal-scale instance aggregation with avg-pooling (ablation) | Ours · FFIW-10K test | AUC (%): 70.9 -> 65.7 | Hurt |
| Add short-term aggregation (ablation) | Ours · FFIW-10K test | AUC (%): 69.7 -> 70.9 | Helped |
| Add long-term aggregation (ablation) | Ours · FFIW-10K test | AUC (%): 70.4 -> 70.9 | Helped |
| Replace attention-based bag aggregation with max-pooling (ablation) | Ours · FFIW-10K test | AUC (%): 70.9 -> 69.5 | Hurt |
| Replace attention-based bag aggregation with avg-pooling (ablation) | Ours · FFIW-10K test | AUC (%): 70.9 -> 66.8 | Hurt |
| Add sparsity regularization loss (ablation) | Ours · FFIW-10K test | mAP (%): 28.5 -> 30.8 | Helped |
| Add sparsity regularization loss (ablation) | Ours · FFIW-10K test | AUC (%): 70.3 -> 70.9 | Helped |
Closest papers by meaning
- Face Forgery Video Detection via Temporal Forgery Cue Unraveling (CVPR 2025 · similarity 0.88)
- Identity-Aware Vision-Language Model for Explainable Face Forgery Detection (AAAI 2026 · similarity 0.88)
- Forensics Adapter: Adapting CLIP for Generalizable Face Forgery Detection (CVPR 2025 · similarity 0.87)
- Towards General Visual-Linguistic Face Forgery Detection (CVPR 2025 · similarity 0.87)
- Rethinking Vision-Language Model in Face Forensics: Multi-Modal Interpretable Forged Face Detector (CVPR 2025 · similarity 0.87)
- DevFD : Developmental Face Forgery Detection by Learning Shared and Orthogonal LoRA Subspaces (NeurIPS 2025 · similarity 0.87)
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.