MOTIF: Person-of-Interest Deepfake Detection Beyond 3DMM Coefficients
cs.CV
Submitted: 2026-10-07
Updated: 2026-10-07
Comments: 6 pages. Accepted at the 2026 IEEE International Workshop on Information Forensics and Security (WIFS)
Code: https://github.com/polimi-ispl/MOTIF
License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
Sources
- ExposeAnyone: Personalized Audio-to-Expression Diffusion Models Are Robust Zero-Shot Face Forgery Detectors
- DeepFakes: a New Threat to Face Recognition? Assessment and Detection
Related papers
- Loss Knows Best: Detecting Annotation Errors in Videos via Loss Trajectories
- AnchorWeave: World-Consistent Video Generation with Retrieved Local Spatial Memories
- Benchmarking the Robustness of Foundation Models for Mammography under Domain Shift
- MambaX-Net: Dual-Input Mamba-Enhanced Cross-Attention Network for Longitudinal MRI Segmentation
- TeleOCR: Navigating Document Parsing Across Digital and Camera-Captured Documents
- A Survey on Efficient Vision-Language-Action Models