activity
20242026
collaborators

5 papers

cs.CV2026

Unleashing Vision-Language Semantics for Deepfake Video Detection

Jiawen Zhu, Yunqi Miao, Xueyi Zhang +2

Recent Deepfake Video Detection (DFD) studies have demonstrated that pre-trained Vision-Language Models (VLMs) such as CLIP exhibit strong generalization capabilities in detecting…

cs.CV2025

Interact2Ar: Full-Body Human-Human Interaction Generation via Autoregressive Diffusion Models

Pablo Ruiz-Ponce, Sergio Escalera, José García-Rodríguez +2

Generating realistic human-human interactions is a challenging task that requires not only high-quality individual body and hand motions, but also coherent coordination among all i…

cs.CV2024

Unified Physical-Digital Attack Detection Challenge

Haocheng Yuan, Ajian Liu, Junze Zheng +6

Face Anti-Spoofing (FAS) is crucial to safeguard Face Recognition (FR) Systems. In real-world scenarios, FRs are confronted with both physical and digital attacks. However, existin…

cs.CV2024

CFPL-FAS: Class Free Prompt Learning for Generalizable Face Anti-spoofing

Ajian Liu, Shuai Xue, Jianwen Gan +5

Domain generalization (DG) based Face Anti-Spoofing (FAS) aims to improve the model's performance on unseen domains. Existing methods either rely on domain labels to align domain-i…

cs.CV2024

Unified Physical-Digital Face Attack Detection

Hao Fang, Ajian Liu, Haocheng Yuan +8

Face Recognition (FR) systems can suffer from physical (i.e., print photo) and digital (i.e., DeepFake) attacks. However, previous related work rarely considers both situations at…