3 papers
cs.CV2025
Kronecker Mask and Interpretive Prompts are Language-Action Video Learners
Jingyi Yang, Zitong Yu, Xiuming Ni +2
Contrastive language-image pretraining (CLIP) has significantly advanced image-based vision learning. A pressing topic subsequently arises: how can we effectively adapt CLIP to the…
cs.CV2024
GVformer: Graph Guided Video Vision Transformer for Face Anti-Spoofing
Jingyi Yang, Zitong Yu, Xiuming Ni +2
In videos containing spoofed faces, we may uncover the spoofing evidence based on either photometric or dynamic abnormality, even a combination of both. Prevailing face anti-spoofi…
cs.CV2024
Generalized Face Anti-spoofing via Finer Domain Partition and Disentangling Liveness-irrelevant Factors
Jingyi Yang, Zitong Yu, Xiuming Ni +2
Face anti-spoofing techniques based on domain generalization have recently been studied widely. Adversarial learning and meta-learning techniques have been adopted to learn domain-…