← Search

Wanyi Zhuang

2 accepted papers

2024

Exploiting Modality-Specific Features for Multi-Modal Manipulation Detection and Grounding

ICASSP 2024accepted

AI-synthesized text and images have gained significant attention, particularly due to the widespread dissemination of multi-modal manipulations on the internet, which has resulted in numerous negative impacts on society. Existing methods for multi-modal manipulation detection and grounding primarily…

Cited by 0SourceScholar
2022

UIA-ViT: Unsupervised Inconsistency-Aware Method Based on Vision Transformer for Face Forgery Detection

ECCV 2022poster

"Intra-frame inconsistency has been proved to be effective for the generalization of face forgery detection. However, learning to focus on these inconsistency requires extra pixel-level forged location annotations. Acquiring such annotations is non-trivial. Some existing methods generate large-scale…