Can I read Towards More General Video-Based Deepfake Detection Through Facial Component Guided Adaptation For Foundation Model on EtoBox?
Towards More General Video-Based Deepfake Detection Through Facial Component Guided Adaptation For Foundation Model by amalmohan480 is a document available to read on EtoBox.
What is Towards More General Video-Based Deepfake Detection Through Facial Component Guided Adaptation For Foundation Model about?
The document presents a novel approach for video-based deepfake detection using a side-network-based decoder that incorporates spatial and temporal modules, enhancing generalizability and efficiency. By leveraging the CLIP image encoder and introducing Facial Component Guidance (FCG), the method focuses on key facial regions to improve detection accuracy. Experimental results demonstrate that this approach outperforms state-of-the-art methods in cross-dataset evaluations while being robust and data-efficien
- Author
- amalmohan480
- Language
- EN