AMID: Audio–visual deepfake detection via adaptive multi-dimensional interaction modeling
- 16 May 2026
- journal article
- Published by Elsevier in Knowledge-Based Systems
- Vol. 346
Abstract
No abstract availableFunding Information
- Natural Science Foundation of Jiangsu Province (BK20180080)
- National Natural Science Foundation of China (62371469)
- National Natural Science Foundation of China (62071484)
This publication has 25 references indexed in Scilit:
- Co-space Representation Interaction Network for multimodal sentiment analysisKnowledge-Based Systems, 2023
- ImageBind One Embedding Space to Bind Them All2023
- Audio-Visual Person-of-Interest DeepFake Detection2023
- AVFakeNet: A unified end-to-end Dense Swin Transformer deep learning model for audio–visual deepfakes detectionApplied Soft Computing, 2023
- Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection2022
- Video Swin Transformer2022
- Multi-attentional Deepfake Detection2021
- Deepfakes and beyond: A Survey of face manipulation and fake detectionInformation Fusion, 2020
- A Style-Based Generator Architecture for Generative Adversarial Networks2019
- Face2Face: Real-Time Face Capture and Reenactment of RGB Videos2016