Vision Transformer-Based Video Hashing Retrieval for Tracing the Source of Fake Videos

<div>Thumbnails of the datasets. (a) DFS: a dataset for detecting DeepFake of similar (DFS) scene videos. (b) Video splicing: a dataset for detecting video splicing. (c) DAVIS-VI: a dataset for detecting video inpainting based on DAVIS2016.</div>

Security and Communication Networks

fig5

Figure 5

Figure 5: Vision Transformer-Based Video Hashing Retrieval for Tracing the Source of Fake Videos 