MSCT: Differential Cross-Modal Attention for Deepfake Detection
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2026
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866913018269401088 |
|---|---|
| author | Wei, Fangda Liu, Miao Wang, Yingxue Wang, Jing Zhao, Shenghui Li, Nan |
| author_facet | Wei, Fangda Liu, Miao Wang, Yingxue Wang, Jing Zhao, Shenghui Li, Nan |
| contents | Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily extract forgery traces through audio-visual alignment, which results from the inconsistency between audio and video modalities. However, the traditional multi-modal forgery detection method has the problem of insufficient feature extraction and modal alignment deviation. To address this, we propose a multi-scale cross-modal transformer encoder (MSCT) for deepfake detection. Our approach includes a multi-scale self-attention to integrate the features of adjacent embeddings and a differential cross-modal attention to fuse multi-modal features. Our experiments demonstrate competitive performance on the FakeAVCeleb dataset, validating the effectiveness of the proposed structure. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2604_07741 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | MSCT: Differential Cross-Modal Attention for Deepfake Detection Wei, Fangda Liu, Miao Wang, Yingxue Wang, Jing Zhao, Shenghui Li, Nan Computer Vision and Pattern Recognition Multimedia Audio-visual deepfake detection typically employs a complementary multi-modal model to check the forgery traces in the video. These methods primarily extract forgery traces through audio-visual alignment, which results from the inconsistency between audio and video modalities. However, the traditional multi-modal forgery detection method has the problem of insufficient feature extraction and modal alignment deviation. To address this, we propose a multi-scale cross-modal transformer encoder (MSCT) for deepfake detection. Our approach includes a multi-scale self-attention to integrate the features of adjacent embeddings and a differential cross-modal attention to fuse multi-modal features. Our experiments demonstrate competitive performance on the FakeAVCeleb dataset, validating the effectiveness of the proposed structure. |
| title | MSCT: Differential Cross-Modal Attention for Deepfake Detection |
| topic | Computer Vision and Pattern Recognition Multimedia |
| url | https://arxiv.org/abs/2604.07741 |