EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2026
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866911488048889856 |
|---|---|
| author | Mai, Hung Dinh, Loi Nguyen, Duc Hai Do, Dat Doan, Luong Quoc, Khanh Nguyen Vu, Huan Islam, Naeem Ul Do, Tuan |
| author_facet | Mai, Hung Dinh, Loi Nguyen, Duc Hai Do, Dat Doan, Luong Quoc, Khanh Nguyen Vu, Huan Islam, Naeem Ul Do, Tuan |
| contents | Recent advances in foundation video generators such as Sora2, Veo3, and other commercial systems have produced highly realistic synthetic videos, exposing the limitations of existing detection methods that rely on shallow embedding trajectories, image-based adaptation, or computationally heavy MLLMs. We propose EA-Swin, an Embedding-Agnostic Swin Transformer that models spatiotemporal dependencies directly on pretrained video embeddings via a factorized windowed attention design, making it compatible with generic ViT-style patch-based encoders. Moreover, we construct the EA-Video dataset, a benchmark dataset comprising 130K videos that integrates newly collected samples with curated existing datasets, covering diverse commercial and open-source generators and including unseen-generator splits for rigorous cross-distribution evaluation. Extensive experiments show that EA-Swin achieves 0.97-0.99 accuracy across major generators, outperforming prior SoTA methods (typically 0.8-0.9) by a margin of 5-20\%, while maintaining strong generalization to unseen distributions, establishing a scalable and robust solution for modern AI-generated video detection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2602_17260 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection Mai, Hung Dinh, Loi Nguyen, Duc Hai Do, Dat Doan, Luong Quoc, Khanh Nguyen Vu, Huan Islam, Naeem Ul Do, Tuan Computer Vision and Pattern Recognition Recent advances in foundation video generators such as Sora2, Veo3, and other commercial systems have produced highly realistic synthetic videos, exposing the limitations of existing detection methods that rely on shallow embedding trajectories, image-based adaptation, or computationally heavy MLLMs. We propose EA-Swin, an Embedding-Agnostic Swin Transformer that models spatiotemporal dependencies directly on pretrained video embeddings via a factorized windowed attention design, making it compatible with generic ViT-style patch-based encoders. Moreover, we construct the EA-Video dataset, a benchmark dataset comprising 130K videos that integrates newly collected samples with curated existing datasets, covering diverse commercial and open-source generators and including unseen-generator splits for rigorous cross-distribution evaluation. Extensive experiments show that EA-Swin achieves 0.97-0.99 accuracy across major generators, outperforming prior SoTA methods (typically 0.8-0.9) by a margin of 5-20\%, while maintaining strong generalization to unseen distributions, establishing a scalable and robust solution for modern AI-generated video detection. |
| title | EA-Swin: An Embedding-Agnostic Swin Transformer for AI-Generated Video Detection |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2602.17260 |