Metraipolis › archive › dc_4dc27583a397

Learning Unified Video and Image Representation for Video Face Forgery Detection — arXiv:2608.13064

Source
arXiv (en)
Original
https://arxiv.org/abs/2608.13064
License (as archived)
CC0-1.0
Archived
2026-10-19T04:55:44.407Z
SHA-256 of the archived text
62d3bf8dfd057ebbfa460f194513208bbca4d0e2a395c7ea77942fb0229a8c0c
Stable URL of this page
https://metraipolis.com/documento/dc_4dc27583a397

How to cite

Learning Unified Video and Image Representation for Video Face Forgery Detection — arXiv:2608.13064 — arXiv (en), https://arxiv.org/abs/2608.13064 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_4dc27583a397 (Metraipolis archive dc_4dc27583a397, sha256 62d3bf8dfd057ebbfa460f194513208bbca4d0e2a395c7ea77942fb0229a8c0c)
BibTeX
@misc{dc4dc27583a397,
  title = {Learning Unified Video and Image Representation for Video Face Forgery Detection — arXiv:2608.13064},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2608.13064},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_4dc27583a397; sha256 62d3bf8dfd057ebbfa460f194513208bbca4d0e2a395c7ea77942fb0229a8c0c},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2608.13064. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

Face forgery detection is crucial for preserving the security and integrity of facial data given the rapid developments in face manipulation techniques and deep generative models. Existing methods for video face forgery detection typically assume that all frames in a forged video are manipulated, while detecting partially forged videos that contain only a subset of altered frames remains challenging. To address this issue, we propose a novel framework, UVIF, that utilizes additional annotated images to provide fine-grained supervision for detecting partial forgeries in videos. UVIF employs a unified encoder and a multi-task learning paradigm to jointly model facial videos and images for boosted video face forgery detection. A 2D backbone with temporal fusion modules is employed as the unified encoder. A pseudo labeling process is designed for video frames to bridge their representations with those of static images. A video-oriented feature alignment strategy is further introduced to reduce the distribution gap between videos and images. Extensive experiments on benchmark datasets demonstrate the effectiveness of our framework, which outperforms state-of-theart methods in detecting partially forged videos while introducing no additional computational overhead. Our code is available at this https URL .

Tema degli esploratori: statistica e scienza dei dati (retro-catalogo arXiv: annunci del 2026-08-14 in cs.CV).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV).
Pagina del lavoro: https://arxiv.org/abs/2608.13064 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-19T04:46:30.150Z dalla pagina https://arxiv.org/catchup/cs.CV/2026-08-14?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).