Metraipolis › archive › dc_533158cc55bb
MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection — arXiv:2611.12508
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2611.12508
- License (as archived)
- CC0-1.0
- Archived
- 2026-11-10T18:44:09.674Z
- SHA-256 of the archived text
a0ca4c2071c8dabb988aafa1f87da03b08b61f2dd73a2e86cc652fab0f859044- Stable URL of this page
https://metraipolis.com/documento/dc_533158cc55bb
How to cite
MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection — arXiv:2611.12508 — arXiv (en), https://arxiv.org/abs/2611.12508 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_533158cc55bb (Metraipolis archive dc_533158cc55bb, sha256 a0ca4c2071c8dabb988aafa1f87da03b08b61f2dd73a2e86cc652fab0f859044)
BibTeX
@misc{dc533158cc55bb,
title = {MARS: Multiscale Appearance-Residual Streams for Video Forgery Detection — arXiv:2611.12508},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2611.12508},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_533158cc55bb; sha256 a0ca4c2071c8dabb988aafa1f87da03b08b61f2dd73a2e86cc652fab0f859044},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2611.12508. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Generalizing deepfake detection across facial manipulation and fully generated video remains challenging due to forgery traces varying with the manipulation method and scene content. Explicit spatial and temporal feature differences offer a way to capture this variation, but also respond to natural texture and motion, motivating their joint interpretation with appearance features. We investigate whether combining multiscale feature differences with adapted appearance representations improves detection across both forgery categories. We introduce Multiscale Appearance-Residual Streams (MARS), a two-path video detector. The residual path applies fixed spatial and temporal difference-of-Gaussians operators to frozen intermediate features and models the resulting differences alongside appearance context across frames. The semantic path adapts the encoder's normalization parameters for frame classification, and a clip-dependent gate combines their predictions. Under a shared protocol across seven datasets, MARS achieves the highest average AUROC of 91.43\%, outperforming seven compared detectors. When trained on facial manipulations alone, MARS achieves 93.99\% AUROC on GenVideo and 75.50\% on DF26, demonstrating transfer to generated videos without generated-video training data. MARS also provides signed patch and frame contributions, whose faithfulness we evaluate through controlled spatial and temporal removal against random controls. MARS is publicly available for research: Project page: this https URL Github: this https URL Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.AI, nuovi lavori del giorno). Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI). Pagina del lavoro: https://arxiv.org/abs/2611.12508 — 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 2026-11-10T18:37:37.696Z dalla pagina https://arxiv.org/list/cs.AI/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).