Frame Selection Strategies for Video Deepfake Detection: Benchmarking Accuracy and Runtime Trade-Offs
Applied Sciences · 27.05.2026 · 16 (11) · 5364
DOI: 10.3390/app16115364 ↗Kurz gefasst
Fachartikel in der Zeitschrift Applied Sciences, online erschienen am 27.05.2026. Verfasst von Artūras Serackis und 3 weiteren Autor:innen. Die Arbeit nennt 36 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Economic Revitalization and Resilience Enhancement Plan “New Generation Lithuania”.
Abstract (Originalsprache)
This study evaluates frame selection during inference as an independent factor in video deepfake detection while keeping the downstream detectors fixed. We compare twelve frame selection strategies, ranging from simple temporal and quality baselines to landmark aware policies, using four validated pretrained detectors: Self-Blended Images (SBIs), Frequency-Enhanced Self-Blended Images (FSBIs), Generative Convolutional Vision Transformer (GenConViT), and GenD. The primary experiment is a complete factorial benchmark with 300 videos and five frame budgets (2, 4, 8, 16, and 32 selected frames), which provides the reference results at 32 frames. To address sample size limitations, an additional validation experiment uses a deduplicated split of 1180 Celeb-DF++ and FaceForensics++ videos, with complete results for 2, 4, and 8 selected frames and a reported subset for 16 selected frames. In the complete 300-video benchmark, 32 frames achieved the strongest average AUC, while 8 and 16 frames recovered most of the attainable performance with lower runtime. The best single validated configuration was GenD with Shot-aware sampling at 32 frames, yielding an AUC of 0.9607 and a balanced accuracy of 0.9133. The study therefore does not claim that smaller budgets universally outperform 32 frames; instead, it quantifies the tradeoff between accuracy and runtime and shows that frame selection remains a meaningful design variable under constrained inference budgets.
Förderung
- Economic Revitalization and Resilience Enhancement Plan “New Generation Lithuania”
Zitieren
APA
Serackis, A., Jankauskas, M., Grubinskienė, A., & Abromavičius, V. (2026). Frame Selection Strategies for Video Deepfake Detection: Benchmarking Accuracy and Runtime Trade-Offs. Applied Sciences, 16(11), 5364. https://doi.org/10.3390/app16115364
Vancouver
Serackis A, Jankauskas M, Grubinskienė A, Abromavičius V. Frame Selection Strategies for Video Deepfake Detection: Benchmarking Accuracy and Runtime Trade-Offs. Applied Sciences. 2026;16(11):5364. doi:10.3390/app16115364
BibTeX
@article{Serackis2026,
author = {Serackis, Artūras and Jankauskas, Mindaugas and Grubinskienė, Anastasija and Abromavičius, Vytautas},
title = {Frame Selection Strategies for Video Deepfake Detection: Benchmarking Accuracy and Runtime Trade-Offs},
journal = {Applied Sciences},
year = {2026},
volume = {16},
number = {11},
pages = {5364},
doi = {10.3390/app16115364}
}
EUVIMED