pith. sign in

Uia-vit: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection.ArXiv, abs/2210.12752

2 Pith papers cite this work. Polarity classification is still indexing.

2 Pith papers citing it

fields

cs.CV 2

years

2026 2

verdicts

UNVERDICTED 2

representative citing papers

The Regularizing Power of Language-Training Deepfake Detectors

cs.CV · 2026-05-29 · unverdicted · novelty 7.0

A dual-encoder deepfake detector pairs a frozen specialist with a LoRA-tuned MLLM, trained first via binary alignment then via RL to reward explain-then-classify behavior, yielding improved cross-dataset performance and interpretability.

citing papers explorer

Showing 2 of 2 citing papers.

  • The Regularizing Power of Language-Training Deepfake Detectors cs.CV · 2026-05-29 · unverdicted · none · ref 74

    A dual-encoder deepfake detector pairs a frozen specialist with a LoRA-tuned MLLM, trained first via binary alignment then via RL to reward explain-then-classify behavior, yielding improved cross-dataset performance and interpretability.

  • Robust Deepfake Detection, NTIRE 2026 Challenge: Report cs.CV · 2026-04-27 · unverdicted · none · ref 96

    The NTIRE 2026 challenge finds that large foundation models combined with ensembles and degradation-aware training produce the most robust deepfake detectors.