TruEye presents a mask-conditioned dual-stream transformer for fine-grained five-category detection and localization of AI-generated humans in images, claiming superior accuracy and speed over prior detectors on six datasets plus a new FineSyn dataset.
arXiv preprint arXiv:2306.02412 (2023),https: //arxiv.org/abs/2306.02412, accessed: Nov 2025
2 Pith papers cite this work. Polarity classification is still indexing.
2
Pith papers citing it
years
2026 2verdicts
UNVERDICTED 2representative citing papers
Develops a bi-form framework unifying contrast and pre-contrast functions on torsion-full Lauritzen manifolds and constructs a canonical contrast bi-form on dually curvature-free cases.
citing papers explorer
-
TruEye: Fine-Grained Detection of AI-Generated Human Subjects in Images
TruEye presents a mask-conditioned dual-stream transformer for fine-grained five-category detection and localization of AI-generated humans in images, claiming superior accuracy and speed over prior detectors on six datasets plus a new FineSyn dataset.
-
Potential functions in information geometry via bi-forms
Develops a bi-form framework unifying contrast and pre-contrast functions on torsion-full Lauritzen manifolds and constructs a canonical contrast bi-form on dually curvature-free cases.