The rapid advancement of generative AI has enabled highly realistic image manipulations, posing challenges to trustworthy media analysis. Existing multimodal forgery detection methods often rely on single-stage fusion and one-shot generation, failing to establish reliable cross-modal grounding and leading to inconsiste...
Yi-Lin Wang, Da-Wei Luo, Shuai Chen et al.· 0 citations
A dual supportability audit is proposed that filters privileged cues before distillation, preventing unsupported details from leaking into the student and significantly raising explanation faithfulness compared to existing paradigms.
Bin-Jia Zhou, Da-Wei Luo, Shuai Chen et al.· 0 citations
The Frequency-Aware Multi-Label Learning Network (FMCerNet), a tile-level feature extractor equipped with a Large-Field Frequency-Enhanced ViT backbone and a Coarse-to-Fine multi-label classification head that improves the accuracy of positive screening and fine-grained subtype classification while maintaining high inf...
Lin-Yun Zhou, Qiu-Yu Cai, Xiao-Ling Wang et al.· Bioinformatics· 0 citations
RippleNet is proposed, an AI-generated image detection framework based on local differential signals that adaptively identifies forgery-sensitive regions and constructs multi-directional, multi-scale differential representations within local neighborhoods, explicitly characterizing anomalous patterns in neighborhood st...
Jia-Zhen Yang, Ruijin Jin, Junjun Zheng et al.· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.