Open access
Sep 2026
Manipulation-equivariant evidence-state learning for multimodal fake news detection
MEEL (Manipulation-Equivariant Evidence Learning) learns typed directions of manipulation-induced evidence-state movement under a fixed-evidence setting, and learns the movement of evidence states under semantic manipulation, beyond static image-text compatibility.
Hong-Yu Jin, Ming-Shu Zhang, Wei Bin et al.
· Journal of King Saud Univers... · 0 citations