Conference
2026
ForgerySpotter: Pinpointing Tampered Regions with Multi-scale Evidence and Confidence-Guided Refinement
This paper proposes a unified framework that incorporates multi-dimensional feature extraction, multi-scale feature fusion, and a confidence-guided refine mechanism that achieves state-of-the-art performance and shows strong generalization, validating its effectiveness and practicality.
Xiaolong Cheng
· Poster Volume 0007 The 2026... · 0 citations