电子科技学刊2025,Vol.23Issue(3):56-70,15.DOI:10.1016/j.jnlest.2025.100325
CLIP-IML:A novel approach for CLIP-based image manipulation localization
CLIP-IML:A novel approach for CLIP-based image manipulation localization
摘要
关键词
Image manipulation localization/Multi-scale feature/Pre-trained model/Vision-language model/Vision TransformerKey words
Image manipulation localization/Multi-scale feature/Pre-trained model/Vision-language model/Vision Transformer引用本文复制引用
Xue-Yang Hou,Yilihamu Yaermaimaiti,Shuo-Qi Cheng..CLIP-IML:A novel approach for CLIP-based image manipulation localization[J].电子科技学刊,2025,23(3):56-70,15.基金项目
This work was supported by the Natural Science Foundation of Xinjiang Uygur Autonomous Region under Grant No.2023D01C21 and the National Natural Science Foundation of China under Grant No.62362063. ()