Learning Rich Features for Image Manipulation Detection
CVPR, pp. 1053-1061, 2018.
Image manipulation detection is different from traditional semantic object detection because it pays more attention to tampering artifacts than to image content, which suggests that richer features need to be learned. We propose a two-stream Faster R-CNN network and train it end-to-end to detect the tampered regions given a manipulated im...More
PPT (Upload PPT)