Abstract
This project aims to detect the differences between a pair of images in the domain of media manipulation, while also deducing the implications of these alterations. In contrast to regular pictures, edited media images always contain complicated contexts, wherein the edits can thoroughly change the stories they depict. Hence, we explore an approach to encode images into natural language and infer the modifications based on the captions of the source image and the edited image.
Members
- Li Guanzhen (Current Master’s Student)
- Yuxi Xie (PhD Student)
- Min-Yen Kan (Professor and Advisor)